DEVELOPMENT OF A HYBRID PLATFORM FOR THUMBPRINT FORENSICS

Size: px
Start display at page:

Download "DEVELOPMENT OF A HYBRID PLATFORM FOR THUMBPRINT FORENSICS"

Transcription

1 DEVELPMENT F A HYRID PLATFRM FR THUMPRINT FRENSICS luwole Charles Akinyokun 1, Cleopas fficer Angaye, abatunde Gabriel Iwasokun 1 1 Department of Computer Science, Federal University of Technology, Akure, Nigeria National Information Technology Development Agency (NITDA), Abuja, Nigeria akinwole003@yahoo co.uk; cangaye@hotmail.com; maxtunde@yahoo.com ASTRACT. Thumbprint has remained the most commonly used technique for biometric identification in the world today. Research activities on the improvement of the theory and practice of thumbprint forensics have, therefore continued to be a major task in the world today. The research which is reported in this paper takes a study of the features of the existing and popular research activities on the theory and practice of thumbprint forensics, analyzed their Strengths, Weaknesses, pportunities and Threats (SWT) and proposed a hybrid system for thumbprint forensics which integrates the strengths and opportunities. The hybrid system is characterized by an architecture which is composed of database of thumbprint profile, data mining engine and decision support engine. The data mining engine is composed of thumbprint image enhancement, thumbprint minutiae extraction, database of thumbprint minutiae extraction, thumbprint pattern recognition and thumbprint pattern matching. The decision support engine is composed of error detection and error correction subsystems. Keywords: Forensics, iometrics, Thumbprint, Minutiae, Segmentation, Normalization, inarization 1 INTRDUCTIN Thumbprints are the results of minute ridges and valleys found on the thumb of every person. It is an impression of the friction ridges of all or any part of the thumb. A friction ridge is a raised portion of the epidermis on the palmar (palm and thumbs) or plantar (sole and toes) skin, consisting of one or more connected ridge units of friction ridge skin. Thumbprint is also an impression of the coetaneous ridges of the fleshy distal portion of a thumb, which may be obtained by applying ink and pressing the thumb on paper. Each print has an exclusive owner, and there has never been two individuals recorded with the same print [1, ]. The ridges of thumb form patterns of loops, whorls and arches [3, 4, 5, 6, 7]. 183

2 Figure 1.1: Comparative Analysis of iometrics Identifications The result of the survey conducted by the International iometric Group (IG) in 004 as presented in Figure 1.1 confirms that thumbprint identification is a more widely used technique of biometric identification in the world today [8].The principle and practice of thumbprint forensics are concerned with pattern recognition and matching. In [9], the features of the existing and popular techniques of pattern recognition and matching; namely: template technique, prototype technique, feature based technique and computational technique were presented. In [10, 11, 1, 13, 14, 15, 16, 17, 18, 19], thumbprint forensics which adopts some of the techniques for pattern recognition and matching were reported. The features of the research activities of these listed authorities were studied and their strengths were integrated to form the basis of the proposed hybrid system for thumbprint forensics. The architecture of the hybrid system is composed of the database of thumbprint profile, data mining engine and decision support engine. The data mining engine is composed of thumbprint image enhancement, thumbprint minutiae extraction, database of thumbprint minutiae extraction, thumbprint pattern recognition and thumbprint pattern matching. The decision support engine is composed of error detection and error correction subsystems. ARCHITECTURE F THUMPRINT FRENSICS The conceptual diagram of the proposed architecture of thumbprint forensics is presented in Figure.1. It is composed of database of thumbprint profile, data mining engine and decision support engine. 184

3 P Acquisition of Thumbprints Acquisition of other iometric Data Database of Thumbprint Image Enhancement Image Segmenta Normaliza tion Gabor Filter inarizati on/thinn ing Thumbprint Data Mining Engine Thumbprint Minutiae Mathematic al Model 3CF Databas e of Extracte d Thumbprint Pattern Similarity Score Calculati on Dissimila r Formula Thumbprint Pattern Matching Multipath method Minimu m Cost Flow method 3CF: Chain Coded Contour Following FMR: False Match Rate Decision Support Engine Error Error Detectio Correctio n FMR Cognitive n Filter FNMR Emotion al Filter Decision Making Figure.1: Architecture of Thumbprint Forensics 185

4 .1 Database of Thumbprint Profile The building of thumbprint profile database starts with the acquisition of all relevant data and the major tasks are the following: Thumbprint enrollment. Acquisition of facial image of the person whose thumbprint is being captured. Collection of other relevant biometric data. The success of thumbprint processing depends greatly on the quality of the thumbprint image. Consequently, a high quality digital thumbprint scanner that will produce low noise and low contract deficiency images is used for the enrollment. A digital camera with a high resolution and pixel configurations is used for the acquisition of facial images. ther relevant biometric data that are desirable for the verification and validation of a person s unique identification are names, signature, complexion, height, colour of eyes (Irish), tribe, date of birth, age, blood group, marital status, thumbprint pattern type and features (end point, bifurcation point or island, cross over, lake, independent ridge and so on).. Data Mining Engine The data mining engine is responsible for the extraction of the needed features from the captured thumbprints and the processing of these features to obtain aggregate data which could assist in taking notable decisions on the degree of resemblance or similarity of the captured thumbprints. The data mining engine is composed of the following: Thumbprint image enhancement. Thumbprint minutiae extraction. Database of extracted thumbprint minutiae. Thumbprint pattern recognition. Thumbprint pattern matching...1 Thumbprint Image Enhancement The process of thumbprint image enhancement has the following phases: a. Image Segmentation: It is the process of separating the foreground regions in the image from the background regions. The foreground regions correspond to the clear thumbprint area containing the ridges and valleys, which is the area of interest. The background corresponds to the regions outside the borders of the thumbprint area, which do not contain any valid thumbprint information. When minutiae extraction algorithms are applied to the background regions of an image, it results in the extraction of noisy and false minutiae. Thus, segmentation 186

5 is employed to discard these background regions for the purpose of obtaining fine and reliable extraction of thumbprint minutiae. In a thumbprint image, the background regions generally exhibit a very low greyscale variance value, whereas the foreground regions have a very high variance. Hence, a method based on variance threshold is used to perform the segmentation. Firstly, the image is divided into blocks and the grey-scale variance is calculated for each block in the image. If the variance is less than the global threshold, then the block is assigned to a background region; otherwise, it is assigned to the foreground region. The grey-level variance for a block of size W x W is defined as: 1 V ( k) W W 1W 1 i 0 j 0 ( I ( i, j) M ( k)) (.1) where V (k) is the variance for block k, I(i, j) is the grey-level value at pixel (i, j), and M(k) is the mean grey-level value for the block k. b. Image Normalization: It is used to standardize the intensity values in an image by adjusting the range of grey-level values so that it lies within a desired range of values. If I(i, j) represents the grey-level value at pixel (i, j), and N(i, j ) represents the normalized grey-level value at pixel (i, j ). The normalized image is defined as: M o N( i, j) M o V o V o ( I ( i, j) M V ( I( i, j) M ) V ) if I( i, j) M if otherwise...(.) where M and V are the estimated mean and variance of I(i, j) respectively, M 0 and V 0 are the values of the desired mean and variance, respectively. Normalization does not change the ridge structures in a thumbprint. It is performed to standardize the dynamic levels of variation in grey-level values, which facilitates the processing of subsequent image enhancement stages. 187

