Real-time Video Based Finger Spelling Recognition System Using Low Computational Complexity Artificial Neural Networks

Size: px
Start display at page:

Download "Real-time Video Based Finger Spelling Recognition System Using Low Computational Complexity Artificial Neural Networks"

Transcription

1 Real-time Video Based Finger Spelling Recognition System Using Low Computational Complexity Artificial Neural Networks T. A. C. Bragatto G. I. S. Ruas M. V. Lamar Department of Electrical Engineering Federal University of Parana Curitiba, PR, Abstract The automatic sign language translation still is the most complex and challenging task for video recognition and processing. This work presents the Brazilian Sign Language Automatic Translation project and specifically focuses on low complexity Artificial Neural Networks dedicated to real-time video processing. A new approach for reducing the computational complexity of the activation function of the Multi-Layer Perceptron is proposed in this work, allowing complex processing of video signals be done in real-time. The low complexity neural networks are used in two stages of the system. In the color detection and hand posture classification blocks. The obtained results indicate an increase of the frame rate from 8.6 fps to 28.1 fps using a personal microcomputer with a USB webcam, without reduction of the correct recognition rate. Index Terms Gesture Recognition, Computational Complexity Reduction, Low Complexity Neural Networks. I. INTRODUCTION The communication between men and machines is done mainly by the use of instruments as keyboard and mouse, which are not natural ways of human communication. Therefore, researches that allow computers to see and hear are very important for the creation of a system capable of interact in a more natural way with the human beings. Voice recognition is a very popular study field, and many works have been published. Nowadays, with the advance of the computational power of personal computers, gesture recognition is starting to attract the attention of many researches. The development of real-time video processing systems is still a very challenging task. The most complex and grammatically structured set of human gestures are the gestures associated with the sign languages, used by hearing impaired people. The TALIS (from Portuguese Tradução Automática da Linguagem dos Sinais) project aims to develop a Brazilian Sign Language (LIBRAS) automatic translation system. The system has to be able to translate a video of a sentence gesture performed using the Brazilian Sign Language into voice, at real-time using a portable computer. In telecommunications, the coding of the video signal of signers, very common now-a-days in broadcast television, can be largely improved by using a better modeling of the hand movement, using this information to increase the performance of MPEG4 based codecs. In this work, we propose the use of low computational complexity neural networks for real-time video processing, and present the results obtained from their application in a pixel color classifier and in an user dependent hand posture recognition system. Comparisons of speed in real-time and recognition rate with classical classification methods, and published similar works are presented also. The paper is organized as follows: First, the proposed system is briefly described; next the methodology of the implementation of Artificial Neural Networks (ANN) with low computational cost is presented. The obtained results in an experiment of real-time hand location and posture recognition are presented and analyzed, and finally, the conclusions of this work are given. II. HAND GESTURE RECOGNITION SYSTEM The proposed block diagram of the hand gesture recognition system is shown in Fig.1. This system is still being developed and it aims to analyze and classify two hand gestures, that is to locate and tracking the position of the hands in a limited 2-D space jointly with the analysis of the variations of the hands postures over the time[1]. Fig. 1. Block diagram of the proposed hand gesture recognition system In this work, we are interested on the study of an efficient method to locate one hand over a video signal and classify its static posture at real-time. In order to reduce the computational effort of the tracking stage, an inexpensive color glove is used, where each finger has one different color, shown in Fig. 2. Such approach has been tested and approved by many researches [2][3][4]. The use of a color glove allows a quicker detection and modeling of the fingers postures than systems operating with free hand, which need a complex skin color detection stage[5], besides the modeling of a free hand becomes much more elaborated and computationally complex[5]. Each stage of Fig. 1 is briefly explained next. SBrT 955

2 Fig. 2. The color glove used in this work Fig. 3. Color classifier output A. Capture Stage We are working under Windows R environment, using Microsoft Visual C 6.0 R compiler with OpenCV, an opensource computer vision library, from Intel[6]. The OpenCV uses DirectX s Direct Show for capture, allowing acquisition of video signals at high frame rates from any popular webcam using a USB interface. When creating a new capture session, a callback function is defined in OpenCV. This function is called for each new grabbed frame. Inside this function the whole system is developed. All functions have been written in ANSI C, so it is straightforward to migrate the system either to Linux or MacOS, two platforms also supported by OpenCV. The possibility of using Linux Operating System leads this project to the encounter of the Brazilian government software politics that encourage the use of free software. Figure 2 shows an example of image grabbed by the system. In this work the background subtraction technique is used [7] in order to improve more the speed of the system, reducing the amount of pixels that need be analyzed by the next stages. B. Image Pre-Processing Once a video frame is grabbed, the image pre-processing step is performed in order to locate the hand. The preprocessing is composed by a color classifier based on ANN followed by two morphological filters. 1) Color Classification using ANN: The first step is to transform each pixel of the acquired image from the RGB color space to a set of 7 previous defined colors sub-space - one color for each finger, one for the palm of the hand, and one color representing the pixels that do not belong to the glove. A 3 layer Multi-Layer Perceptron (MLP) ANN has been designed for classifying each pixel in one of the 6 possible classes. 2) Morphological Filters: After color classification stage, an image matrix where each element is an integer number ranging from 0 to 6 is obtained. This matrix corresponds to a very noisy image with large amount of small regions that do not belong to the hand. This noise is mainly created by the own user s body and wears, non-uniform background, illumination and digitalization problems, Fig 3. To improve the quality of the image, two morphological filters are used. First an erosion filter is applied, which erases the isolated pixels or the ones in small connected regions. Next, a dilation filter is applied, acting in the opposite way. This improves the definition of the borders and close small gaps inside colored areas. The result of these filtering is shown in Fig. 4. Despite the use of both morphological filters, a great amount of no interest regions is left in the image. To seek the hand, all remaining connected regions are checked by their area and centroid. Fig. 4. Image obtained from the morphological filtering C. The Hand Modelling With the centroids and areas, the remaining regions are analyzed by the hand model proposed in [8]. The final selected regions are show in Fig 5. From each region a 4-D characteristic vector is extracted using the methodology proposed by Lamar et al. [8]. Using only the fingers information a time dependent 20-D vector is generated which represents the hand posture in a time moment. So, a hand motion is characterized by a temporal sequence of the 22-D vectors, where two components are the centroid of the hand palm, to locate the position of the hand in the image, and remaining 20 dimensions are used to model its posture. Fig. 5. Final selected regions supposed to belong to the color glove D. Hand Posture Classification Using ANN Given that this work aims to analyze only static hand postures, the information of the hand location is not used SBrT 956

