CHAPTER 5 AGE GROUP CLASSIFICATION OF FACIAL IMAGES USING RANK BASED EDGE TEXTURE UNIT
|
|
- Malcolm Flynn
- 7 years ago
- Views:
Transcription
1 CHAPTER 5 AGE GROUP CLASSIFICATION OF FACIAL IMAGES USING RANK BASED EDGE TEXTURE UNIT 5.1 BRIEF OUTLINE Human beings can easily categorize a person s age group from an image of the person s face where as this ability has not been pursued in the computer vision community. To address this problem very important area of research, the present thesis proposes a novel scheme of age classification system using features derived from co-occurrence parameters using Rank based Edge Texture Unit (RETU). The Cooccurrence Matrix (CM) on RETU characterizes the relationship between the neighboring edge values, while preserving local information. The novelty of the proposed RETU is it classifies the age of human into seven categories i.e. in the age groups of 1-10, 11-20, 21-30, 31-40, 41-50, 51-60, and greater than 60. The TU of the proposed RETU ranges from 0 to 17 and thus reduces overall complexity in evaluating features from CM. The co occurrence features extracted from the RETU provide complete facial image information for age classification purpose. The RETU reduces each 3 3 sub image into 2 2 sub image while preserving the texture features and thus reduces the overall dimensionality of the image. 5.2 INTRODUCTION The human face provides the observer with much information on gender, age, health, emotion and so on. Indeed, considerable research on 85
2 the human face has taken place in psychology and in the other cognitive sciences quite early. In recent years, applications in the area of human communication are actively studied from the viewpoint of information technology. A major goal of such studies is to achieve automatic identification of individuals using computers. To incorporate a human-face database in such applications, it is required to solve the issue of age development of the human face. While studying physical changes due to the ageing process many researchers tried to classify facial images into various groups [35, 55, 56, 115]. The authors carried out classification of: babies and adults [102], two age groups and [35], sex [35, 55]. So far, no study has attempted to classify the age groups with a span of ten years, based on RETU-CM features. Due to this reason, the present thesis attempted the tedious and complex task of classification of age into seven groups based on rank based edge texture units (RETU). The age groups are classified in to 1-10, 11-20, 21-30, 31-40, 41-50, and above 60 by deriving a new classification algorithm on the co-occurrence features derived from the novel approach called RETU. Recently, Vijaya kumar V, Chandra mohan et al [ 110 ] classified the age groups into seven categories i.e in the age groups of 16 to 25, 26 to 35, 36 to 45, 46 to 55, 56 to 65, 66 to 75 and 76 to 85 by using Topological Texture Features (TTF) in the facial skin. They [110] observed the fact that the facial skin of a person tends to undergo more changes with growing age. These rapid topological changes in the skin are exploited by TTF s using mathematical morphology. The TTF s are derived from the 86
3 patterns formed by Bezier, Koch and Elliptic curves and U, V, I, T and Z patterns on the facial skin. Wen-Bing Horng, Cheng-Ping Lee and Chun-Wen Chen et.al [124] considered four age groups for classification, including babies, young adults, middleaged adults, and old adults. Their method [124] is divided into three phases: location, feature extraction, and age classification. Based on the symmetry of human faces and the variation of gray levels, the positions of eyes, noses, and mouths are located by applying the Sobel edge operator and region labeling in the above methods [124]. Age classification on facial images based on cranio-facial development theory and skin wrinkle analysis [130], considered only three age-groups babies, young adults, and senior adults. The computations are based on cranio-facial development theory and skin wrinkle analysis. This method [56] is complex in nature and obtained only 81.57% of correct classification. 5.3 PROPOSED METHOD FOR AGE CLASSIFICATION ON FACIAL IMAGES BASED ON RETU-CM The proposed RETU-CM consists of seven steps. The block diagram of the proposed method is shown in figure 5.1. Original color image Cropping Cropped image Conversion of color to gray Robinson compass masks Extract edges from cropped face image RETU matrix Co-occurrence Matrix Extract features Classification Figure 5.1: block diagram of RETU-CM for age group classification system. 87
4 The original facial image is cropped based on the location two eyes of in the first step as shown in figure 4.5. In the step 2, if the facial image is a color image then it is converted into a gray level facial image by using HSV color model. In the third step, edge image is obtained by converting a 3 3 sub image into a 2 2 sub image by using Robinson compass masks. In the fourth step, rank values are assigned on the obtained edge image. In the fifth step, RETU are evaluated. In the sixth step co-occurrence matrix (CM) is formed on RETU. In the seventh step, statistical features are evaluated on the new RETU-CM for age group classification. In the last step a new algorithm is derived for an efficient age classification system based on the feature set derived from the proposed RETU-CM features RGB to HSV color model conversion In color image processing, there are various color models in use today. In order to extract gray level features from color information, the proposed RETU-CM utilized the HSV color space. In the RGB model, images are represented by three components, one for each primary color red, green and blue. Hue is a color attribute and represents a dominant color. Saturation is an expression of the relative purity or the degree to which a pure color is diluted by white light. HSV color space is a nonlinear transform from RGB color space that can describe perceptual color relationship more accurately than RGB color space. The present chapter has used HSV color space model conversion, because the present study is aimed to classify the human age in to seven groups with a gap of 10 years. HSV color space is formed by hue (H), saturation (S) and value (V). Hue denotes the property of color such as blue, green, red. Saturation 88