6 c. Application of Gabor Filter: Gabor filter which is a very useful tool for analysis in spatial or frequency domain [16] is adopted in this phase. It is applied for the enhancement of the segmented thumbprint images. It has both frequency selective property and orientation selective property. It also has optimal joint resolution in both spatial and frequency domain. It is used to further improve the segmented thumbprint image by removing noise and preserving the true ridge and valley structures. The general form of Gabor filter is: / x / 1 y G( x, y : f, ) exp x y / cos(fx )...(.3) where f is the frequency of the sinusoidal plane wave along the direction θ from the x-axis, and δ x and δ y are the space constants along x and y axes respectively. The values of the space constants δ x and δ y for the Gabor filters were empirically determined as each is set to about half the average inter-ridge distance in their respective direction. In addition, x = xsin + ycos and y = xcos + ysin. d. Image inarization/thininng: The image obtained from the application of the Gabor filter is binarized or thinned to obtain its best performance threshold. The tsu method of image binarization proposed in [19] is employed. The tsu Method sets the threshold (T) for making each cluster as tight as possible, thereby minimizing their overlap. To determine the actual value of T, the following operations are performed on a set of presumed threshold values: i. The pixels are separated into two clusters according to the threshold. ii. The mean of each cluster are determined. iii. The difference between the means is squared. iv. The product of the number of pixels in one cluster and the number in the other is determined. The success of these operations depends on the difference between the means of the clusters. The optimal threshold is the one that maximizes the between-class variance or, conversely, the one that minimizes the within-class variance. The within-class variance of each of the cluster is calculated as: 188

7 within where T n ( T ) p( i)...(.5) i0 N 1 n ( T ) p( i)...(.6) it ( T ) the var iance of the pixels in the background ( below) threshold ( T ) n ( T ) ( T ) T 1 n ( T ) ( T )...(.4) the var iance of the pixels in the foreground ( above) threshold between p(i) is the pixel value at location i, N is the intensity level and [0,N 1] is the range of intensity levels. The between-class variance, which is the difference between the within-class variance and the total variance of the combined distribution, is then obtained from: T T n ( T ) ( T ) n ( T ) ( T )...(.7) within where σ is the combined variance and µ is the combined mean. The betweenclass variance is simply the weighted variance of the cluster means themselves around the overall mean. Substituting µ = n(t)µ(t) +n(t)µ(t) and simplifying further, the result is: between T n ( T ) n ( T ) ( T ) ( T )...(.8) Using recurrence relations, the between-class variance is updated as each threshold is successfully tested by using the following formula: n n ( T 1) ( T 1) ( T 1) ( T 1) n n ( T ) n ( T ) n ( T ) n ( T ) ntt n ( T 1) ( T ) n n T T ( T ) n T ( T 1) T...(.9)...(.10)...(.11)...(.1) 189

8 .. Thumbprint Minutiae Extraction The following alternative methods are proposed for the extraction of thumbprint: a. Mathematical model: A mathematical model that hinges on the assumption that the pixel is on a thinned image (eight-connected) and has a value of one and zero otherwise as presented in [11] is used. The mathematical model uses (x, y) to denote a pixel on a thinned ridge and N 0, N 1,, N 7 to denote its neighbours. Then pixel (x, y) is considered as a ridge ending if: 7 N i i0 1 (.13) and as a ridge bifurcation if: 7 N i i0 (.14) With these steps, the algorithm is to identify and extract most of the minutiae present in the thinned image. The extracted thumbprint minutiae will be stored in a database before they are subjected to pattern recognition. b. Chain Code ased Minutiae Extraction: The conventional minutiae extraction algorithms are based on thinning and iterative process which are computationally expensive and produce artifacts such as spurs and bridges. To avoid this problem, a chain coded contour tracing method is proposed. In the chain code based minutiae extraction, chain coded contour following (3CF) method where the ridges and valleys of a thumbprint in a -dimentional representation are represented in contours is used for thumbprint minutiae extraction [17]. A wide range of information such as curvature, direction and length are derived from the contours. To obtain the minutiae from the contours, the ridges are traced consistently in anti-clockwise direction for the purpose of exhibiting the following features: i. Minutiae points which are considered as places where the contour has a significant turn. ii. Ridge end which is a significant left turn in the contour iii. ifurcation which is a significant right turn in the contour. 190

9 The turning direction is determined by taking into consideration the sign of the cross product of the incoming and outgoing vectors at each point. The sign of the cross product is obtained from: sgn( Pin x Pout sgn( x1 y x y1)...(.15) where P in is the incoming vector, P out is the outgoing vector and x 1 y and x y 1 define the pixel locations of the vectors. The product is right handled if the sign is positive and left handled if the sign is negative as shown in Figure.. (a) (b) (c) Figure.: (a) Minutiae marked by significant turn in the contour (b) Left turn (c) Right turn The turn is only significant if x 1 y 1 + x y is less than or equals to a small threshold value T. No matter what type of turning points are detected, if the angle between the leading in and out of a vector for the interested point is greater than 90 o, then, the threshold T is chosen to have a small value. The angle can be calculated by using dot product of the two vectors given by: arccos P. in Pout P. in Pout (.16) The extracted minutiae will be stored in a database before they are subjected to pattern recognition. 191

10 ..3 Database of Extracted Thumbprint Minutiae A database of the extracted minutiae is created to serve as repository of the minutiae that were extracted from a thumbprint. The minutiae database assumes a relational model to give room for defining the relationships among the minutiae from different thumbprints. It is also used for effective and dynamic minutiae storage pattern. The dynamic nature of the database gives room for an open end so that continuous growth of the database is not prevented. The data are stored in tables of related entities such as thumbprint identification number, thumbprint type, type of minutiae and number of extracted minutiae. The data obtained for each thumbprint is assigned a unique identification number that promote collective and effective identification as well as smooth reading during subsequent operations. Let S represents the similarity score; Let height c represents the height of combined fingerprint; Let width c represents the width of combined fingerprint; Let max h represents the maximum possible height; Let max w represents the maximum possible width; Let T m be an integer-valued threshold; If (N < 7 and (height c > max h or width c > max w )) then S = 0; Else If ( a < 5) then a = 5; End if If ( b < 5) then b = 5; End if 19

11 ..4 Thumbprint Pattern Recognition The following two methods are proposed for the pattern recognition of the extracted thumbprint minutiae: a. Similarity Score Calculation: The similarity score will be generated to obtain the degree of similarity of thumbprint minutiae extracted from the thumbprint images. To achieve this objective, minutiae based query I and reference R thumbprint databases are formulated. The following information is then used in the computation of the similarity scores: i. n: the number of matched feature points; ii. size I : the number of feature points on the query I; iii. size R : the number of feature points on the reference R; iv. I : the number of feature points in the overlapping area of query I; v. R : the number of feature points in the overlapping area of reference R; vi. S avg : the average feature distance of all the matched features. Using features such as ridge flows, singular points and scars, the similarity scores for the minutiae-based system is calculated from: n /(size I x size R ) (.17) The details of the heuristic rule for generating similarity scores are presented in Figure.3. b. Dissimilar Score Calculation: It is characterized by dissimilar algorithm for recognizing and identifying thumbprint images using the distances between mid point and the core point of the thumbprint for pattern recognition. Image existing junction points were classified as bi-junctions, tri-junctions and quad-junctions. The classification is also based on the number of lines passing through each image. Distances between these points and the image core were computed and used as recognition features. To minimize the size of the adopted feature data, only the nearest 10-junctions to the core of each type would be considered as proposed in [10]. The following were strictly observed: i. If 10-junctions of any type have not been found then, distances of only those found are calculated and recorded while the rest of the 10-values are defined as zeros. 193

12 ii. To avoid any image rotational effect, the measured features were arranged in a descending order (that is from farthest to nearest to the core point). The following dissimilar formula is used to measure the distances between matched images: DIS 34 P( i) I( i) %( ) 1 ( ) S i i P i...(.18) where, P(i) and I(i) represent preserved and identified image distances respectively. S%(i) are weighting factors assigned for measured matching features as follows: i. S% = 1% for distances of maximum lines in the 4 directions. ii. S% = % for i-junction points. iii. S% = 3% for Tri-junction points. iv. S% = 4% for Quad-junction points. If all the p(i) elements were in existence, the maximum dissimilar coefficient (DIS) will not exceed 94%. Therefore, normalized Cross-Correlation Coefficient (CR) is computed and used to measure the similarity between matched images by using the formula: CR = 1 (DIS/94) (.19) From this formula, in case of exact similar matched images the dissimilar value will be DIS = 0 and, consequently, the cross-correlation will be Thumbprint Pattern Matching: The proposed pattern matching subsystem is expected to take any of the following two methods for its thumbprint pattern matching tasks: a. Multi-path Matching Method: A multi-path matching algorithm includes the following two matching methods: i. rute-force matching 194