3 and the system analyzes continually each captured frame. A MLP ANN was trained from the Brazilian Sign Language hand alphabet, shown on Fig. 6. The MLP ANN architecture has 20 input neuron and 26 output neurons. The number of hidden neurons and hidden layers was experimentally defined and is described on section IV. the sigmoidal activation function in real-time neural network systems. The sigmoidal function requires the computation of one division, one sum and one exponential. To reduce the computational complexity a piecewise linear approximated activation function is used. For a three lines approximation, the sigmoidal function is approximated by 0 x< 2.2, Φ(x) = 1 x>2.2, (2) x x 2.2. resulting a function composed by one multiplication, one sum and two comparisons. Figure 7 shows the sigmoidal and the 3 lines piecewise linear activation functions. Fig. 6. Brazilian Sign Language hand alphabet The most computationally expensive stage of the proposed system is the image pre-processing. Every pixel must be analyzed, classified and the connected regions also must be processed in order to generate a characteristic vector of each hand posture in the video sequence. The output classifier is also an important point, because the hand posture will be classified for every input frame. III. LOW COMPUTATIONAL COMPLEXITY ARTIFICIAL NEURAL NETWORK In order to allow the implementation of highly computationally demanding systems, such as video processing systems, based on neural networks in real-time, a study of the computational complexity of the implementation of such neural systems has been done by many researchers[9][10]. Most of them aim to design computationally efficient network structures, considering the number of neurons units and layers, as well the type of activation function. For programming implementation of systems using MLP ANN, the most computationally expensive is the activation function, which involves the evaluation of a sigmoidal non-linear function, defined by 1 Φ(x) = 1+e x (1) where Φ(x) is the sigmoidal activation function and x is the pondered sum of the neuron inputs. To reduce this complexity Bragatto et al. [11] proposed the use a piecewise linear approximation for the implementation of Fig. 7. Activation Functions A Computational Complexity Index (ICC) is defined to compare the speed gain of using the approximation. It is a index based on the assignment of relative weights for every mathematical operation, computer action and command, for analyzing a section of program code[11]. The ICC is used in this work to compare the obtained results. IV. RESULTS The results presented in this section were obtained using a Pentium IV 2.4 GHz, 512 MBytes RAM microcomputer and a simple webcam that provides 352x288 pixel images, 24 bits/pixel at a maximum frame rate of 30fps. The experiment environment is a typical computer research laboratory, with complex background and no rigorous luminosity control, as shown in Fig. 2. A. Color Classification A 3 layer MLP ANN has been designed for classifying each pixel in one of the 6 possible classes. The ANN has 3 input neurons, one for each RGB component normalized between -1 and 1. The outputs consist of 6 neuron units, which indicate the classified color of the input pixel. The training set has been built with 50 examples of pixels of each color, sampled from different angles and luminosity SBrT 957