5 denotes the perceived intensity of a specific color. Value denotes brightness perception of a specific color. However, HSV color space separates the color into hue, saturation, and value which means observation of color variation can be individually discriminated. In order to transform RGB color space to HSV color space, the transformation is described as follows: The transformation equations for RGB to HSV color model conversion is given below. =max,, (5.1) S =,, (5.2) H= V=R (5.3) H= + V=G (5.4) H= + V=B (5.5) where the range of color component Hue (H) is [0,255], the component saturation (S) range is [0,1] and the Value (V) range is [0,255]. In this work, the color component Hue (H) is considered as color information for the classification of facial images. Color is an important attribute for image processing applications Extraction of edge information from the facial image The proposed RETU scheme generates the edges in the second stage. Various low-level visual features (e.g. color, texture, shape, edges) can be extracted as a preprocessing step from the images. Image edges give good information about the image content because they allow the identification 89
6 of the object structures. Edge detection is a fundamental tool used in most of the image processing applications to obtain information from the images as a precursor step to feature extraction. The edges contain the following features of the image. 1. Edge aims at identifying points in a digital image at which the image brightness changes sharply or more formally and has discontinuities. 2. Edge detection process detects and outlines the boundaries between objects and the background in the image. 3. Edge features are useful to overcome the problems generated by noise, edge strips and acuity. 4. Edges form boundaries between the different textures. 5. Edge reveals the discontinuities in image intensity from one pixel to another. Based on the above, the present chapter found that edges are relatively a good choice for obtaining facial image attributes or contents. The proposed RETU uses local edge features as the preprocessing step. The proposed method evaluates edge features on the entire cropped facial image. For evaluating the edges the Robinson Compass edge operator is used. The Robinson Compass edge operator provides better edge information with an advantage of being less sensitive to noise and extract explicit information about edges in any direction. Any edge detection masks can be extended by rotating them like compass masks, which will allow to extract explicit information about 90
7 edges in any direction. Robinson Compass edge detection is applied on the facial image to segment the enhanced borders from the background image. The Robinson edge detector applies Robinson approximation to the derivative of the facial image and detects edges in facial image. The masks are defined by taking a single mask and rotating it to eight major compass orientations: North, Northwest, West, Southwest, South, Southeast, East and Northeast as represented in figure 5.2. These masks are symmetrical about their directional axis, which contains zeros. The present study applied only the four primary Robinson compass masks { r 0, r 1, r 2 and r 3} on each 3 3 neighborhood of facial image by taking the absolute differences. The remaining four masks are not considered because they are just reflections of the above four. By applying r 0, r 1, r 2 and r 3 masks on the sub image of 3 3 mask four grey values which are nothing but edge values i.e. E 0(r 0), E 1(r 1), E 2(r 3) and E 3(r 3) are obtained. This leads to the formation of a 2 2 sub image from 3 3 sub image as shown in figure 5.3. Figure 5.2: Robinson compass masks or edge detection masks P 1 P 2 P 3 P 4 P 5 P 6 E 0(r 0) E 1(r 1) P 7 P 8 P 9 E 2(r 2) E 3(r 3) (a) (b) Figure 5.3: (a) A sub image of 3 3 (b) obtained 2 2 edge matrix 91
8 5.3.3 Generation of RETU from Edge matrix: The proposed method extracted local image information in the form of texture unit from obtained 2 2 edge matrix as represented in figure 5.4. The obtained 2 2 edge matrix represents the smallest complete unit and it is different from usual texture unit that is represented in the literature. In the proposed method a 2 2 sub edge image is decomposed into a set of essential small unit called texture unit (TU), which characterize the local texture edge information. The following procedure is used to derive RETU of the TU values. For each 2 2 edge representation the following steps are evaluated to obtain RETU. 1. Sort the elements of each 2 2 edge matrix. 2. Assign the ranks (0, 1, 2 or 3) to the sorted elements of edge matrix (E 0(r 0), E 1(r 1), E 2(r 3) and E 3(r 3)). While assigning the rank values, if any values in 2 2 edge matrix are same then same rank is assigned. 3. By step two each element of TU (R 1, R 2, R 3 and R 4), will have only one of the four possible values {0, 1, 2 or 3}. From this TU value is calculated by using the equation 5.6. This texture unit is named as Rank based Edge Texture Unit (RETU). 4, 1 /2 =1,2,3,4 5.6 where x i is the element of TU in 2 2 edge matrix. By equation 5.6 the TU values of the proposed RETU ranges from 0 to 17 only. There is no unique way to label and order the 17 texture units. 92
9 The illustration process of generating the RETU from original facial image is shown in figure 5.4. The proposed RETU reduces the original matrix of size N M into N/3 M/ (a) (b) ( c) (d) Figure 5.4: The illustration process of RETU (a) original image (b) edge image after applying Robinson compass masks (c) rank values on edge image (d) RETU Generation of Co-occurrence matrices on RETU matrix Grey level co-occurrence matrices (GLCM) introduced by Haralick [33] attempt to describe texture by statistically sampling how certain grey 93
10 levels occur in relation to other grey levels. One of the major inconveniences of Co-occurrence Matrix (CM) is the large range of its possible values (256 gray values) at the same time that these values are not correlated. It also requires more computation time. In general, the size of CM depends on gray level range of the image. To reduce gray values on images and also to reduce overall dimension of the image, the present study used CM on the proposed RETU. A set of RETU-CM, features defined by Haralick are extracted on facial image. The features used in this method are energy, entropy, inertia, local homogeneity, correlation, and cluster shade. They are represented from equations ( ). The proposed RETU-CM combines the merits of both statistical and structural information of images and thus represents complete information of the facial image. Entropy= ln P P, Energy= ln P, Inertia= P i j, P Local Homogenity= 1+ i j, Correlation= P, i µ j µ σ 5.11 h = i M + j M P,