13 ii. Secondary feature matching rute force matching is for small number of minutiae query and reference partial thumbprints while secondary feature matching is for the relative larger number of minutiae in query and reference thumbprints. In the multi-path approach to pattern matching of thumbprints shown in Figure.4, a scenario based on the number of minutiae on the query I and the reference R thumbprints in the thumbprint recognition system is used. M and N are taken as the number of minutiae on query and reference thumbprints respectively where α represents a pre-defined threshold value. The brute-force matching system is used if any of the following conditions is met: i. oth number of minutiae on I and R are less than the predefined value α; ii. Either I or R has number of minutiae less than α; and iii. oth I and R contain more than α minutiae. Query Fingerprin t l Minutiae Extraction M > α and Yes Secondary Feature Matching Template Database R No M <= α and Yes rute-force Matching Result No Secondary Feature Extraction No Has a match? Yes Figure.4: Flowchart of rute-force Matching Algorithm rute-force technique will examine all the possible solutions and select the match with the highest number of matches. Each minutia point in R and I are used as reference points. If none of the above conditions is met, secondary feature matching is adopted. Choosing the appropriate matching methods in terms of speed and accuracy is dependent on an empirical threshold (α). The technique involves the following steps: i. Working directly on the minutiae information, all possible correspondences between the minutiae on query I and reference R thumbprints are determined. ii. For each minutiae p i (x i, y i,i ) on I and q j (x j, y j, j ) on R, p i and q j were taken as the matched reference points. 195

14 iii. ther matched minutiae in the polar coordinate system were subsequently determined. b. Minimum Cost Flow (MCF) Method: It is used to provide the matching scenarios with the least cost in terms of minutia detection and matching times. Emphasis will be on the maximum number of matches and the minimum cost. Using MCF technique for matching the feature points on any two thumbprints is equivalent to finding the correspondences between the feature points. When there are two sets of feature points from different thumbprint images, say, I and R and they are already aligned with respect to a pair of reference points in each image, an extra point (node), say the source s, is added into the set of I and add the point (node), say sink (target) t to the set of R. The links (edges) between nodes will be set up by obeying the following rules: i. ne and only one link exists, that connects s to every point in the first set. ii. ne and only one link exists, that connects t to every point in the second set. iv. There is no link between the points within the same set. v. There is exactly one link between every point in first set and every point in the second set. vi. Every link is associated with a capacity and a cost. The cost matrix C i,j which represents the costs of the edge between I and R is defined by: C i, j = dist (I i, R j ) where 1 i N i and 1 j N R given that N i and N R are the numbers of feature points on R and I respectively and also, I i and R j are the feature point on I and R respectively. The function dist(a,b) is the distance measure of two feature points, a and b on I and R, respectively. For efficiency, the edge between I i and R j are removed if I i is not in the tolerance area of R j..3 Decision Support Engine.(.0) The decision support engine of the proposed system is to aid the user in making good decisions based on findings from the thumbprint minutiae pattern recognition and matching. This unit comprises of two subcomponents, namely: Error Detection and Error Correction 196

15 a. Error Detection: The error detection subcomponent is concerned with identifying the errors that feature during thumbprint pattern recognition and matching. Thumbprint pattern recognition and matching system, like any other biometric system, is susceptible to the following two types of error: i. Mistaking thumbprint measurements from two different persons described as false match. ii. Mistaking two thumbprint measurements from same person to be from two different persons describe as false non-match. Due to variations in the image quality, intra-class variations in the thumbprint capture devices, limitations of thumbprint image analysis systems, enhancement methods, feature detection algorithms and matching algorithms, a genuine individual could be mistakenly rejected. Similarly, an imposter individual could be falsely accepted. The rate of mistaking thumbprint measurements from two different persons is called False Match Rate (FMR) while the rate of mistaking two thumbprint measurements from same person to be from two different persons is described as False Non-Match Rate (FNMR). In the system being proposed, there is a tradeoff between the FMR and FNMR. oth FMR and FNMR are functions of the predefined system threshold t. If t is decreased to make the system more tolerant to input variation (that is, match thumbprints on the basis of minimum number of common features) and noise, then FMR increases. n the other hand, if t is raised to make the system more reliable (that is, match thumbprints on the basis of maximum number of common features), then FNMR increases accordingly. The errors in thumbprint pattern recognition and matching as they apply to the system being proposed can be formulated as follows: If the stored thumbprint template of the first person is represented by X I and the enrolled thumbprint for recognition is represented by X Q, the null and alternate hypotheses are: H 0 : enrolled thumbprint X Q does not come from the same person as the template X I H I : enrolled thumbprint X Q comes from the same person as the template X I The following are therefore the associated decisions: D 0 : the template thumbprint X I and the enrolled thumbprint X Q do not come from the same person 197

16 D I : the template thumbprint X I and the enrolled thumbprint X Q are from the same person The following will guide these decisions: If the matching score (X Q, X I ) is less than the system threshold t, then D 0 else D I FMR is the probability of false match while FNMR is the probability of false non-match and given as:.(.1) FMR = P(D I H ) FNMR = P(D 0 H I ) 3.18.(.) 1 FNMR would be defined as the power of the hypothesis test. Therefore, to evaluate the accuracy of the thumbprint pattern recognition system, scores from several images of same thumb (which is the distribution p(s(x Q, X I ) H I )) as well as scores from several images of different thumb (which is the distribution p(s(x Q, X I ) H )) will be collected. FMR and FNMR are then computed from: FMR p ( S ( X Q, X I ) H ) ds t...(.3) FNMR t p( S ( X Q, X I ) H I ) ds...(.4 ) b. Error Correction: The error correction system is characterized by a cognitive filter and an emotional filter. The cognitive filter takes the output of the error detecting unit as input and applies the objective rules in the domain of thumbprint pattern recognition and matching with a view to ranking the alternative output reports of the error detecting unit. The emotional filter takes the output of the cognitive filter as input and applies the subjective rules in the domain of thumbprint pattern recognition and matching with a view to ranking the alternative output reports of the cognitive filter. The final goal is to filter the cognitive and emotional factors that may inhibit sound decision-making on the degree of similarity between two or more thumbprints. During cognitive filtering of the results of thumbprint matching, judgment or decision on errors is based on objective considerations of information existing 198

17 between the thumbprints. This involves a genuine and close observation of empirical data from the thumbprints. Such empirical data could include data from both inductive and deductive logic, similarity score pattern and information from the thumbprints such as the location, the orientation and the position of each print. bjective consideration of errors by inductive and deductive logic involves the use of experience which is the long term residual knowledge regarding past observations from thumbprint matching to fix the errors. It also involves the use of physical evidence such as thumbprint pattern and ridge information, investigative information, and other documentary and testimonial evidence. During emotional filtering of the results of thumbprint matching, judgment or decision made on the detected errors is based on sentiments rather than principles. In this case, the results from thumbprint matching are subjected to emotional considerations before a final decision is taken. For instance the reliability of the recording instrument (scanner), the efficiency of the matching algorithms, the integrity or fairness of the thumbprint pattern recognition and matching team and other personal interests are factors that could determine the final decision on the errors. 3. CNCLUSINS The process of recognizing a pattern involves the identification of a complex arrangement of sensory stimuli. The four distinct techniques of the cognitive perspective of pattern recognition are the Template-Matching technique, Prototype-Matching technique, Feature-ased technique and Computational technique. Each of these techniques has been found to have some strengths, weaknesses, opportunities and threats. Existing and popular research activities have been found to adopt and integrate only a few of these techniques as the driver of their thumbprint forensics. An attempt has been made, in this paper, to present a framework for cognitive perspective of pattern recognition of thumbprint which integrates the strengths of the above listed four techniques and emotional perspective mechanism which is contained in the decision support engine. The experimental study of the proposed hybrid system for thumbprint forensics is currently being carried out with a view to demonstrating its practical function. The environment of the experimental study is characterized by LINUX perating System as the platform, Microsoft Access Database Management System as backend engine and MATLA as front-end engine. References 1. Eckert W. G.: Introduction to Forensic Science ; New York: Elsevier, 1996, pp FIDIS: Forensic Implications of Identity Management Systems, Technical report by the FIDIS consortium - EC Contract No , 006, pp