4 conditions. The test set is composed by 30 pixels for each color, sampled from other acquired images. To minimize the computational complexity, ANNs with 5, 4, 3 and 2 neurons on the hidden layer have been tested. The results obtained using the networks with 5 and 4 neurons were equivalent to the one with 3 hidden neurons. The network with only 2 neurons did not achieve satisfactory results. Based on this analysis, the network with 3 neurons on the hidden layer was chosen. The network structure is shown by Fig. 8, where the connections with bias are not shown. Fig. 9. ANN error in the test set Fig. 8. The proposed ANN structure for color classification TABLE I COLOR CLASSIFICATION RESULTS Method ICC Correct Recognition Rate TM Euclidean % TM City Block % K-NN Euclidean 2, % ANN Sigmoidal % ANN Piecewise % K-NN City Block 1, % Each output neuron corresponds to one color belonging to the glove. The winner-takes-all approach validates the color of the largest output neuron level. As it does not have an output neuron indicating the colors that do not belong to the glove, a threshold is defined in agreement with the confidence of the ANN in the classification. If the winner neuron output level is less than 0.65, value empirically determined, the pixel is considered as not belonging to the glove, so it has the black color attributed. Once the weights of the ANN were trained using the classical Error Backpropagation algorithm, it was implemented in a classical way, using sigmoidal activation function, and also using the proposed approach of using a piecewise linear activation function. The ANNs had their performances compared with classical classifiers based on Template Matching (TM)[12] and K- Nearest Neighbor (K-NN). The metrics tested are the Euclidean and City-Block distances. The same training set used to train the ANNs were used to determine the TM templates. One template for each color is assigned as the average of the samples points of that color. In the K-NN classifier, all training set is used as templates and the best result was obtained using K =1. Figure 9 presents the error on the test set - formed by 180 samples, 30 samples for each color of the glove. This error is calculated by the difference of the correct and the obtained outputs of the ANN. Once the confidence threshold defined is 0.65, the outputs larger than 0.35(dashed line) are considered errors. Table I shows the ICC and correct recognition rate obtained in the color classification stage using K-Nearest Neighbor (K- NN), Template Matching (TM), classic ANN (Sigmoidal) and low computational complexity ANN (Piecewise), in a test set. As expected, the fastest classifier is the Template Matching using City Block distance, however its correct color identi- fication rate is very poor. On the other hand, the best color classifier is obtained applying K-NN with City Block distance metric, achieving 93.8% of correct classification. However, it uses all training set as template vectors increasing considerably the computational effort, achieving an ICC of 1,824, near to 50 times slower than TM City Block. ANN classifiers give better classification rate, comparable with K-NN, having only a very low computational complexity. The use of 3 lines approach piecewise linear activation function reduces the ICC from 364 to 81, allowing the implementation of systems having color classification stage almost 4,5 times faster and without any reduction in the recognition rate, 93.3%. Figure 10 shows the importance of a efficient color classification scheme for the next stages and hand location. We can see that the Template Matching produces a very poor hand modeling, losing important information, making more difficult the posterior hand posture classification. On the other hand, ANN achieves very good visual results for both detection and hand modeling. In this work, the system analyzes every acquired frame, so a reduction of approximately 80% in the computational complexity of the ANN color classifier, allows an increment of the frame rate from 8.7 fps to 27.1 fps. It is because each pixel of the image is processed by this ANN causing a massive computational saving. B. Hand Posture Classification Table II presents a comparison of the use of ANN and classic classifiers in the hand posture recognition stage. In these experiments two networks with different architectures gave equivalent results. ANN1 is a MLP ANN with 1 hidden layer and 100 hidden neuron units. ANN2 is a MLP ANN with 2 hidden layers and 30 neurons on each hidden layer. SBrT 958

5 Fig. 10. (a) (b) (c) (d) (e) (f) Color. (a)(d) Original (b)(e) TM-Euclidean (c)(f) ANN - Sigmoidal TABLE II HAND POSTURE CLASSIFICATION RESULTS Method ICC Correct Recognition Rate TM Euclidian 1, % TM City Block 1, % K-NN Euclidian 31, % K-NN City Block 21, % ANN1 Sigmoidal 13, % ANN1 Piecewise 9, % ANN2 Sigmoidal 7, % ANN2 Piecewise 4, % In this classification stage, ANN overcame the quality of all classic methods. Due to the noisy input data, even K- NN, which is well known, is not an appropriate classification method for noisy signals. ANN are able to model better the problem due it inherent noise robustness. TM is the lightest classification method, however its recognition performance is not good. Comparing ANN1 and ANN2, we can conclude that the use of 2 hidden layers is able to solve a problem with less computational effort, because has a reduced number of neurons and weights to train and more inter connectivity between neurons, when compared with a large 1 hidden layer ANN. Since this stage in executed only once per frame, the speed gain of using a low computational complexity ANN is not so significant, improving the frame rate from 27.1 to 28.1 fps. Table III shows a comparison with related published work using color gloves, different approaches and backgrounds homogenous and complex as well as their recognition rate. TABLE III COMPARISON WITH RELATED WORKS Approach Method Background Recognition Rate Iwai[13] Decision Tree Homogeneous 92.3% Lamar[8] Neural Network Complex 94.5% Proposed Method Neural Network Complex 99.2% Both first and second authors are using finger spelling from American Sign Language(ASL) which has also 26 different hand postures. So the proposed system outperform both approaches. V. CONCLUSIONS This paper presents the TALIS project, which aims to develop a Brazilian Sign Language Automatic Translation System. This work specifically proposes the use of a piecewise linear activation function on two neural networks, for color classification and hand posture recognition, aiming to produce video processing in real-time. Comparisons using different classification methods and development environments are also shown, demonstrating how the same system can be implemented, obtaining different speeds of processing. The use of low complexity neural networks allows a considerable decrement of the computational complexity of the whole system, achieving 28.1 fps for a continuous hand posture classification from Brazilian Sign Language hand alphabet set. New technologies of classification are being tested, such as Support Vector Machines and a second prototype is being developed, using not only static hand postures. ACKNOWLEDGMENTS The authors would like to give special thanks to CNPq The Brazilian National Council for Scientific and Technological Development for the Scholarship; to IEP Parana s Engineering Institute for supporting author s registration. REFERENCES [1] M.V.Lamar, Md.S.Bhuiyan, and A. Iwata, Hand gesture recognition using t-combnet: A new neural network model, IEICE Trans. on Information and Systems, vol. E83-D, no. 11, pp , [2] K. Abe, H. Saito, and S. Ozawa, 3-d drawing system via hand motion recognition from two cameras, Systems, Man, and Cybernetics, 2000 IEEE International Conference on, vol. 2, no , [3] M. Bray, H. Sidenbladh, and J.-O. Eklundh, Recognition of gestures in the context of speech, Pattern Recognition, Proceedings. 16th International Conference on, vol. 1, no , [4] T. Starner and A. Pentland, Visual recognition of american sign language using hidden markov models, International Workshop on Automatic Face and Gesture Recognition, [5] S.G.Wysoski, M. Lamar, S. Kuroyanagi, and A. Iwata, A rotation invariant approach on static-gesture recognition using boundary histograms and neural networks, 9th International Conference on Neural Information Processing, no , [6] G. Sudra, Seminar medizinische simulationssysteme intel R opencv, [7] Y. Ivanov, A. Bobick, and J. Liu, Fast lighting independent background subtraction, International Journal of Computer Vision, vol. 37, no. 2, pp , [8] M. V. Lamar, M. S. Bhuiyan, and A. Iwata, Hand gesture recognition using morphological principal component analysis and an improved CombNET-II, Proc. of IEEE International Conference on System, Man, and Cybernetics, vol. IV, pp , [9] J. Hertz, A. Krogh, and R. G. Palmer, Introduction to the theory of neural computation. Boston, MA, USA: Addison-Wesley Longman Publishing Co., Inc., [10] J. A. Anderson, A simple neural network generating an interactive memory, pp , [11] T. A. C. Bragatto, J. Y. Sugawara, V. A. P. Benso, and M. V. Lamar, Reconhecimento de gestos em tempo-real utilizando uma rede neural artificial de baixa complexidade computacional para detecção de cores, Brazilian Symposium on Computer Graphics and Image Processing, [12] K. Fukunaga, Introduction to Statistical Pattern Recognition. Academic Press, [13] Y. Iwai, K. Watanabe, Y. Yagi, and M. Yachida, Gesture recognition using colored gloves, IEEE International Conference on Pattern Recognition, vol. A, pp , SBrT 959