11 5.4 RESULTS AND DISCUSSIONS The proposed scheme established a database of the 1002 face images collected from FG-NET database, 500 face images collected from Google database and other 600 images collected from the scanned photographs. This leads a total of 2102 sample facial images. Sample images of each group images are shown in figure 1.4. The present proposed RETU-CM classified the seven different age groups by using the following two methods. 1) Proposed age group classification algorithm on RETU-CM features. 2) Using Leave one out method on RETU-CM features Age group classification by the proposed algorithm on the proposed RETU-CM features. The proposed method classifies the facial images into seven age groups 1 to 10, 11 to 20, 21 to 30, 31 to 40, 41 to 50, 51 to 60 and greater than 60. The statistical features are extracted from RETU-CM of different age groups of facial images and the results are stored in the feature database. Feature set leads to representation of the training images. The statistical features of seven groups of facial images are shown in tables 5.1, 5.2, 5.3, 5.4, 5.5, 5.6 and 5.7 respectively. The classification algorithm to classify the facial image is given in algorithm 5.1. To show the significance of the proposed RETU-CM method, probe or test images are taken. On probe image, RETU-CM features are evaluated on the facial image. Based on the age group classification algorithm using RETU-CM features, the probe images are tested. For this 40 probe images are collected randomly from various data bases, belonging to various age groups are given in table 5.8. The table 5.8 gives the classification rate of 92.5%. 95
12 Table 5.1: RETU-CM feature set values of age group from 1 to 10 years SN IMAGE Homo correlation shade Cluster Inertia Energy Entropy O NAME geneity 1 001A A A A A A A A A A A A A A07a A07b Table 5.2: RETU-CM feature set values of age group from 11 to 20 years SNO IMAGE Homogeneitrelation shade Cor- Cluster Inertia Energy Entropy NAME A A A A A A A A A A A A A16a A16b A
13 Table 5.3: RETU-CM feature set values of age group from 21 to 30 years SNO IMAGE Homo- Cor- Cluster Inertia Energy Entropy NAME geneity relation shade A A A A A A A A A A A A A A A22a Table 5.4: RETU-CM feature set values of age group from 31 to 40 years SNO IMAGE Homo Cor Cluster Inertia Energy Entropy NAME geneity relation shade A A A A A A A A A A A A A A A
14 Table 5.5: RETU-CM feature set values of age group from 41 to 50 years IMAGE Homo Cor- Cluster SNO Inertia Energy Entropy NAME geneity relation shade A43a A A A A A A A A A A A A A43b A Table 5.6: RETU-CM feature set values of age group from 51 to 60 years SN IMAGE Homogeneity relation Cor- Cluster Inertia Energy Entropy O NAME shade 1 006A A A A A A A A A A
15 Table 5.7: RETU-CM feature set values of age group greater than 60 years SN IMAGE Homogeneity relation Cor- Cluster Inertia Energy Entropy O NAME shade 1 006A A A A A A A A A A A Algorithm 5.1 : Age group classification using RETU-CM features if ( ENTROPHY < 100 ) print ( facial image age is 1-10) Table. 9: classification rates of facial databases else if ( ENERGY < 1000) % correct classification print ( Image facial image Database age is ) rates FG-NET ageing else if ( HOMOGENITY database > 200 ) print Google ( facial Images image age is ) Scanned Images else if ( CORRELATION < 0.02 ) print ( facial image age is > 60 ) else if ( CLUSTER SHADE < 9000 ) print ( facial image age is 31-40) else if ( INERTIA > 150 ) print ( facial image age is 41-50) else print ( facial image age is 51-60) end 99
16 Table 5.8: successful classification results of test data bases for the Image name Inert ia proposed RETU-CM method. Entrop y Homo geneit y Energy correlatio n Cluste r shade Classifi ed age group Result 002A Success 002A Success 014A Success 015A Success 014A Success 021A Success 021A Fail 021A Success 025A Success 025A Success 027A Success 028A Success 028A Success 028A Success 033A Success 039A Success 047A Success 048A Success Sci Success Sci Success Sci >60 Fail Sci >60 Success Sci >60 Success Sci Success Success Success Success Success Success Success Success Success Success 100
17 Success Success Fail Success Success Success Success Age group classification by Leave one out method: The present chapter used another classification technique called Leaves One Out classifier [51] for the age group classification. To evaluate the correct classification on the proposed RETU-CM using the above classifier the following three situations are considered: Setup 1: The training set considers only the original sub images and the others are used for testing. (Approximately 20% are used for training and 80% for testing) Setup 2: The training set considers of sub images with rotation angle of 0 0, 45 0, 90 0, and, (approximately 30% are used for training and 70% for testing). Setup 3: The training set considers half of all sub images that are selected randomly (50% are used for training and 50% for testing). The absolute difference of the feature vector values of the query image and database images are calculated. After that, a threshold and k- NN classifier is used to measure the similarity between query image and the database images. The classification results of different age groups are tabulated in table 5.9 using leave one out method, where each entry corresponds to the 101
18 average correct classification rate of different kinds of facial images. By comparing the table 5.9 and 5.10 it is clearly evident that the classification by Leave One Out method, and the proposed age classification algorithm on the proposed RETU-CM classifies the facial image into seven groups with an average classification rate of 93%. and 95% respectively. The complexity of the Leave One O0ut method is high when compared to the proposed classification algorithm. So the present chapter observed from table 5.9 the classification rate for seven age groups by using leave one out method on the proposed RETU-CM features energy, entropy and contrast gives high classification rate compared to remaining features. Table 5.9: Mean % classification of facial images Group Inertia Energy Entropy Homo geneity correlation Cluster shade > Comparison with other Methods Though the proposed classification algorithm based on RETU-CM is powerful in classification of age groups with a span of 10 years. Still it is compared with various existing algorithms. In skin wrinkle geograph map [124] three age groups are classified i.e. child, adults and senior adults between age groups 1 to 10, and 102