18 3. Salter D.: Thumbprint An Emerging Technology, Engineering Technology, New Mexico State University, Wayman J., Jain A., Maltoni D. and Maio D.: iometric Systems, Springer-Verlag London Limited, 005., pp Yount L.: Forensic Science from Fibres to Thumbprints, Chelsea House Publisher, Adegbeyeni E.. Akinyokun. C.: Scientific Evaluation of the Process of Scanning and Forensic Analysis of Thumb Prints on allot Papers, Forensics Expert Report, ndo State of Nigeria Governorship Election Tribunal, Akinyokun. C. and Adegbeyeni E..: Scientific Evaluation of the Process of Scanning and Forensic Analysis of Thumb Prints on allot Papers, Proceedings of Allied Academies International Conference in New rleans, April 8-10, 009; Vol. 13; No. 1; Pages Roberts C. : iometrics ( Accessed 1 July, Konar A., Artificial Intelligence and Soft Computing: ehavioural and Cognitive Modeling of the Human rain, CRC Press, ISN , Ali S. M. and Al-Zewary M. S.: A New Fast Automatic Technique for Fingerprints Recognition and Identification, Journal of Islamic Academy of Sciences 10:, 1997 pp Espinosa Virginia: A Minutiae Detection Algorithm for Fingerprint Pattern Recognition, IEEE Systems Magazine, 00, pp López A. C, Ricardo R. López, Reinaldo Cruz Queeman: Fingerprint Pattern Recognition, PhD Thesis, Electrical Engineering Department, Polytechnic University, 00, pp Chikkerur Sharat, Chaohong Wu, Venu Govindaraju: A Systematic Approach for Feature Extraction in Fingerprint Pattern Recognition, Center for Unified iometrics and Censors (CUS), University at uffalo, NY, USA, 004, pp Zhang Weiwei, Wang Sen and Wang Yangsheng: Structure Matching Algorithm of Fingerprint Minutiae ased on Core Point, Technical Report, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science, eijing, 004, pp Tsai-Yang Jea, and Venu Govindaraju: A Minutia-ased Partial Fingerprint Recognition System, Technical Report, Center for Unified iometrics and Sensors, University at uffalo, State University of New York, Amherst, NY USA 148, Arun Vinodh C: Extracting and Enhancing the Core Area in Fingerprint Images, International Journal of Computer Science and Network Security, VL.7 No.1, 007, pp Chaohong Wu: Advanced feature extraction algorithms for automatic fingerprint recognition system, A PhD dissertation submitted to the Faculty of the Graduate School of the State University of New York at uffalo, 007, pp Raymond Thai: Fingerprint Image Enhancement and Minutiae Extraction, PhD Thesis Submitted to School of Computer Science and Software Engineering, University of Western Australia, Liang, X: A Linear Time Algorithm for inary Fingerprint Image De-noising using Distance Transform, IEICE TRANSACTINS on Information and Systems, Vol. E89-D, No. 4, (009), pp

Palmprint Recognition. By Sree Rama Murthy kora Praveen Verma Yashwant Kashyap

Palmprint Recognition. By Sree Rama Murthy kora Praveen Verma Yashwant Kashyap Palmprint Recognition By Sree Rama Murthy kora Praveen Verma Yashwant Kashyap Palm print Palm Patterns are utilized in many applications: 1. To correlate palm patterns with medical disorders, e.g. genetic

More information

Classification of Fingerprints. Sarat C. Dass Department of Statistics & Probability

Classification of Fingerprints. Sarat C. Dass Department of Statistics & Probability Classification of Fingerprints Sarat C. Dass Department of Statistics & Probability Fingerprint Classification Fingerprint classification is a coarse level partitioning of a fingerprint database into smaller

More information

Automatic Biometric Student Attendance System: A Case Study Christian Service University College

Automatic Biometric Student Attendance System: A Case Study Christian Service University College Automatic Biometric Student Attendance System: A Case Study Christian Service University College Dr Thomas Yeboah Dr Ing Edward Opoku-Mensah Mr Christopher Ayaaba Abilimi ABSTRACT In many tertiary institutions

More information

High Resolution Fingerprint Matching Using Level 3 Features

High Resolution Fingerprint Matching Using Level 3 Features High Resolution Fingerprint Matching Using Level 3 Features Anil K. Jain and Yi Chen Michigan State University Fingerprint Features Latent print examiners use Level 3 all the time We do not just count

More information

Multimodal Biometric Recognition Security System

Multimodal Biometric Recognition Security System Multimodal Biometric Recognition Security System Anju.M.I, G.Sheeba, G.Sivakami, Monica.J, Savithri.M Department of ECE, New Prince Shri Bhavani College of Engg. & Tech., Chennai, India ABSTRACT: Security

More information

Development of a Networked Thumb Print-Based Staff Attendance Management System

Development of a Networked Thumb Print-Based Staff Attendance Management System American Journal of Engineering Research (AJER) e-issn : 2320-0847 p-issn : 2320-0936 Volume-03, Issue-03, pp-121-126 www.ajer.org Research Paper Open Access Development of a Networked Thumb Print-Based

More information

Pattern Recognition 43 (2010) 1050 -- 1061. Contents lists available at ScienceDirect. Pattern Recognition

Pattern Recognition 43 (2010) 1050 -- 1061. Contents lists available at ScienceDirect. Pattern Recognition Pattern Recognition 43 (2010) 1050 -- 1061 Contents lists available at ScienceDirect Pattern Recognition journal homepage: www.elsevier.com/locate/pr High resolution partial fingerprint alignment using

More information

Development of Attendance Management System using Biometrics.

Development of Attendance Management System using Biometrics. Development of Attendance Management System using Biometrics. O. Shoewu, Ph.D. 1,2* and O.A. Idowu, B.Sc. 1 1 Department of Electronic and Computer Engineering, Lagos State University, Epe Campus, Nigeria.

More information

Fingerprint s Core Point Detection using Gradient Field Mask

Fingerprint s Core Point Detection using Gradient Field Mask Fingerprint s Core Point Detection using Gradient Field Mask Ashish Mishra Assistant Professor Dept. of Computer Science, GGCT, Jabalpur, [M.P.], Dr.Madhu Shandilya Associate Professor Dept. of Electronics.MANIT,Bhopal[M.P.]

More information

International Journal of Advanced Information in Arts, Science & Management Vol.2, No.2, December 2014

International Journal of Advanced Information in Arts, Science & Management Vol.2, No.2, December 2014 Efficient Attendance Management System Using Face Detection and Recognition Arun.A.V, Bhatath.S, Chethan.N, Manmohan.C.M, Hamsaveni M Department of Computer Science and Engineering, Vidya Vardhaka College

More information

Signature Region of Interest using Auto cropping

Signature Region of Interest using Auto cropping ISSN (Online): 1694-0784 ISSN (Print): 1694-0814 1 Signature Region of Interest using Auto cropping Bassam Al-Mahadeen 1, Mokhled S. AlTarawneh 2 and Islam H. AlTarawneh 2 1 Math. And Computer Department,

More information

PARTIAL FINGERPRINT REGISTRATION FOR FORENSICS USING MINUTIAE-GENERATED ORIENTATION FIELDS

PARTIAL FINGERPRINT REGISTRATION FOR FORENSICS USING MINUTIAE-GENERATED ORIENTATION FIELDS PARTIAL FINGERPRINT REGISTRATION FOR FORENSICS USING MINUTIAE-GENERATED ORIENTATION FIELDS Ram P. Krish 1, Julian Fierrez 1, Daniel Ramos 1, Javier Ortega-Garcia 1, Josef Bigun 2 1 Biometric Recognition