Analecta Vol. 8, No. 2 ISSN 2064-7964

Analecta 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 information

GLOVE-BASED GESTURE RECOGNITION SYSTEM

GLOVE-BASED GESTURE RECOGNITION SYSTEM CLAWAR 2012 Proceedings of the Fifteenth International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines, Baltimore, MD, USA, 23 26 July 2012 747 GLOVE-BASED GESTURE

More information

Tracking and Recognition in Sports Videos

Tracking and Recognition in Sports Videos Tracking and Recognition in Sports Videos Mustafa Teke a, Masoud Sattari b a Graduate School of Informatics, Middle East Technical University, Ankara, Turkey mustafa.teke@gmail.com b Department of Computer

More information

Neural Networks and Support Vector Machines

Neural Networks and Support Vector Machines INF5390 - Kunstig intelligens Neural Networks and Support Vector Machines Roar Fjellheim INF5390-13 Neural Networks and SVM 1 Outline Neural networks Perceptrons Neural networks Support vector machines

More information

A secure face tracking system

A 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 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

Neural Network based Vehicle Classification for Intelligent Traffic Control

Neural Network based Vehicle Classification for Intelligent Traffic Control Neural Network based Vehicle Classification for Intelligent Traffic Control Saeid Fazli 1, Shahram Mohammadi 2, Morteza Rahmani 3 1,2,3 Electrical Engineering Department, Zanjan University, Zanjan, IRAN

More information

High-Performance Signature Recognition Method using SVM

High-Performance Signature Recognition Method using SVM High-Performance Signature Recognition Method using SVM Saeid Fazli Research Institute of Modern Biological Techniques University of Zanjan Shima Pouyan Electrical Engineering Department University of

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

VISUAL RECOGNITION OF HAND POSTURES FOR INTERACTING WITH VIRTUAL ENVIRONMENTS

VISUAL RECOGNITION OF HAND POSTURES FOR INTERACTING WITH VIRTUAL ENVIRONMENTS VISUAL RECOGNITION OF HAND POSTURES FOR INTERACTING WITH VIRTUAL ENVIRONMENTS Radu Daniel VATAVU Ştefan-Gheorghe PENTIUC "Stefan cel Mare" University of Suceava str.universitatii nr.13, RO-720229 Suceava

More information

A Study on SURF Algorithm and Real-Time Tracking Objects Using Optical Flow

A Study on SURF Algorithm and Real-Time Tracking Objects Using Optical Flow , pp.233-237 http://dx.doi.org/10.14257/astl.2014.51.53 A Study on SURF Algorithm and Real-Time Tracking Objects Using Optical Flow Giwoo Kim 1, Hye-Youn Lim 1 and Dae-Seong Kang 1, 1 Department of electronices

More information

Journal of Industrial Engineering Research. Adaptive sequence of Key Pose Detection for Human Action Recognition

Journal of Industrial Engineering Research. Adaptive sequence of Key Pose Detection for Human Action Recognition IWNEST PUBLISHER Journal of Industrial Engineering Research (ISSN: 2077-4559) Journal home page: http://www.iwnest.com/aace/ Adaptive sequence of Key Pose Detection for Human Action Recognition 1 T. Sindhu

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

Recurrent Neural Networks

Recurrent Neural Networks Recurrent Neural Networks Neural Computation : Lecture 12 John A. Bullinaria, 2015 1. Recurrent Neural Network Architectures 2. State Space Models and Dynamical Systems 3. Backpropagation Through Time

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

Mouse Control using a Web Camera based on Colour Detection

Mouse Control using a Web Camera based on Colour Detection Mouse Control using a Web Camera based on Colour Detection Abhik Banerjee 1, Abhirup Ghosh 2, Koustuvmoni Bharadwaj 3, Hemanta Saikia 4 1, 2, 3, 4 Department of Electronics & Communication Engineering,

More information

Speed Performance Improvement of Vehicle Blob Tracking System

Speed Performance Improvement of Vehicle Blob Tracking System Speed Performance Improvement of Vehicle Blob Tracking System Sung Chun Lee and Ram Nevatia University of Southern California, Los Angeles, CA 90089, USA sungchun@usc.edu, nevatia@usc.edu Abstract. A speed

More information

HAND GESTURE BASEDOPERATINGSYSTEM CONTROL

HAND GESTURE BASEDOPERATINGSYSTEM CONTROL HAND GESTURE BASEDOPERATINGSYSTEM CONTROL Garkal Bramhraj 1, palve Atul 2, Ghule Supriya 3, Misal sonali 4 1 Garkal Bramhraj mahadeo, 2 Palve Atule Vasant, 3 Ghule Supriya Shivram, 4 Misal Sonali Babasaheb,