19 above 60 respectively. Since 7 age groups are not classified by [124], the proposed age classification method on RETU-CM features is modified to classify age groups into three groups in the following way by using only entropy and homogeneity parameters. The proposed algorithm is given below. The classification results by the proposed method and skin wrinkle analysis are given in table Table 5.10: % mean classification rates for proposed method and craniofacial development theory and skin wrinkle analysis method. Image cranio-facial development Proposed Method theory and skin wrinkle RETU-CM analysis Child age 78.15% 97.23% adults 79.31% 96.42% Senior adults 81.57% 97.57% Algorithm 5.2: Age group classification to classify age into three categories by the proposed RETU-CM features if ( ENTROPHY < 100 ) print ( facial image age is child s age) else if ( HOMOGENITY < 13) else end print ( facial image age is adult s age) print ( facial image age is senior adult s age) In another Facial Feature method [130] four age groups are classified as babies, young-adults, middle age adults, old adults between the age group 1 to 2, 3 to 39, 40 to 60 and above 61years respectively. The 103
20 proposed age classification algorithm based on RETU-CM used only clustershade and energy parameters to classify above age groups. The proposed algorithm is given below and the classification results are given in table Table 5.11: % mean classification rates for proposed method and Facial Image feature method Facial Features Proposed Method RETU-CM Babies 92.52% 100% Young Adults 91.72% 96.37% Middle age adults 91.47% 97.23% Senior adults 90.07% 96.78% Algorithm 5.3: Age group classification to classify age into four categories by the proposed RETU-CM features if (CLUSTER SHADE < 10 ) print ( facial image age is Baby) else if ( CLUSTER SHADE > 100) AND CLUSTER SHADE > 10000) print ( facial image age is YOUNG adult s age) else if ( ENERGY < 2000) else end print ( facial image age is MIDDLE adult s age) print ( facial image age is OLD adult s age) Various authors classify the age groups into various categories. The present study tabulated the various age classification rates in the following table
21 Table 5.12: Comparison with Other Methods S. No. Authors Name of the Method % of Classifica -tion Rate Type of Age Classification Proposed Method (RETU- CM) Chandra Sekhar et al.,[12] Chandra Mohan et al.[11] Chandra Mohan et al.[13], Chandra Mohan et al., Chandra Mohan et al[14]., Young H. Kwon, et al.[130] Tsuneo KANNO, et al., Wen-Bing Horng, Cheng-et al.[124], Age group classification of facial images using rank based edge texture unit Texton based shape features on local binary pattern for age classification Novel Method for Child and Adulthood Classification (CAC) Based on Geometrical Features of Facial Image. Novel Method of Child and Adulthood Classification Using Linear Wavelet Transforms. Age Classification of Adults Based on Topological Texture Features of Facial Skin. Novel Method of Adult Age Classification Using (2-level) Linear Wavelet Transforms. Age Classification from Facial Images, Computer Vision and Image understanding Vol. 74, No. 1, April, pp. 1 21, Classification of Age Group Based on Facial Images of Young Males by Using Neural Networks, IEICE Trans.. Inf. & Syst., Vol.E84 D, No.8, August Classification of Age Groups Based on Facial Features, Tamkang Journal of Science and Engineering, Vol. 4, No. 3, pp (2001) % , 11-20,21-30, 31-40, 41-50, and > 60 Child Adulthood Child Adulthood Child Adulthood and and and 16-25, 26-35, 36-45, 46-55, 56-65, and , 26-35, 36-45, 46-55, 56-65, and Babies, adults, and Senior adults. Only young males are age groups considered for classifications are 12, 15, 18 and 22 years. Classified age groups are babies, young adults, middleaged adults, and old adults SUMMARY The proposed method RETU-CM features classifies the facial images into seven age groups (1-10, 11-20, 21-30, 31-40, 41-50, 51-60, and age 105
22 greater than 60 years) very efficiently and effectively. So far, no research has attempted, for this type of age classification. The proposed method derived a new age group classification feature using rank based edge texture units. The novelty of the proposed method is, that reduces the overall dimension of the image by three times while preserving the local features. The other advantage of the derived RETU features is it reduced the TU size from 0 to 6561 and 0 to 79 to 0 to 17 as in the case of original TU and fuzzy texture units respectively. That is why the proposed RETU is more suitable for the evaluation of Co-occurrence features and it reduced greatly the overall complexity. The proposed method does not need a particular classification algorithm. The complexity of proposed method is reduced drastically because of its simplicity than Leave One Out method. The proposed method RETU-CM features is also tested by using leave one out classification method for classification of age groups into seven groups (1-10, 11-20, 21-30, 31-40, 41-50, 51-60, and age greater than 60 years). This technique also yielded a classification rate of above 95%. When compared with other approaches, the proposed scheme is more effective and exhibiting effective and significant classification ability by using minimum subset of co-occurrence features (i.e., energy, entropy and contrast). The experimental results clearly indicate the efficacy of the proposed RETU-CM over the various the other existing methods. There are several directions that need to be further explored. The problem of varying orientation of the face needs to be addressed. 106
Colour Image Segmentation Technique for Screen Printing
60 R.U. Hewage and D.U.J. Sonnadara Department of Physics, University of Colombo, Sri Lanka ABSTRACT Screen-printing is an industry with a large number of applications ranging from printing mobile phone
More informationAssessment. 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 informationModelling, 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 informationAnalecta Vol. 8, No. 2 ISSN 2064-7964
EXPERIMENTAL APPLICATIONS OF ARTIFICIAL NEURAL NETWORKS IN ENGINEERING PROCESSING SYSTEM S. Dadvandipour Institute of Information Engineering, University of Miskolc, Egyetemváros, 3515, Miskolc, Hungary,