More information

ECE 533 Project Report Ashish Dhawan Aditi R. Ganesan

ECE 533 Project Report Ashish Dhawan Aditi R. Ganesan Handwritten Signature Verification ECE 533 Project Report by Ashish Dhawan Aditi R. Ganesan Contents 1. Abstract 3. 2. Introduction 4. 3. Approach 6. 4. Pre-processing 8. 5. Feature Extraction 9. 6. Verification

More information

SWGFAST. Defining Level Three Detail

SWGFAST. Defining Level Three Detail SWGFAST Defining Level Three Detail ANSI / NIST Workshop Data Format for the Interchange of Fingerprint, Facial, & Scar Mark & Tattoo (SMT) Information April 26-28,2005 28,2005 Defining Level Three Detail

More information

Biometric Authentication using Online Signatures

Biometric Authentication using Online Signatures Biometric Authentication using Online Signatures Alisher Kholmatov and Berrin Yanikoglu alisher@su.sabanciuniv.edu, berrin@sabanciuniv.edu http://fens.sabanciuniv.edu Sabanci University, Tuzla, Istanbul,

More information

On the Operational Quality of Fingerprint Scanners

On the Operational Quality of Fingerprint Scanners BioLab - Biometric System Lab University of Bologna - ITALY http://biolab.csr.unibo.it On the Operational Quality of Fingerprint Scanners Davide Maltoni and Matteo Ferrara November 7, 2007 Outline The

More information

Secured Employee Attendance Management System Using Fingerprint

Secured Employee Attendance Management System Using Fingerprint IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661, p- ISSN: 2278-8727Volume 16, Issue 1, Ver. III (Jan. 2014), PP 32-37 Secured Employee Attendance Management System Using Fingerprint Chiwa,

More information

Face detection is a process of localizing and extracting the face region from the

Face detection is a process of localizing and extracting the face region from the Chapter 4 FACE NORMALIZATION 4.1 INTRODUCTION Face detection is a process of localizing and extracting the face region from the background. The detected face varies in rotation, brightness, size, etc.

More information

The Role of Size Normalization on the Recognition Rate of Handwritten Numerals

The Role of Size Normalization on the Recognition Rate of Handwritten Numerals The Role of Size Normalization on the Recognition Rate of Handwritten Numerals Chun Lei He, Ping Zhang, Jianxiong Dong, Ching Y. Suen, Tien D. Bui Centre for Pattern Recognition and Machine Intelligence,

More information

LOCAL SURFACE PATCH BASED TIME ATTENDANCE SYSTEM USING FACE. indhubatchvsa@gmail.com

LOCAL SURFACE PATCH BASED TIME ATTENDANCE SYSTEM USING FACE. indhubatchvsa@gmail.com LOCAL SURFACE PATCH BASED TIME ATTENDANCE SYSTEM USING FACE 1 S.Manikandan, 2 S.Abirami, 2 R.Indumathi, 2 R.Nandhini, 2 T.Nanthini 1 Assistant Professor, VSA group of institution, Salem. 2 BE(ECE), VSA

More information

Efficient on-line Signature Verification System

Efficient on-line Signature Verification System International Journal of Engineering & Technology IJET-IJENS Vol:10 No:04 42 Efficient on-line Signature Verification System Dr. S.A Daramola 1 and Prof. T.S Ibiyemi 2 1 Department of Electrical and Information

More information

Efficient Attendance Management: A Face Recognition Approach

Efficient Attendance Management: A Face Recognition Approach Efficient Attendance Management: A Face Recognition Approach Badal J. Deshmukh, Sudhir M. Kharad Abstract Taking student attendance in a classroom has always been a tedious task faultfinders. It is completely

More information

Modelling, Extraction and Description of Intrinsic Cues of High Resolution Satellite Images: Independent Component Analysis based approaches

Modelling, Extraction and Description of Intrinsic Cues of High Resolution Satellite Images: Independent Component Analysis based approaches Modelling, Extraction and Description of Intrinsic Cues of High Resolution Satellite Images: Independent Component Analysis based approaches PhD Thesis by Payam Birjandi Director: Prof. Mihai Datcu Problematic

More information

A PHOTOGRAMMETRIC APPRAOCH FOR AUTOMATIC TRAFFIC ASSESSMENT USING CONVENTIONAL CCTV CAMERA

A PHOTOGRAMMETRIC APPRAOCH FOR AUTOMATIC TRAFFIC ASSESSMENT USING CONVENTIONAL CCTV CAMERA A PHOTOGRAMMETRIC APPRAOCH FOR AUTOMATIC TRAFFIC ASSESSMENT USING CONVENTIONAL CCTV CAMERA N. Zarrinpanjeh a, F. Dadrassjavan b, H. Fattahi c * a Islamic Azad University of Qazvin - nzarrin@qiau.ac.ir

More information

Keywords: fingerprints, attendance, enrollment, authentication, identification

Keywords: fingerprints, attendance, enrollment, authentication, identification Volume 4, Issue 11, November 2014 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com 94 POS Terminal

More information

Establishing the Uniqueness of the Human Voice for Security Applications

Establishing the Uniqueness of the Human Voice for Security Applications Proceedings of Student/Faculty Research Day, CSIS, Pace University, May 7th, 2004 Establishing the Uniqueness of the Human Voice for Security Applications Naresh P. Trilok, Sung-Hyuk Cha, and Charles C.

More information

SIGNATURE VERIFICATION

SIGNATURE VERIFICATION SIGNATURE VERIFICATION Dr. H.B.Kekre, Dr. Dhirendra Mishra, Ms. Shilpa Buddhadev, Ms. Bhagyashree Mall, Mr. Gaurav Jangid, Ms. Nikita Lakhotia Computer engineering Department, MPSTME, NMIMS University

More information

FUZZY CLUSTERING ANALYSIS OF DATA MINING: APPLICATION TO AN ACCIDENT MINING SYSTEM

FUZZY CLUSTERING ANALYSIS OF DATA MINING: APPLICATION TO AN ACCIDENT MINING SYSTEM International Journal of Innovative Computing, Information and Control ICIC International c 0 ISSN 34-48 Volume 8, Number 8, August 0 pp. 4 FUZZY CLUSTERING ANALYSIS OF DATA MINING: APPLICATION TO AN ACCIDENT

More information

ORGANIZATIONAL KNOWLEDGE MAPPING BASED ON LIBRARY INFORMATION SYSTEM

ORGANIZATIONAL KNOWLEDGE MAPPING BASED ON LIBRARY INFORMATION SYSTEM ORGANIZATIONAL KNOWLEDGE MAPPING BASED ON LIBRARY INFORMATION SYSTEM IRANDOC CASE STUDY Ammar Jalalimanesh a,*, Elaheh Homayounvala a a Information engineering department, Iranian Research Institute for

More information

Use of Data Mining Techniques to Improve the Effectiveness of Sales and Marketing

Use of Data Mining Techniques to Improve the Effectiveness of Sales and Marketing Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 4, Issue. 4, April 2015,

More information

Aman Chadha et al, Int. J. Comp. Tech. Appl., Vol 2 (5), 1419-1425

Aman Chadha et al, Int. J. Comp. Tech. Appl., Vol 2 (5), 1419-1425 Rotation, Scaling and Translation Analysis of Biometric Templates Aman Chadha, Divya Jyoti, M. Mani Roja Thadomal Shahani Engineering College, Mumbai, India aman.x64@gmail.com Abstract Biometric authentication

More information

Development of Academic Attendence Monitoring System Using Fingerprint Identification

Development of Academic Attendence Monitoring System Using Fingerprint Identification 164 Development of Academic Attendence Monitoring System Using Fingerprint Identification TABASSAM NAWAZ, SAIM PERVAIZ, ARASH KORRANI, AZHAR-UD-DIN Software Engineering Department Faculty of Telecommunication