More information

Novelty Detection in image recognition using IRF Neural Networks properties

Novelty Detection in image recognition using IRF Neural Networks properties Novelty Detection in image recognition using IRF Neural Networks properties Philippe Smagghe, Jean-Luc Buessler, Jean-Philippe Urban Université de Haute-Alsace MIPS 4, rue des Frères Lumière, 68093 Mulhouse,

More information

Navigation Aid And Label Reading With Voice Communication For Visually Impaired People

Navigation Aid And Label Reading With Voice Communication For Visually Impaired People Navigation Aid And Label Reading With Voice Communication For Visually Impaired People A.Manikandan 1, R.Madhuranthi 2 1 M.Kumarasamy College of Engineering, mani85a@gmail.com,karur,india 2 M.Kumarasamy

More information

An Approach for Utility Pole Recognition in Real Conditions

An Approach for Utility Pole Recognition in Real Conditions 6th Pacific-Rim Symposium on Image and Video Technology 1st PSIVT Workshop on Quality Assessment and Control by Image and Video Analysis An Approach for Utility Pole Recognition in Real Conditions Barranco

More information

Comparison of Supervised and Unsupervised Learning Classifiers for Travel Recommendations

Comparison of Supervised and Unsupervised Learning Classifiers for Travel Recommendations Volume 3, No. 8, August 2012 Journal of Global Research in Computer Science REVIEW ARTICLE Available Online at www.jgrcs.info Comparison of Supervised and Unsupervised Learning Classifiers for Travel Recommendations

More information

A Real Time Hand Tracking System for Interactive Applications

A Real Time Hand Tracking System for Interactive Applications A Real Time Hand Tracking System for Interactive Applications Siddharth Swarup Rautaray Indian Institute of Information Technology Allahabad ABSTRACT In vision based hand tracking systems color plays an

More information

Impact of Feature Selection on the Performance of Wireless Intrusion Detection Systems

Impact of Feature Selection on the Performance of Wireless Intrusion Detection Systems 2009 International Conference on Computer Engineering and Applications IPCSIT vol.2 (2011) (2011) IACSIT Press, Singapore Impact of Feature Selection on the Performance of ireless Intrusion Detection Systems

More information

Object Recognition and Template Matching

Object Recognition and Template Matching Object Recognition and Template Matching Template Matching A template is a small image (sub-image) The goal is to find occurrences of this template in a larger image That is, you want to find matches of

More information

Using Data Mining for Mobile Communication Clustering and Characterization

Using Data Mining for Mobile Communication Clustering and Characterization Using Data Mining for Mobile Communication Clustering and Characterization A. Bascacov *, C. Cernazanu ** and M. Marcu ** * Lasting Software, Timisoara, Romania ** Politehnica University of Timisoara/Computer

More information

Laser Gesture Recognition for Human Machine Interaction

Laser Gesture Recognition for Human Machine Interaction International Journal of Computer Sciences and Engineering Open Access Research Paper Volume-04, Issue-04 E-ISSN: 2347-2693 Laser Gesture Recognition for Human Machine Interaction Umang Keniya 1*, Sarthak

More information

DESIGN OF DIGITAL SIGNATURE VERIFICATION ALGORITHM USING RELATIVE SLOPE METHOD

DESIGN OF DIGITAL SIGNATURE VERIFICATION ALGORITHM USING RELATIVE SLOPE METHOD DESIGN OF DIGITAL SIGNATURE VERIFICATION ALGORITHM USING RELATIVE SLOPE METHOD P.N.Ganorkar 1, Kalyani Pendke 2 1 Mtech, 4 th Sem, Rajiv Gandhi College of Engineering and Research, R.T.M.N.U Nagpur (Maharashtra),

More information

Real Time Vision Hand Gesture Recognition Based Media Control via LAN & Wireless Hardware Control

Real Time Vision Hand Gesture Recognition Based Media Control via LAN & Wireless Hardware Control Vol. 3, Issue. 5, Sep - Oct. 2013 pp-3129-3133 ISSN: 2249-6645 Real Time Vision Hand Gesture Recognition Based Media Control via LAN & Wireless Hardware Control Tarachand Saini,Savita Sivani Dept. of Software

More information

Accurate and robust image superresolution by neural processing of local image representations

Accurate and robust image superresolution by neural processing of local image representations Accurate and robust image superresolution by neural processing of local image representations Carlos Miravet 1,2 and Francisco B. Rodríguez 1 1 Grupo de Neurocomputación Biológica (GNB), Escuela Politécnica

More information

Template-based Eye and Mouth Detection for 3D Video Conferencing

Template-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 information

HANDS-FREE PC CONTROL CONTROLLING OF MOUSE CURSOR USING EYE MOVEMENT

HANDS-FREE PC CONTROL CONTROLLING OF MOUSE CURSOR USING EYE MOVEMENT International Journal of Scientific and Research Publications, Volume 2, Issue 4, April 2012 1 HANDS-FREE PC CONTROL CONTROLLING OF MOUSE CURSOR USING EYE MOVEMENT Akhil Gupta, Akash Rathi, Dr. Y. Radhika

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

Efficient Background Subtraction and Shadow Removal Technique for Multiple Human object Tracking

Efficient Background Subtraction and Shadow Removal Technique for Multiple Human object Tracking ISSN: 2321-7782 (Online) Volume 1, Issue 7, December 2013 International Journal of Advance Research in Computer Science and Management Studies Research Paper Available online at: www.ijarcsms.com Efficient