More informationClassification 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 informationPerception of Light and Color
Perception of Light and Color Theory and Practice Trichromacy Three cones types in retina a b G+B +R Cone sensitivity functions 100 80 60 40 20 400 500 600 700 Wavelength (nm) Short wavelength sensitive
More informationVolume 2, Issue 9, September 2014 International Journal of Advance Research in Computer Science and Management Studies
Volume 2, Issue 9, September 2014 International Journal of Advance Research in Computer Science and Management Studies Research Article / Survey Paper / Case Study Available online at: www.ijarcsms.com
More informationCBIR: Colour Representation. COMPSCI.708.S1.C A/P Georgy Gimel farb
CBIR: Colour Representation COMPSCI.708.S1.C A/P Georgy Gimel farb Colour Representation Colour is the most widely used visual feature in multimedia context CBIR systems are not aware of the difference
More informationCOMPARISON OF OBJECT BASED AND PIXEL BASED CLASSIFICATION OF HIGH RESOLUTION SATELLITE IMAGES USING ARTIFICIAL NEURAL NETWORKS
COMPARISON OF OBJECT BASED AND PIXEL BASED CLASSIFICATION OF HIGH RESOLUTION SATELLITE IMAGES USING ARTIFICIAL NEURAL NETWORKS B.K. Mohan and S. N. Ladha Centre for Studies in Resources Engineering IIT
More informationThe 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 informationGalaxy Morphological Classification
Galaxy Morphological Classification Jordan Duprey and James Kolano Abstract To solve the issue of galaxy morphological classification according to a classification scheme modelled off of the Hubble Sequence,
More informationComparison of Non-linear Dimensionality Reduction Techniques for Classification with Gene Expression Microarray Data
CMPE 59H Comparison of Non-linear Dimensionality Reduction Techniques for Classification with Gene Expression Microarray Data Term Project Report Fatma Güney, Kübra Kalkan 1/15/2013 Keywords: Non-linear
More informationFace 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 informationInternational 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 informationEfficient 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 informationHSI BASED COLOUR IMAGE EQUALIZATION USING ITERATIVE n th ROOT AND n th POWER
HSI BASED COLOUR IMAGE EQUALIZATION USING ITERATIVE n th ROOT AND n th POWER Gholamreza Anbarjafari icv Group, IMS Lab, Institute of Technology, University of Tartu, Tartu 50411, Estonia sjafari@ut.ee
More informationGIS Tutorial 1. Lecture 2 Map design
GIS Tutorial 1 Lecture 2 Map design Outline Choropleth maps Colors Vector GIS display GIS queries Map layers and scale thresholds Hyperlinks and map tips 2 Lecture 2 CHOROPLETH MAPS Choropleth maps Color-coded
More informationOutline. Quantizing Intensities. Achromatic Light. Optical Illusion. Quantizing Intensities. CS 430/585 Computer Graphics I
CS 430/585 Computer Graphics I Week 8, Lecture 15 Outline Light Physical Properties of Light and Color Eye Mechanism for Color Systems to Define Light and Color David Breen, William Regli and Maxim Peysakhov
More informationFPGA Implementation of Human Behavior Analysis Using Facial Image
RESEARCH ARTICLE OPEN ACCESS FPGA Implementation of Human Behavior Analysis Using Facial Image A.J Ezhil, K. Adalarasu Department of Electronics & Communication Engineering PSNA College of Engineering
More informationjorge s. marques image processing
image processing images images: what are they? what is shown in this image? What is this? what is an image images describe the evolution of physical variables (intensity, color, reflectance, condutivity)
More informationBlood Vessel Classification into Arteries and Veins in Retinal Images
Blood Vessel Classification into Arteries and Veins in Retinal Images Claudia Kondermann and Daniel Kondermann a and Michelle Yan b a Interdisciplinary Center for Scientific Computing (IWR), University
More informationMultiscale Object-Based Classification of Satellite Images Merging Multispectral Information with Panchromatic Textural Features
Remote Sensing and Geoinformation Lena Halounová, Editor not only for Scientific Cooperation EARSeL, 2011 Multiscale Object-Based Classification of Satellite Images Merging Multispectral Information with
More informationA New Image Edge Detection Method using Quality-based Clustering. Bijay Neupane Zeyar Aung Wei Lee Woon. Technical Report DNA #2012-01.
A New Image Edge Detection Method using Quality-based Clustering Bijay Neupane Zeyar Aung Wei Lee Woon Technical Report DNA #2012-01 April 2012 Data & Network Analytics Research Group (DNA) Computing and
More informationECE 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 informationAn Introduction to Data Mining. Big Data World. Related Fields and Disciplines. What is Data Mining? 2/12/2015
An Introduction to Data Mining for Wind Power Management Spring 2015 Big Data World Every minute: Google receives over 4 million search queries Facebook users share almost 2.5 million pieces of content
More informationComponent 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 informationCircle Object Recognition Based on Monocular Vision for Home Security Robot
Journal of Applied Science and Engineering, Vol. 16, No. 3, pp. 261 268 (2013) DOI: 10.6180/jase.2013.16.3.05 Circle Object Recognition Based on Monocular Vision for Home Security Robot Shih-An Li, Ching-Chang
More informationTemplate-based Eye and Mouth Detection for 3D Video Conferencing
Template-based Eye and Mouth Detection for 3D Video Conferencing Jürgen Rurainsky and Peter Eisert Fraunhofer Institute for Telecommunications - Heinrich-Hertz-Institute, Image Processing Department, Einsteinufer
More informationREAL TIME TRAFFIC LIGHT CONTROL USING IMAGE PROCESSING
REAL TIME TRAFFIC LIGHT CONTROL USING IMAGE PROCESSING Ms.PALLAVI CHOUDEKAR Ajay Kumar Garg Engineering College, Department of electrical and electronics Ms.SAYANTI BANERJEE Ajay Kumar Garg Engineering
More informationPotential of face area data for predicting sharpness of natural images
Potential of face area data for predicting sharpness of natural images Mikko Nuutinen a, Olli Orenius b, Timo Säämänen b, Pirkko Oittinen a a Dept. of Media Technology, Aalto University School of Science
More informationThe 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 informationMorphological 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 informationImplementation of Canny Edge Detector of color images on CELL/B.E. Architecture.