More information

EM Clustering Approach for Multi-Dimensional Analysis of Big Data Set

EM Clustering Approach for Multi-Dimensional Analysis of Big Data Set EM Clustering Approach for Multi-Dimensional Analysis of Big Data Set Amhmed A. Bhih School of Electrical and Electronic Engineering Princy Johnson School of Electrical and Electronic Engineering Martin

More information

Face Recognition in Low-resolution Images by Using Local Zernike Moments

Face Recognition in Low-resolution Images by Using Local Zernike Moments Proceedings of the International Conference on Machine Vision and Machine Learning Prague, Czech Republic, August14-15, 014 Paper No. 15 Face Recognition in Low-resolution Images by Using Local Zernie

More information

Hierarchically linked extended features for fingerprint processing

Hierarchically linked extended features for fingerprint processing Hierarchically linked extended features for fingerprint processing Dissertation zur Erlangung des Doktorgrades der Mathematisch-Naturwissenschaftlichen Fakultäten der Georg-August-Universität zu Göttingen

More information

Recognition of Handwritten Digits using Structural Information

Recognition of Handwritten Digits using Structural Information Recognition of Handwritten Digits using Structural Information Sven Behnke Martin-Luther University, Halle-Wittenberg' Institute of Computer Science 06099 Halle, Germany { behnke Irojas} @ informatik.uni-halle.de

More information

Automatic Detection of PCB Defects

Automatic Detection of PCB Defects IJIRST International Journal for Innovative Research in Science & Technology Volume 1 Issue 6 November 2014 ISSN (online): 2349-6010 Automatic Detection of PCB Defects Ashish Singh PG Student Vimal H.

More information

The Scientific Data Mining Process

The Scientific Data Mining Process Chapter 4 The Scientific Data Mining Process When I use a word, Humpty Dumpty said, in rather a scornful tone, it means just what I choose it to mean neither more nor less. Lewis Carroll [87, p. 214] In

More information

Social Media Mining. Data Mining Essentials

Social Media Mining. Data Mining Essentials Introduction Data production rate has been increased dramatically (Big Data) and we are able store much more data than before E.g., purchase data, social media data, mobile phone data Businesses and customers

More information

Keywords image processing, signature verification, false acceptance rate, false rejection rate, forgeries, feature vectors, support vector machines.

Keywords image processing, signature verification, false acceptance rate, false rejection rate, forgeries, feature vectors, support vector machines. International Journal of Computer Application and Engineering Technology Volume 3-Issue2, Apr 2014.Pp. 188-192 www.ijcaet.net OFFLINE SIGNATURE VERIFICATION SYSTEM -A REVIEW Pooja Department of Computer

More information

Document #8 Standard for the Documentation of Analysis, Comparison, Evaluation, and Verification (ACE-V) (Latent)

Document #8 Standard for the Documentation of Analysis, Comparison, Evaluation, and Verification (ACE-V) (Latent) Document #8 Standard for the Documentation of Analysis, Comparison, Evaluation, and Verification (ACE-V) (Latent) 1. Preamble 1.1. When friction ridge detail is examined using the ACE-V methodology, examiners

More information

Fingerprint Recognition System

Fingerprint Recognition System International Journal of Electronics and Computer Science Engineering 872 Available Online at www.ijecse.org ISSN- 2277-1956 Fingerprint Recognition System Bhawna Negi 1, Varun Sharma 2 1 2 Department

More information

Development of Palmprint Verification System Using Biometrics

Development of Palmprint Verification System Using Biometrics ISSN 1000-985, CDEN RUXUEW E-mail: jos@iscas.ac.cn Journal of Software, Vol.17, No.8, August 006, pp.184 1836 http://www.jos.org.cn DI: 10.1360/jos17184 Tel/Fax: +86-10-656563 006 by Journal of Software.

More information

TIETS34 Seminar: Data Mining on Biometric identification

TIETS34 Seminar: Data Mining on Biometric identification TIETS34 Seminar: Data Mining on Biometric identification Youming Zhang Computer Science, School of Information Sciences, 33014 University of Tampere, Finland Youming.Zhang@uta.fi Course Description Content

More information

Poker Vision: Playing Cards and Chips Identification based on Image Processing

Poker Vision: Playing Cards and Chips Identification based on Image Processing Poker Vision: Playing Cards and Chips Identification based on Image Processing Paulo Martins 1, Luís Paulo Reis 2, and Luís Teófilo 2 1 DEEC Electrical Engineering Department 2 LIACC Artificial Intelligence

More information

The Implementation of Face Security for Authentication Implemented on Mobile Phone

The Implementation of Face Security for Authentication Implemented on Mobile Phone The Implementation of Face Security for Authentication Implemented on Mobile Phone Emir Kremić *, Abdulhamit Subaşi * * Faculty of Engineering and Information Technology, International Burch University,

More information

De-duplication The Complexity in the Unique ID context

De-duplication The Complexity in the Unique ID context De-duplication The Complexity in the Unique ID context 1. Introduction Citizens in India depend on the Government for various services at various stages of the human lifecycle. These services include issuance

More information

Implementation of OCR Based on Template Matching and Integrating it in Android Application

Implementation of OCR Based on Template Matching and Integrating it in Android Application International Journal of Computer Sciences and EngineeringOpen Access Technical Paper Volume-04, Issue-02 E-ISSN: 2347-2693 Implementation of OCR Based on Template Matching and Integrating it in Android

More information

Solving Simultaneous Equations and Matrices

Solving Simultaneous Equations and Matrices Solving Simultaneous Equations and Matrices The following represents a systematic investigation for the steps used to solve two simultaneous linear equations in two unknowns. The motivation for considering

More information

A responsive Fingerprint Matching system for a scalable functional agent

A responsive Fingerprint Matching system for a scalable functional agent A responsive Fingerprint Matching system for a scalable functional agent N. Nagaraju Research Scholar, PACE Institute of Technology & Sciences Ongole. ABSTRACT The Fingerprint Matching is that the most

More information

Clustering. 15-381 Artificial Intelligence Henry Lin. Organizing data into clusters such that there is

Clustering. 15-381 Artificial Intelligence Henry Lin. Organizing data into clusters such that there is Clustering 15-381 Artificial Intelligence Henry Lin Modified from excellent slides of Eamonn Keogh, Ziv Bar-Joseph, and Andrew Moore What is Clustering? Organizing data into clusters such that there is

More information

Method of Combining the Degrees of Similarity in Handwritten Signature Authentication Using Neural Networks

Method of Combining the Degrees of Similarity in Handwritten Signature Authentication Using Neural Networks Method of Combining the Degrees of Similarity in Handwritten Signature Authentication Using Neural Networks Ph. D. Student, Eng. Eusebiu Marcu Abstract This paper introduces a new method of combining the

More information

A Learning Based Method for Super-Resolution of Low Resolution Images

A Learning Based Method for Super-Resolution of Low Resolution Images A Learning Based Method for Super-Resolution of Low Resolution Images Emre Ugur June 1, 2004 emre.ugur@ceng.metu.edu.tr Abstract The main objective of this project is the study of a learning based method

More information

Morphological segmentation of histology cell images

Morphological segmentation of histology cell images Morphological segmentation of histology cell images A.Nedzved, S.Ablameyko, I.Pitas Institute of Engineering Cybernetics of the National Academy of Sciences Surganova, 6, 00 Minsk, Belarus E-mail abl@newman.bas-net.by

More information

The Development of a Pressure-based Typing Biometrics User Authentication System

The Development of a Pressure-based Typing Biometrics User Authentication System The Development of a Pressure-based Typing Biometrics User Authentication System Chen Change Loy Adv. Informatics Research Group MIMOS Berhad by Assoc. Prof. Dr. Chee Peng Lim Associate Professor Sch.