More information

A Method for Controlling Mouse Movement using a Real- Time Camera

A Method for Controlling Mouse Movement using a Real- Time Camera A Method for Controlling Mouse Movement using a Real- Time Camera Hojoon Park Department of Computer Science Brown University, Providence, RI, USA hojoon@cs.brown.edu Abstract This paper presents a new

More information

Virtual Mouse Using a Webcam

Virtual Mouse Using a Webcam 1. INTRODUCTION Virtual Mouse Using a Webcam Since the computer technology continues to grow up, the importance of human computer interaction is enormously increasing. Nowadays most of the mobile devices

More information

An Introduction to Data Mining

An Introduction to Data Mining An Introduction to Intel Beijing wei.heng@intel.com January 17, 2014 Outline 1 DW Overview What is Notable Application of Conference, Software and Applications Major Process in 2 Major Tasks in Detail

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

Artificial Neural Network for Speech Recognition

Artificial Neural Network for Speech Recognition Artificial Neural Network for Speech Recognition Austin Marshall March 3, 2005 2nd Annual Student Research Showcase Overview Presenting an Artificial Neural Network to recognize and classify speech Spoken

More information

Neural network software tool development: exploring programming language options

Neural network software tool development: exploring programming language options INEB- PSI Technical Report 2006-1 Neural network software tool development: exploring programming language options Alexandra Oliveira aao@fe.up.pt Supervisor: Professor Joaquim Marques de Sá June 2006

More information

Blood Vessel Classification into Arteries and Veins in Retinal Images

Blood 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 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

Tracking Groups of Pedestrians in Video Sequences

Tracking 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 information

REAL-TIME HUMAN-COMPUTER INTERACTION BASED ON FACE AND HAND GESTURE RECOGNITION

REAL-TIME HUMAN-COMPUTER INTERACTION BASED ON FACE AND HAND GESTURE RECOGNITION REAL-TIME HUMAN-COMPUTER INTERACTION BASED ON FACE AND HAND GESTURE RECOGNITION Reza Azad 1, Babak Azad 2, Nabil Belhaj Khalifa 3, Shahram Jamali 4 1 Department of Electrical and Computer Engineering,

More information

Electroencephalography Analysis Using Neural Network and Support Vector Machine during Sleep

Electroencephalography Analysis Using Neural Network and Support Vector Machine during Sleep Engineering, 23, 5, 88-92 doi:.4236/eng.23.55b8 Published Online May 23 (http://www.scirp.org/journal/eng) Electroencephalography Analysis Using Neural Network and Support Vector Machine during Sleep JeeEun

More information

A NATURAL HAND GESTURE HUMAN COMPUTER INTERFACE USING CONTOUR SIGNATURES

A NATURAL HAND GESTURE HUMAN COMPUTER INTERFACE USING CONTOUR SIGNATURES A NATURAL HAND GESTURE HUMAN COMPUTER INTERFACE USING CONTOUR SIGNATURES Paulo Peixoto ISR - Institute of Systems and Robotics Department of Electrical and Computer Engineering University of Coimbra Polo

More information

Technical Trading Rules as a Prior Knowledge to a Neural Networks Prediction System for the S&P 500 Index

Technical Trading Rules as a Prior Knowledge to a Neural Networks Prediction System for the S&P 500 Index Technical Trading Rules as a Prior Knowledge to a Neural Networks Prediction System for the S&P 5 ndex Tim Cheno~ethl-~t~ Zoran ObradoviC Steven Lee4 School of Electrical Engineering and Computer Science

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

Detection and Restoration of Vertical Non-linear Scratches in Digitized Film Sequences

Detection and Restoration of Vertical Non-linear Scratches in Digitized Film Sequences Detection and Restoration of Vertical Non-linear Scratches in Digitized Film Sequences Byoung-moon You 1, Kyung-tack Jung 2, Sang-kook Kim 2, and Doo-sung Hwang 3 1 L&Y Vision Technologies, Inc., Daejeon,

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

Data Mining using Artificial Neural Network Rules

Data Mining using Artificial Neural Network Rules Data Mining using Artificial Neural Network Rules Pushkar Shinde MCOERC, Nasik Abstract - Diabetes patients are increasing in number so it is necessary to predict, treat and diagnose the disease. Data

More information

Keywords: Image complexity, PSNR, Levenberg-Marquardt, Multi-layer neural network.

Keywords: Image complexity, PSNR, Levenberg-Marquardt, Multi-layer neural network. Global Journal of Computer Science and Technology Volume 11 Issue 3 Version 1.0 Type: Double Blind Peer Reviewed International Research Journal Publisher: Global Journals Inc. (USA) Online ISSN: 0975-4172

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

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

Adaptive Face Recognition System from Myanmar NRC Card

Adaptive Face Recognition System from Myanmar NRC Card Adaptive Face Recognition System from Myanmar NRC Card Ei Phyo Wai University of Computer Studies, Yangon, Myanmar Myint Myint Sein University of Computer Studies, Yangon, Myanmar ABSTRACT Biometrics is

More information

FPGA Implementation of Human Behavior Analysis Using Facial Image

FPGA 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 information

Recognition of Single Handed Sign Language Gestures using Contour Tracing Descriptor

Recognition of Single Handed Sign Language Gestures using Contour Tracing Descriptor , July 3-5, 2013, London, U.K. Recognition of Single Handed Sign Language Gestures using Contour Tracing Descriptor Rohit Sharma, Yash Nemani, Sumit Kumar, Lalit Kane, Pritee Khanna, Member, IAENG Abstract

More information

An Active Head Tracking System for Distance Education and Videoconferencing Applications