Implementation of Canny Edge Detector of color images on CELL/B.E. Architecture. Chirag Gupta,Sumod Mohan K cgupta@clemson.edu, sumodm@clemson.edu Abstract In this project we propose a method to improve
More informationDIGITAL IMAGE PROCESSING AND ANALYSIS
DIGITAL IMAGE PROCESSING AND ANALYSIS Human and Computer Vision Applications with CVIPtools SECOND EDITION SCOTT E UMBAUGH Uffi\ CRC Press Taylor &. Francis Group Boca Raton London New York CRC Press is
More information3 An Illustrative Example
Objectives An Illustrative Example Objectives - Theory and Examples -2 Problem Statement -2 Perceptron - Two-Input Case -4 Pattern Recognition Example -5 Hamming Network -8 Feedforward Layer -8 Recurrent
More informationDATA VISUALIZATION GABRIEL PARODI STUDY MATERIAL: PRINCIPLES OF GEOGRAPHIC INFORMATION SYSTEMS AN INTRODUCTORY TEXTBOOK CHAPTER 7
DATA VISUALIZATION GABRIEL PARODI STUDY MATERIAL: PRINCIPLES OF GEOGRAPHIC INFORMATION SYSTEMS AN INTRODUCTORY TEXTBOOK CHAPTER 7 Contents GIS and maps The visualization process Visualization and strategies
More informationIntroduction to Pattern Recognition
Introduction to Pattern Recognition Selim Aksoy Department of Computer Engineering Bilkent University saksoy@cs.bilkent.edu.tr CS 551, Spring 2009 CS 551, Spring 2009 c 2009, Selim Aksoy (Bilkent University)
More informationTexture. Chapter 7. 7.1 Introduction
Chapter 7 Texture 7.1 Introduction Texture plays an important role in many machine vision tasks such as surface inspection, scene classification, and surface orientation and shape determination. For example,
More informationVisualization of large data sets using MDS combined with LVQ.
Visualization of large data sets using MDS combined with LVQ. Antoine Naud and Włodzisław Duch Department of Informatics, Nicholas Copernicus University, Grudziądzka 5, 87-100 Toruń, Poland. www.phys.uni.torun.pl/kmk
More informationOpen issues and research trends in Content-based Image Retrieval
Open issues and research trends in Content-based Image Retrieval Raimondo Schettini DISCo Universita di Milano Bicocca schettini@disco.unimib.it www.disco.unimib.it/schettini/ IEEE Signal Processing Society
More informationSOURCE SCANNER IDENTIFICATION FOR SCANNED DOCUMENTS. Nitin Khanna and Edward J. Delp
SOURCE SCANNER IDENTIFICATION FOR SCANNED DOCUMENTS Nitin Khanna and Edward J. Delp Video and Image Processing Laboratory School of Electrical and Computer Engineering Purdue University West Lafayette,
More informationSYMMETRIC EIGENFACES MILI I. SHAH
SYMMETRIC EIGENFACES MILI I. SHAH Abstract. Over the years, mathematicians and computer scientists have produced an extensive body of work in the area of facial analysis. Several facial analysis algorithms
More informationIntelligent Diagnose System of Wheat Diseases Based on Android Phone
Journal of Information & Computational Science 12:18 (2015) 6845 6852 December 10, 2015 Available at http://www.joics.com Intelligent Diagnose System of Wheat Diseases Based on Android Phone Yongquan Xia,
More informationTracking Moving Objects In Video Sequences Yiwei Wang, Robert E. Van Dyck, and John F. Doherty Department of Electrical Engineering The Pennsylvania State University University Park, PA16802 Abstract{Object
More informationThe 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 informationPredict the Popularity of YouTube Videos Using Early View Data
000 001 002 003 004 005 006 007 008 009 010 011 012 013 014 015 016 017 018 019 020 021 022 023 024 025 026 027 028 029 030 031 032 033 034 035 036 037 038 039 040 041 042 043 044 045 046 047 048 049 050
More informationBig Data: Rethinking Text Visualization
Big Data: Rethinking Text Visualization Dr. Anton Heijs anton.heijs@treparel.com Treparel April 8, 2013 Abstract In this white paper we discuss text visualization approaches and how these are important
More informationPerformance Comparison of Visual and Thermal Signatures for Face Recognition
Performance Comparison of Visual and Thermal Signatures for Face Recognition Besma Abidi The University of Tennessee The Biometric Consortium Conference 2003 September 22-24 OUTLINE Background Recognition
More informationSubspace Analysis and Optimization for AAM Based Face Alignment
Subspace Analysis and Optimization for AAM Based Face Alignment Ming Zhao Chun Chen College of Computer Science Zhejiang University Hangzhou, 310027, P.R.China zhaoming1999@zju.edu.cn Stan Z. Li Microsoft
More informationROBOTRACKER A SYSTEM FOR TRACKING MULTIPLE ROBOTS IN REAL TIME. by Alex Sirota, alex@elbrus.com
ROBOTRACKER A SYSTEM FOR TRACKING MULTIPLE ROBOTS IN REAL TIME by Alex Sirota, alex@elbrus.com Project in intelligent systems Computer Science Department Technion Israel Institute of Technology Under the
More informationCONTENT-BASED IMAGE RETRIEVAL FOR ASSET MANAGEMENT BASED ON WEIGHTED FEATURE AND K-MEANS CLUSTERING
CONTENT-BASED IMAGE RETRIEVAL FOR ASSET MANAGEMENT BASED ON WEIGHTED FEATURE AND K-MEANS CLUSTERING JUMI¹, AGUS HARJOKO 2, AHMAD ASHARI 3 1,2,3 Department of Computer Science and Electronics, Faculty of
More informationVisualization and Feature Extraction, FLOW Spring School 2016 Prof. Dr. Tino Weinkauf. Flow Visualization. Image-Based Methods (integration-based)
Visualization and Feature Extraction, FLOW Spring School 2016 Prof. Dr. Tino Weinkauf Flow Visualization Image-Based Methods (integration-based) Spot Noise (Jarke van Wijk, Siggraph 1991) Flow Visualization:
More informationFUZZY 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 informationImage Segmentation and Registration
Image Segmentation and Registration Dr. Christine Tanner (tanner@vision.ee.ethz.ch) Computer Vision Laboratory, ETH Zürich Dr. Verena Kaynig, Machine Learning Laboratory, ETH Zürich Outline Segmentation
More informationSIGNATURE 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 informationTracking Groups of Pedestrians in Video Sequences
Tracking Groups of Pedestrians in Video Sequences Jorge S. Marques Pedro M. Jorge Arnaldo J. Abrantes J. M. Lemos IST / ISR ISEL / IST ISEL INESC-ID / IST Lisbon, Portugal Lisbon, Portugal Lisbon, Portugal
More informationScienceDirect. Brain Image Classification using Learning Machine Approach and Brain Structure Analysis
Available online at www.sciencedirect.com ScienceDirect Procedia Computer Science 50 (2015 ) 388 394 2nd International Symposium on Big Data and Cloud Computing (ISBCC 15) Brain Image Classification using
More informationVisual 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 informationAn Information Retrieval using weighted Index Terms in Natural Language document collections
Internet and Information Technology in Modern Organizations: Challenges & Answers 635 An Information Retrieval using weighted Index Terms in Natural Language document collections Ahmed A. A. Radwan, Minia
More informationMultimodal 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 informationIntroduction to Computer Graphics
Introduction to Computer Graphics Torsten Möller TASC 8021 778-782-2215 torsten@sfu.ca www.cs.sfu.ca/~torsten Today What is computer graphics? Contents of this course Syllabus Overview of course topics
More informationData Mining: Exploring Data. Lecture Notes for Chapter 3. Introduction to Data Mining
Data Mining: Exploring Data Lecture Notes for Chapter 3 Introduction to Data Mining by Tan, Steinbach, Kumar What is data exploration? A preliminary exploration of the data to better understand its characteristics.
More informationA secure face tracking system
International Journal of Information & Computation Technology. ISSN 0974-2239 Volume 4, Number 10 (2014), pp. 959-964 International Research Publications House http://www. irphouse.com A secure face tracking
More informationAutomatic 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 informationPart-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 informationTopological Data Analysis Applications to Computer Vision
Topological Data Analysis Applications to Computer Vision Vitaliy Kurlin, http://kurlin.org Microsoft Research Cambridge and Durham University, UK Topological Data Analysis quantifies topological structures
More informationBuilding an Advanced Invariant Real-Time Human Tracking System
UDC 004.41 Building an Advanced Invariant Real-Time Human Tracking System Fayez Idris 1, Mazen Abu_Zaher 2, Rashad J. Rasras 3, and Ibrahiem M. M. El Emary 4 1 School of Informatics and Computing, German-Jordanian
More informationDetermining optimal window size for texture feature extraction methods
IX Spanish Symposium on Pattern Recognition and Image Analysis, Castellon, Spain, May 2001, vol.2, 237-242, ISBN: 84-8021-351-5. Determining optimal window size for texture feature extraction methods Domènec
More informationPattern Recognition of Japanese Alphabet Katakana Using Airy Zeta Function
Pattern Recognition of Japanese Alphabet Katakana Using Airy Zeta Function Fadlisyah Department of Informatics Universitas Malikussaleh Aceh Utara, Indonesia Rozzi Kesuma Dinata Department of Informatics
More informationDocument 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 informationOverview. Raster Graphics and Color. Overview. Display Hardware. Liquid Crystal Display (LCD) Cathode Ray Tube (CRT)
Raster Graphics and Color Greg Humphreys CS445: Intro Graphics University of Virginia, Fall 2004 Color models Color models Display Hardware Video display devices Cathode Ray Tube (CRT) Liquid Crystal Display
More informationA Novel Cryptographic Key Generation Method Using Image Features
Research Journal of Information Technology 4(2): 88-92, 2012 ISSN: 2041-3114 Maxwell Scientific Organization, 2012 Submitted: April 18, 2012 Accepted: May 23, 2012 Published: June 30, 2012 A Novel Cryptographic
More informationLOCAL 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 informationMorphological analysis on structural MRI for the early diagnosis of neurodegenerative diseases. Marco Aiello On behalf of MAGIC-5 collaboration
Morphological analysis on structural MRI for the early diagnosis of neurodegenerative diseases Marco Aiello On behalf of MAGIC-5 collaboration Index Motivations of morphological analysis Segmentation of
More informationData Exploration Data Visualization
Data Exploration Data Visualization What is data exploration? A preliminary exploration of the data to better understand its characteristics. Key motivations of data exploration include Helping to select
More informationClustering. Adrian Groza. Department of Computer Science Technical University of Cluj-Napoca
Clustering Adrian Groza Department of Computer Science Technical University of Cluj-Napoca Outline 1 Cluster Analysis What is Datamining? Cluster Analysis 2 K-means 3 Hierarchical Clustering What is Datamining?