More information

International Journal of Computer Science Trends and Technology (IJCST) Volume 2 Issue 3, May-Jun 2014

International Journal of Computer Science Trends and Technology (IJCST) Volume 2 Issue 3, May-Jun 2014 RESEARCH ARTICLE OPEN ACCESS A Survey of Data Mining: Concepts with Applications and its Future Scope Dr. Zubair Khan 1, Ashish Kumar 2, Sunny Kumar 3 M.Tech Research Scholar 2. Department of Computer

More information

Binary Image Scanning Algorithm for Cane Segmentation

Binary Image Scanning Algorithm for Cane Segmentation Binary Image Scanning Algorithm for Cane Segmentation Ricardo D. C. Marin Department of Computer Science University Of Canterbury Canterbury, Christchurch ricardo.castanedamarin@pg.canterbury.ac.nz Tom

More information

Finger Print Parameter Based Cryptographic Key Generation

Finger Print Parameter Based Cryptographic Key Generation Finger Print Parameter Based Cryptographic Key Generation B.Raja Rao, Dr.E.V.V.Krishna Rao, S.V.Rama Rao,M.Rama mohan rao (Associate Professor, Department of ECE, URCE, Telaprolu,vijayawada. (Professor

More information

Face Recognition For Remote Database Backup System

Face Recognition For Remote Database Backup System Face Recognition For Remote Database Backup System Aniza Mohamed Din, Faudziah Ahmad, Mohamad Farhan Mohamad Mohsin, Ku Ruhana Ku-Mahamud, Mustafa Mufawak Theab 2 Graduate Department of Computer Science,UUM

More information

FACE RECOGNITION BASED ATTENDANCE MARKING SYSTEM

FACE RECOGNITION BASED ATTENDANCE MARKING SYSTEM Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 3, Issue. 2, February 2014,

More information

An Overview of Knowledge Discovery Database and Data mining Techniques

An Overview of Knowledge Discovery Database and Data mining Techniques An Overview of Knowledge Discovery Database and Data mining Techniques Priyadharsini.C 1, Dr. Antony Selvadoss Thanamani 2 M.Phil, Department of Computer Science, NGM College, Pollachi, Coimbatore, Tamilnadu,

More information

Environmental Remote Sensing GEOG 2021

Environmental Remote Sensing GEOG 2021 Environmental Remote Sensing GEOG 2021 Lecture 4 Image classification 2 Purpose categorising data data abstraction / simplification data interpretation mapping for land cover mapping use land cover class

More information

SPATIAL DATA CLASSIFICATION AND DATA MINING

SPATIAL DATA CLASSIFICATION AND DATA MINING , pp.-40-44. Available online at http://www. bioinfo. in/contents. php?id=42 SPATIAL DATA CLASSIFICATION AND DATA MINING RATHI J.B. * AND PATIL A.D. Department of Computer Science & Engineering, Jawaharlal

More information

Using Lexical Similarity in Handwritten Word Recognition

Using Lexical Similarity in Handwritten Word Recognition Using Lexical Similarity in Handwritten Word Recognition Jaehwa Park and Venu Govindaraju Center of Excellence for Document Analysis and Recognition (CEDAR) Department of Computer Science and Engineering

More information

ARM7 Based Smart ATM Access & Security System Using Fingerprint Recognition & GSM Technology

ARM7 Based Smart ATM Access & Security System Using Fingerprint Recognition & GSM Technology ARM7 Based Smart ATM Access & Security System Using Fingerprint Recognition & GSM Technology Khatmode Ranjit P 1, Kulkarni Ramchandra V 2, Ghodke Bharat S 3, Prof. P. P. Chitte 4, Prof. Anap S. D 5 1 Student

More information

SPECIAL PERTURBATIONS UNCORRELATED TRACK PROCESSING

SPECIAL PERTURBATIONS UNCORRELATED TRACK PROCESSING AAS 07-228 SPECIAL PERTURBATIONS UNCORRELATED TRACK PROCESSING INTRODUCTION James G. Miller * Two historical uncorrelated track (UCT) processing approaches have been employed using general perturbations

More information

Canny Edge Detection

Canny Edge Detection Canny Edge Detection 09gr820 March 23, 2009 1 Introduction The purpose of edge detection in general is to significantly reduce the amount of data in an image, while preserving the structural properties

More information

Application-Specific Biometric Templates

Application-Specific Biometric Templates Application-Specific Biometric s Michael Braithwaite, Ulf Cahn von Seelen, James Cambier, John Daugman, Randy Glass, Russ Moore, Ian Scott, Iridian Technologies Inc. Introduction Biometric technologies

More information

2 FINGERPRINT VERIFICATION

2 FINGERPRINT VERIFICATION 2 FINGERPRINT VERIFICATION Lawrence O'Gorman Veridicom Inc. Chatham, NJ log@veridicom.com Abstract The use of fingerprints for identification has been employed in law enforcement for about a century. A

More information

IT services for analyses of various data samples

IT services for analyses of various data samples IT services for analyses of various data samples Ján Paralič, František Babič, Martin Sarnovský, Peter Butka, Cecília Havrilová, Miroslava Muchová, Michal Puheim, Martin Mikula, Gabriel Tutoky Technical

More information

A colour Code Algorithm for Signature Recognition

A colour Code Algorithm for Signature Recognition Electronic Letters on Computer Vision and Image Analysis 6(1):1-12, 2007 A colour Code Algorithm for Signature Recognition Vinayak Balkrishana Kulkarni Department of Electronics Engineering. Finolex Academy

More information

Open Access A Facial Expression Recognition Algorithm Based on Local Binary Pattern and Empirical Mode Decomposition

Open Access A Facial Expression Recognition Algorithm Based on Local Binary Pattern and Empirical Mode Decomposition Send Orders for Reprints to reprints@benthamscience.ae The Open Electrical & Electronic Engineering Journal, 2014, 8, 599-604 599 Open Access A Facial Expression Recognition Algorithm Based on Local Binary

More information

QOS Based Web Service Ranking Using Fuzzy C-means Clusters

QOS Based Web Service Ranking Using Fuzzy C-means Clusters Research Journal of Applied Sciences, Engineering and Technology 10(9): 1045-1050, 2015 ISSN: 2040-7459; e-issn: 2040-7467 Maxwell Scientific Organization, 2015 Submitted: March 19, 2015 Accepted: April

More information

Local outlier detection in data forensics: data mining approach to flag unusual schools

Local outlier detection in data forensics: data mining approach to flag unusual schools Local outlier detection in data forensics: data mining approach to flag unusual schools Mayuko Simon Data Recognition Corporation Paper presented at the 2012 Conference on Statistical Detection of Potential

More information

METHODOLOGICAL CONSIDERATIONS OF DRIVE SYSTEM SIMULATION, WHEN COUPLING FINITE ELEMENT MACHINE MODELS WITH THE CIRCUIT SIMULATOR MODELS OF CONVERTERS.

METHODOLOGICAL CONSIDERATIONS OF DRIVE SYSTEM SIMULATION, WHEN COUPLING FINITE ELEMENT MACHINE MODELS WITH THE CIRCUIT SIMULATOR MODELS OF CONVERTERS. SEDM 24 June 16th - 18th, CPRI (Italy) METHODOLOGICL CONSIDERTIONS OF DRIVE SYSTEM SIMULTION, WHEN COUPLING FINITE ELEMENT MCHINE MODELS WITH THE CIRCUIT SIMULTOR MODELS OF CONVERTERS. Áron Szûcs BB Electrical

More information

Chapter 6. The stacking ensemble approach

Chapter 6. The stacking ensemble approach 82 This chapter proposes the stacking ensemble approach for combining different data mining classifiers to get better performance. Other combination techniques like voting, bagging etc are also described

More information

Visual-based ID Verification by Signature Tracking

Visual-based ID Verification by Signature Tracking Visual-based ID Verification by Signature Tracking Mario E. Munich and Pietro Perona California Institute of Technology www.vision.caltech.edu/mariomu Outline Biometric ID Visual Signature Acquisition

More information

Big Data with Rough Set Using Map- Reduce

Big Data with Rough Set Using Map- Reduce Big Data with Rough Set Using Map- Reduce Mr.G.Lenin 1, Mr. A. Raj Ganesh 2, Mr. S. Vanarasan 3 Assistant Professor, Department of CSE, Podhigai College of Engineering & Technology, Tirupattur, Tamilnadu,

More information

Two novel characteristics in palmprint verification: datum point invariance and line feature matching