An Active Head Tracking System for Distance Education and Videoconferencing Applications An Active Head Tracking System for Distance Education and Videoconferencing Applications Sami Huttunen and Janne Heikkilä Machine Vision Group Infotech Oulu and Department of Electrical and Information

More information

Video Surveillance System for Security Applications

Video Surveillance System for Security Applications Video Surveillance System for Security Applications Vidya A.S. Department of CSE National Institute of Technology Calicut, Kerala, India V. K. Govindan Department of CSE National Institute of Technology

More information

Tracking 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 information

How To Use Neural Networks In Data Mining

How To Use Neural Networks In Data Mining International Journal of Electronics and Computer Science Engineering 1449 Available Online at www.ijecse.org ISSN- 2277-1956 Neural Networks in Data Mining Priyanka Gaur Department of Information and

More information

User Authentication using Combination of Behavioral Biometrics over the Touchpad acting like Touch screen of Mobile Device

User Authentication using Combination of Behavioral Biometrics over the Touchpad acting like Touch screen of Mobile Device 2008 International Conference on Computer and Electrical Engineering User Authentication using Combination of Behavioral Biometrics over the Touchpad acting like Touch screen of Mobile Device Hataichanok

More information

Forecasting of Economic Quantities using Fuzzy Autoregressive Model and Fuzzy Neural Network

Forecasting of Economic Quantities using Fuzzy Autoregressive Model and Fuzzy Neural Network Forecasting of Economic Quantities using Fuzzy Autoregressive Model and Fuzzy Neural Network Dušan Marček 1 Abstract Most models for the time series of stock prices have centered on autoregressive (AR)

More information

Basics of Computer 1.1 INTRODUCTION 1.2 OBJECTIVES

Basics of Computer 1.1 INTRODUCTION 1.2 OBJECTIVES Basics of Computer :: 1 1 Basics of Computer 1.1 INTRODUCTION In this lesson we present an overview of the basic design of a computer system: how the different parts of a computer system are organized

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

Practical Tour of Visual tracking. David Fleet and Allan Jepson January, 2006

Practical Tour of Visual tracking. David Fleet and Allan Jepson January, 2006 Practical Tour of Visual tracking David Fleet and Allan Jepson January, 2006 Designing a Visual Tracker: What is the state? pose and motion (position, velocity, acceleration, ) shape (size, deformation,

More information

Tennis Winner Prediction based on Time-Series History with Neural Modeling

Tennis Winner Prediction based on Time-Series History with Neural Modeling Tennis Winner Prediction based on Time-Series History with Neural Modeling Amornchai Somboonphokkaphan, Suphakant Phimoltares, and Chidchanok Lursinsap Abstract Tennis is one of the most popular sports

More information

An Introduction to Neural Networks

An Introduction to Neural Networks An Introduction to Vincent Cheung Kevin Cannons Signal & Data Compression Laboratory Electrical & Computer Engineering University of Manitoba Winnipeg, Manitoba, Canada Advisor: Dr. W. Kinsner May 27,

More information

6.2.8 Neural networks for data mining

6.2.8 Neural networks for data mining 6.2.8 Neural networks for data mining Walter Kosters 1 In many application areas neural networks are known to be valuable tools. This also holds for data mining. In this chapter we discuss the use of neural

More information

Low-resolution Character Recognition by Video-based Super-resolution

Low-resolution Character Recognition by Video-based Super-resolution 2009 10th International Conference on Document Analysis and Recognition Low-resolution Character Recognition by Video-based Super-resolution Ataru Ohkura 1, Daisuke Deguchi 1, Tomokazu Takahashi 2, Ichiro

More information

Overview. 1. Introduction. 2. Parts of the Project. 3. Conclusion. Motivation. Methods used in the project Results and comparison

Overview. 1. Introduction. 2. Parts of the Project. 3. Conclusion. Motivation. Methods used in the project Results and comparison Institute of Integrated Sensor Systems Dept. of Electrical Engineering and Information Technology An Image Processing Application on QuickCog and Matlab Door-Key Recognition System Lei Yang Oct, 2009 Prof.

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

International Journal of Computer Science Trends and Technology (IJCST) Volume 3 Issue 3, May-June 2015

International Journal of Computer Science Trends and Technology (IJCST) Volume 3 Issue 3, May-June 2015 RESEARCH ARTICLE OPEN ACCESS Data Mining Technology for Efficient Network Security Management Ankit Naik [1], S.W. Ahmad [2] Student [1], Assistant Professor [2] Department of Computer Science and Engineering

More information

Face Model Fitting on Low Resolution Images

Face Model Fitting on Low Resolution Images Face Model Fitting on Low Resolution Images Xiaoming Liu Peter H. Tu Frederick W. Wheeler Visualization and Computer Vision Lab General Electric Global Research Center Niskayuna, NY, 1239, USA {liux,tu,wheeler}@research.ge.com

More information

Circle Object Recognition Based on Monocular Vision for Home Security Robot

Circle 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 information

Unconstrained Handwritten Character Recognition Using Different Classification Strategies

Unconstrained Handwritten Character Recognition Using Different Classification Strategies Unconstrained Handwritten Character Recognition Using Different Classification Strategies Alessandro L. Koerich Department of Computer Science (PPGIA) Pontifical Catholic University of Paraná (PUCPR) Curitiba,

More information

Role of Neural network in data mining

Role of Neural network in data mining Role of Neural network in data mining Chitranjanjit kaur Associate Prof Guru Nanak College, Sukhchainana Phagwara,(GNDU) Punjab, India Pooja kapoor Associate Prof Swami Sarvanand Group Of Institutes Dinanagar(PTU)