More informationPoker 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 informationAn Energy-Based Vehicle Tracking System using Principal Component Analysis and Unsupervised ART Network
Proceedings of the 8th WSEAS Int. Conf. on ARTIFICIAL INTELLIGENCE, KNOWLEDGE ENGINEERING & DATA BASES (AIKED '9) ISSN: 179-519 435 ISBN: 978-96-474-51-2 An Energy-Based Vehicle Tracking System using Principal
More informationMachine vision systems - 2
Machine vision systems Problem definition Image acquisition Image segmentation Connected component analysis Machine vision systems - 1 Problem definition Design a vision system to see a flat world Page
More informationImage Classification for Dogs and Cats
Image Classification for Dogs and Cats Bang Liu, Yan Liu Department of Electrical and Computer Engineering {bang3,yan10}@ualberta.ca Kai Zhou Department of Computing Science kzhou3@ualberta.ca Abstract
More informationA Dynamic Approach to Extract Texts and Captions from Videos
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. 4, April 2014,
More informationELECTRIC FIELD LINES AND EQUIPOTENTIAL SURFACES
ELECTRIC FIELD LINES AND EQUIPOTENTIAL SURFACES The purpose of this lab session is to experimentally investigate the relation between electric field lines of force and equipotential surfaces in two dimensions.
More informationMore Local Structure Information for Make-Model Recognition
More Local Structure Information for Make-Model Recognition David Anthony Torres Dept. of Computer Science The University of California at San Diego La Jolla, CA 9093 Abstract An object classification
More information1. Introduction to image processing
1 1. Introduction to image processing 1.1 What is an image? An image is an array, or a matrix, of square pixels (picture elements) arranged in columns and rows. Figure 1: An image an array or a matrix
More informationVisualization by Linear Projections as Information Retrieval
Visualization by Linear Projections as Information Retrieval Jaakko Peltonen Helsinki University of Technology, Department of Information and Computer Science, P. O. Box 5400, FI-0015 TKK, Finland jaakko.peltonen@tkk.fi
More informationApplying Image Analysis Methods to Network Traffic Classification
Applying Image Analysis Methods to Network Traffic Classification Thorsten Kisner, and Firoz Kaderali Department of Communication Systems Faculty of Mathematics and Computer Science FernUniversität in
More informationVECTORAL IMAGING THE NEW DIRECTION IN AUTOMATED OPTICAL INSPECTION
VECTORAL IMAGING THE NEW DIRECTION IN AUTOMATED OPTICAL INSPECTION Mark J. Norris Vision Inspection Technology, LLC Haverhill, MA mnorris@vitechnology.com ABSTRACT Traditional methods of identifying and
More informationChoosing Colors for Data Visualization Maureen Stone January 17, 2006
Choosing Colors for Data Visualization Maureen Stone January 17, 2006 The problem of choosing colors for data visualization is expressed by this quote from information visualization guru Edward Tufte:
More informationColor Reduction Using Local Features and a Kohonen Self-Organized Feature Map Neural Network
Color Reduction Using Local Features and a Kohonen Self-Organized Feature Map Neural Network Nikos Papamarkos Electric Circuits Analysis Laboratory, Department of Electrical and Computer Engineering, Democritus
More informationDepartment of Mechanical Engineering, King s College London, University of London, Strand, London, WC2R 2LS, UK; e-mail: david.hann@kcl.ac.
INT. J. REMOTE SENSING, 2003, VOL. 24, NO. 9, 1949 1956 Technical note Classification of off-diagonal points in a co-occurrence matrix D. B. HANN, Department of Mechanical Engineering, King s College London,
More informationNorbert Schuff Professor of Radiology VA Medical Center and UCSF Norbert.schuff@ucsf.edu
Norbert Schuff Professor of Radiology Medical Center and UCSF Norbert.schuff@ucsf.edu Medical Imaging Informatics 2012, N.Schuff Course # 170.03 Slide 1/67 Overview Definitions Role of Segmentation Segmentation
More informationDigital image processing
746A27 Remote Sensing and GIS Lecture 4 Digital image processing Chandan Roy Guest Lecturer Department of Computer and Information Science Linköping University Digital Image Processing Most of the common
More informationCanny 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 informationMinnesota Academic Standards
A Correlation of to the Minnesota Academic Standards Grades K-6 G/M-204 Introduction This document demonstrates the high degree of success students will achieve when using Scott Foresman Addison Wesley
More informationCalculation of Minimum Distances. Minimum Distance to Means. Σi i = 1
Minimum Distance to Means Similar to Parallelepiped classifier, but instead of bounding areas, the user supplies spectral class means in n-dimensional space and the algorithm calculates the distance between
More informationAutomatic 3D Reconstruction via Object Detection and 3D Transformable Model Matching CS 269 Class Project Report
Automatic 3D Reconstruction via Object Detection and 3D Transformable Model Matching CS 69 Class Project Report Junhua Mao and Lunbo Xu University of California, Los Angeles mjhustc@ucla.edu and lunbo
More informationVisualization of General Defined Space Data
International Journal of Computer Graphics & Animation (IJCGA) Vol.3, No.4, October 013 Visualization of General Defined Space Data John R Rankin La Trobe University, Australia Abstract A new algorithm
More informationOpen 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 informationPHYSIOLOGICALLY-BASED DETECTION OF COMPUTER GENERATED FACES IN VIDEO
PHYSIOLOGICALLY-BASED DETECTION OF COMPUTER GENERATED FACES IN VIDEO V. Conotter, E. Bodnari, G. Boato H. Farid Department of Information Engineering and Computer Science University of Trento, Trento (ITALY)
More informationCategorical 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