Two novel characteristics in palmprint verification: datum point invariance and line feature matching Pattern Recognition 32 (1999) 691 702 Two novel characteristics in palmprint verification: datum point invariance and line feature matching Dapeng Zhang*, Wei Shu Department of Computing, Hong Kong Polytechnic

More information

Categorical Data Visualization and Clustering Using Subjective Factors

Categorical Data Visualization and Clustering Using Subjective Factors Categorical Data Visualization and Clustering Using Subjective Factors Chia-Hui Chang and Zhi-Kai Ding Department of Computer Science and Information Engineering, National Central University, Chung-Li,

More information

A Simple Feature Extraction Technique of a Pattern By Hopfield Network

A Simple Feature Extraction Technique of a Pattern By Hopfield Network A Simple Feature Extraction Technique of a Pattern By Hopfield Network A.Nag!, S. Biswas *, D. Sarkar *, P.P. Sarkar *, B. Gupta **! Academy of Technology, Hoogly - 722 *USIC, University of Kalyani, Kalyani

More information

Forensic Science Lesson 3: Trace Evidence Analysis

Forensic Science Lesson 3: Trace Evidence Analysis Forensic Science Lesson 3: Trace Evidence Analysis History Alphonse Bertillon 1883 Created the first systematic system of individual classification & identification Detailed description of subject, full-length

More information

DATA MINING TECHNOLOGY. Keywords: data mining, data warehouse, knowledge discovery, OLAP, OLAM.

DATA MINING TECHNOLOGY. Keywords: data mining, data warehouse, knowledge discovery, OLAP, OLAM. DATA MINING TECHNOLOGY Georgiana Marin 1 Abstract In terms of data processing, classical statistical models are restrictive; it requires hypotheses, the knowledge and experience of specialists, equations,

More information

Microcontroller Based Smart ATM Access & Security System Using Fingerprint Recognition & GSM Technology

Microcontroller Based Smart ATM Access & Security System Using Fingerprint Recognition & GSM Technology Microcontroller Based Smart ATM Access & Security System Using Fingerprint Recognition & GSM Technology Bharath K M, Rohit C V Student of B.E Electronics and Communication Coorg Institute of Technology,

More information

Component Ordering in Independent Component Analysis Based on Data Power

Component Ordering in Independent Component Analysis Based on Data Power Component Ordering in Independent Component Analysis Based on Data Power Anne Hendrikse Raymond Veldhuis University of Twente University of Twente Fac. EEMCS, Signals and Systems Group Fac. EEMCS, Signals

More information

Part-Based Recognition

Part-Based Recognition Part-Based Recognition Benedict Brown CS597D, Fall 2003 Princeton University CS 597D, Part-Based Recognition p. 1/32 Introduction Many objects are made up of parts It s presumably easier to identify simple

More information

Barcode Based Automated Parking Management System

Barcode Based Automated Parking Management System IJSRD - International Journal for Scientific Research & Development Vol. 2, Issue 03, 2014 ISSN (online): 2321-0613 Barcode Based Automated Parking Management System Parth Rajeshbhai Zalawadia 1 Jasmin

More information

KNOWLEDGE-BASED IN MEDICAL DECISION SUPPORT SYSTEM BASED ON SUBJECTIVE INTELLIGENCE

KNOWLEDGE-BASED IN MEDICAL DECISION SUPPORT SYSTEM BASED ON SUBJECTIVE INTELLIGENCE JOURNAL OF MEDICAL INFORMATICS & TECHNOLOGIES Vol. 22/2013, ISSN 1642-6037 medical diagnosis, ontology, subjective intelligence, reasoning, fuzzy rules Hamido FUJITA 1 KNOWLEDGE-BASED IN MEDICAL DECISION

More information

Handwritten Character Recognition from Bank Cheque

Handwritten Character Recognition from Bank Cheque International Journal of Computer Sciences and Engineering Open Access Research Paper Volume-4, Special Issue-1 E-ISSN: 2347-2693 Handwritten Character Recognition from Bank Cheque Siddhartha Banerjee*

More information

A Method of Caption Detection in News Video

A Method of Caption Detection in News Video 3rd International Conference on Multimedia Technology(ICMT 3) A Method of Caption Detection in News Video He HUANG, Ping SHI Abstract. News video is one of the most important media for people to get information.

More information

The multilayer sentiment analysis model based on Random forest Wei Liu1, Jie Zhang2

The multilayer sentiment analysis model based on Random forest Wei Liu1, Jie Zhang2 2nd International Conference on Advances in Mechanical Engineering and Industrial Informatics (AMEII 2016) The multilayer sentiment analysis model based on Random forest Wei Liu1, Jie Zhang2 1 School of

More information

How To Filter Spam Image From A Picture By Color Or Color

How To Filter Spam Image From A Picture By Color Or Color Image Content-Based Email Spam Image Filtering Jianyi Wang and Kazuki Katagishi Abstract With the population of Internet around the world, email has become one of the main methods of communication among

More information

Document Image Retrieval using Signatures as Queries

Document Image Retrieval using Signatures as Queries Document Image Retrieval using Signatures as Queries Sargur N. Srihari, Shravya Shetty, Siyuan Chen, Harish Srinivasan, Chen Huang CEDAR, University at Buffalo(SUNY) Amherst, New York 14228 Gady Agam and

More information

Biometric Authentication using Online Signature

Biometric Authentication using Online Signature University of Trento Department of Mathematics Outline Introduction An example of authentication scheme Performance analysis and possible improvements Outline Introduction An example of authentication

More information

3D Human Face Recognition Using Point Signature

3D Human Face Recognition Using Point Signature 3D Human Face Recognition Using Point Signature Chin-Seng Chua, Feng Han, Yeong-Khing Ho School of Electrical and Electronic Engineering Nanyang Technological University, Singapore 639798 ECSChua@ntu.edu.sg

More information

Fingerprint-Based Authentication System for Time and Attendance Management

Fingerprint-Based Authentication System for Time and Attendance Management 1 2 3 4 5 6 7 8 9 10 11 12 Fingerprint-Based Authentication System for Time and Attendance Management ABSTRACT Ikuomola, Aderonke Justina Ondo State University of Science and Technology, Okitipupa, Ondo

More information

PHOTOGRAMMETRIC TECHNIQUES FOR MEASUREMENTS IN WOODWORKING INDUSTRY

PHOTOGRAMMETRIC TECHNIQUES FOR MEASUREMENTS IN WOODWORKING INDUSTRY PHOTOGRAMMETRIC TECHNIQUES FOR MEASUREMENTS IN WOODWORKING INDUSTRY V. Knyaz a, *, Yu. Visilter, S. Zheltov a State Research Institute for Aviation System (GosNIIAS), 7, Victorenko str., Moscow, Russia

More information

Visual Structure Analysis of Flow Charts in Patent Images

Visual Structure Analysis of Flow Charts in Patent Images Visual Structure Analysis of Flow Charts in Patent Images Roland Mörzinger, René Schuster, András Horti, and Georg Thallinger JOANNEUM RESEARCH Forschungsgesellschaft mbh DIGITAL - Institute for Information

More information

Assessment. Presenter: Yupu Zhang, Guoliang Jin, Tuo Wang Computer Vision 2008 Fall

Assessment. Presenter: Yupu Zhang, Guoliang Jin, Tuo Wang Computer Vision 2008 Fall Automatic Photo Quality Assessment Presenter: Yupu Zhang, Guoliang Jin, Tuo Wang Computer Vision 2008 Fall Estimating i the photorealism of images: Distinguishing i i paintings from photographs h Florin

More information

Chapter 2 The Research on Fault Diagnosis of Building Electrical System Based on RBF Neural Network

Chapter 2 The Research on Fault Diagnosis of Building Electrical System Based on RBF Neural Network Chapter 2 The Research on Fault Diagnosis of Building Electrical System Based on RBF Neural Network Qian Wu, Yahui Wang, Long Zhang and Li Shen Abstract Building electrical system fault diagnosis is the

More information