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

REAL TIME TRAFFIC LIGHT CONTROL USING IMAGE PROCESSING

REAL 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 information

A Color Placement Support System for Visualization Designs Based on Subjective Color Balance

A Color Placement Support System for Visualization Designs Based on Subjective Color Balance A Color Placement Support System for Visualization Designs Based on Subjective Color Balance Eric Cooper and Katsuari Kamei College of Information Science and Engineering Ritsumeikan University Abstract:

More information

Neural Network Design in Cloud Computing

Neural Network Design in Cloud Computing International Journal of Computer Trends and Technology- volume4issue2-2013 ABSTRACT: Neural Network Design in Cloud Computing B.Rajkumar #1,T.Gopikiran #2,S.Satyanarayana *3 #1,#2Department of Computer

More information

CS231M Project Report - Automated Real-Time Face Tracking and Blending

CS231M Project Report - Automated Real-Time Face Tracking and Blending CS231M Project Report - Automated Real-Time Face Tracking and Blending Steven Lee, slee2010@stanford.edu June 6, 2015 1 Introduction Summary statement: The goal of this project is to create an Android

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

Vision based approach to human fall detection

Vision based approach to human fall detection Vision based approach to human fall detection Pooja Shukla, Arti Tiwari CSVTU University Chhattisgarh, poojashukla2410@gmail.com 9754102116 Abstract Day by the count of elderly people living alone at home

More information

Building an Advanced Invariant Real-Time Human Tracking System

Building 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 information

A Content based Spam Filtering Using Optical Back Propagation Technique

A Content based Spam Filtering Using Optical Back Propagation Technique A Content based Spam Filtering Using Optical Back Propagation Technique Sarab M. Hameed 1, Noor Alhuda J. Mohammed 2 Department of Computer Science, College of Science, University of Baghdad - Iraq ABSTRACT

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

Chapter 4: Artificial Neural Networks

Chapter 4: Artificial Neural Networks Chapter 4: Artificial Neural Networks CS 536: Machine Learning Littman (Wu, TA) Administration icml-03: instructional Conference on Machine Learning http://www.cs.rutgers.edu/~mlittman/courses/ml03/icml03/

More information

Implementation of a Wireless Gesture Controlled Robotic Arm

Implementation of a Wireless Gesture Controlled Robotic Arm Implementation of a Wireless Gesture Controlled Robotic Arm Saurabh A. Khajone 1, Dr. S. W. Mohod 2, V.M. Harne 3 ME, Dept. of EXTC., PRMIT&R Badnera, Sant Gadge Baba University, Amravati (M.S.), India

More information

Towards better accuracy for Spam predictions

Towards better accuracy for Spam predictions Towards better accuracy for Spam predictions Chengyan Zhao Department of Computer Science University of Toronto Toronto, Ontario, Canada M5S 2E4 czhao@cs.toronto.edu Abstract Spam identification is crucial

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

Mathematical Model Based Total Security System with Qualitative and Quantitative Data of Human

Mathematical Model Based Total Security System with Qualitative and Quantitative Data of Human Int Jr of Mathematics Sciences & Applications Vol3, No1, January-June 2013 Copyright Mind Reader Publications ISSN No: 2230-9888 wwwjournalshubcom Mathematical Model Based Total Security System with Qualitative

More information

EFFICIENT DATA PRE-PROCESSING FOR DATA MINING

EFFICIENT DATA PRE-PROCESSING FOR DATA MINING EFFICIENT DATA PRE-PROCESSING FOR DATA MINING USING NEURAL NETWORKS JothiKumar.R 1, Sivabalan.R.V 2 1 Research scholar, Noorul Islam University, Nagercoil, India Assistant Professor, Adhiparasakthi College

More information

An Introduction to Data Mining. Big Data World. Related Fields and Disciplines. What is Data Mining? 2/12/2015

An 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 information

Open-Set Face Recognition-based Visitor Interface System

Open-Set Face Recognition-based Visitor Interface System Open-Set Face Recognition-based Visitor Interface System Hazım K. Ekenel, Lorant Szasz-Toth, and Rainer Stiefelhagen Computer Science Department, Universität Karlsruhe (TH) Am Fasanengarten 5, Karlsruhe

More information

Ericsson T18s Voice Dialing Simulator

Ericsson T18s Voice Dialing Simulator Ericsson T18s Voice Dialing Simulator Mauricio Aracena Kovacevic, Anna Dehlbom, Jakob Ekeberg, Guillaume Gariazzo, Eric Lästh and Vanessa Troncoso Dept. of Signals Sensors and Systems Royal Institute of

More information

Artificial Neural Network, Decision Tree and Statistical Techniques Applied for Designing and Developing E-mail Classifier

Artificial Neural Network, Decision Tree and Statistical Techniques Applied for Designing and Developing E-mail Classifier International Journal of Recent Technology and Engineering (IJRTE) ISSN: 2277-3878, Volume-1, Issue-6, January 2013 Artificial Neural Network, Decision Tree and Statistical Techniques Applied for Designing

More information

Using Neural Networks to Create an Adaptive Character Recognition System

Using Neural Networks to Create an Adaptive Character Recognition System Using Neural Networks to Create an Adaptive Character Recognition System Alexander J. Faaborg Cornell University, Ithaca NY (May 14, 2002) Abstract A back-propagation neural network with one hidden layer

More information

Taking Inverse Graphics Seriously

Taking Inverse Graphics Seriously CSC2535: 2013 Advanced Machine Learning Taking Inverse Graphics Seriously Geoffrey Hinton Department of Computer Science University of Toronto The representation used by the neural nets that work best

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