Two Phases Neural Network-Based System for Pornographic Image Classification

Size: px
Start display at page:

Download "Two Phases Neural Network-Based System for Pornographic Image Classification"

Transcription

1 SETIT th International Conference: Sciences Of Electronic, Technologies Of Information and Telecommunications March 2226, 2009 TUNISIA Two Phases Neural NetworkBased System for Pornographic Image Classification Usama SAYED *, Samy SADEK ** and Bernd MICHAELIS *** * Electrical Engineering Department, Faculty of Engineering, Assiut University, Assiut, Egypt usama@aun.edu.eg ** Mathematics & Computer Science Department, Faculty of Science, Sohag University, Sohag, Egypt samy.sakr@yahoo.com *** Institute for Electronics, Signal Processing and Communications,University of Magdeburg, Magdeburg, Germany Bernd. michaelis@ovgu.de Abstract: A robust model for skin detection is the primary need of many fields of computer vision, including face detection, gesture recognition, and pornography detection. In 1996, the first paper on pornographic image detection was published. Since then, different researchers argue different color spaces to be the best choice for skin detection in pornography detection. Unfortunately, no comprehensive work attempts to use more than one color space and evaluate its performance for detecting pornography. In this paper, a new two phases neuralbased system for classifying images into two classes pornographic and nonpornographic is proposed. The proposed system makes use of a fast and precise neural network model based on adaptive transfer function, called Multilevel Sigmoidal Neural Network (MUSNN). Furthermore, the system exploits 5 color spaces in all their possible representations for skin detection in pornographic images. Receiver Operating Characteristics (ROC) curve of the proposed system shows that our system outperforms other pornography detection schemes in the context of detection rate and false positive rate. Plenty of experimental results are presented including photographs and a ROC curve calculated over a test set of photographs, which show stimulating performance. Keywords: Multilevel Sigmoidal Neural Network, Pornography, Color space, Contentbased retrieval INTRODUCTION Images are a vital part of today s World Wide Web. The statistics of more than 4 million HTML webpages reveal that 70.1% of webpages contain images and that on average there are about 18.8 images per HTML webpage [STA 02]. On the other hand, images are also contributing to harmful (e.g. pornographic) or even illegal (e.g. paedophilic) Internet content. So effective filtering of images is important in an Internet filtering solution. To block pornographic content some representative companies as Net Nanny and SurfWatch operate by maintaining lists of URL s and newsgroups and require constant manual updating. Abundant literature is available, but the Internet is very rapidly evolving, not only quantitatively. Each day, 3 million pages are appearing on the Web. Detection based on image content analysis has the advantage to process equally all the images without the need for frequent updating, so will produce more effective filtering. When dealing with detection of pornography in color images, it is important to have a good algorithm of recognizing skin regions. Much work has been done in this regard. References [ANG 01] [HSU 01] [KRU 02] [SHI 02] [STÖ 99] [YAN 98] [BRE 02] discuss detection of human skin and the effect of different cameras, lightsetting, human race and color spaces on the recognition process. Furthermore, references [FOR 96] [REH 99] also use texture information as a component in the skin detection. As a third component in object recognition, many researchers have looked at the shape of the object as a last stage in the information gathering process [ALS 96] [COH 97] [JAI 96] [PAR 01] [SAF 00] [ZHE 06]. Veltkamp and 1

2 Hagedoorn [VEL 99] have written a survey of different stateoftheart shape matching methods. With a set of features describing the image, such as color and shape for segmented objects, it is possible to build fully system for pornographic images detection. The proposed approach is as follows. The first main phase is skin pixels classification. We build a neural networkbased model for the skin distribution. This model uses more than one color spaces. Several simple features from image pixels are calculated. The features are then fed into Multilevel Sigmoidal Neural Network (MUSNN) classifier. The output of this phase is a grayscale skin map with the gray levels being proportional to the skin probabilities. The second main phase is pattern recognition. Several features are calculated from the skin map and ellipses are fitted which form a pattern. A MUSNN classifier is then trained on the training set patterns here; the output of this phase is a real p [0,1] value, probability. proportional to the pornography The rest of this paper is organized as follows: Section 2 discusses the multilevel transfer functions as a functional extension to the existing feedforward neural model. In section 3 a neuralbased skin pixels classifier that makes use of Ohta, Normalized RGB, and YCrCb color spaces is presented. Section 4 is devoted to shape feature extraction and pattern recognition. In section 5, some experimental results are presented. Section 6 concludes this paper. 1 sgd ( x) = (1) 1 βx + e Where, β is the steepness factor of the function. The multilevel form of the sigmoidal function is derived from the previous standard form as fallow: MUSGD( x) sgd( x) + ( λ 1) sgd( c), ( λ 1) c x < λ c (2) Where, λ represents the color index and 1 λ N, N is the number of color scale objects or levels. Here, c represents the color scale contribution. Multilevel sigmoidal (MUSGD) transfer functions for three and five levels (N) are depicted in figures 2 and 3. Figure 1. Sigmoidal transfer function 1. Multilevel transfer functions The neuralbased image classifier has the advantage of being fast (highly parallel), easily trainable and capable of creating arbitrary partitions of feature space. However a neural model, in the standard form, is sometimes unable to correctly classify images. This is due to the fact that each of the component single neuron employs the standard bilevel transfer function as the characteristic transfer function. Since the bilevel transfer function produces only binary responses, the components of the neural network can generate only binary color outputs. So, in order to produce multiple color responses, a functional extension to the existing neural model is required. A multilevel transfer function is a functional extension of the standard transfer functions in existence [BHA 07]. Several multilevel forms pertaining to several standard transfer functions can be designed. At this point, we discuss the basic design mechanism of the multilevel versions of the standard sigmoid (MUSGD) transfer function as follow. The standard sigmoidal transfer function (see figure 1) is given by: 2 Figure 2. MUSGD transfer function for N=3 Figure 3. MUSGD transfer function for N=5 2. Skin pixels classification In this section, a neural networkbased skin pixels classifier that uses Ohta, Normalized RGB and YCrCb color spaces has been described Skin classifier in Ohta space The color axes of Ohta space [OHT 80] are the 3 largest eigenvectors of the RGB space, found

3 through principal components analysis of a large selection of natural images. This yields: I1 = I2 I3 R + G = R B, + = R 2G + B, B (3) The advantage of the Ohta color space is that the color channels are approximately decorrelated, which makes it a good choice for computing color features Skin classifier using RGB channels ratio It was observed, that pixels belonging to skin region regularly contains a significant level of red. Using this observation, certain values of the two g = G/ R and b = B/ R ratios can be used as skin presence indicators [BRA 00] Skin classifier in normalized RGB space Normalized RGB is a representation that is easily obtained from the RGB values by a simple normalization procedure: 2.5. Skin pixels classifier Since there are too many outside factors such as lighting that can change the apparent color of skin, and of course, different people have different colored skin. In addition, objects in the background may be the same color as a person's skin and there is no clear way of telling the difference. To address the above problem, the proposed classifier uses a set of color spaces to extract 9 features for each pixel. It is stated that using pixel features from more than one color spaces is a good idea to precisely extract a more defined skin region. In the implementation of the proposed skin pixels classifier there are some main steps viz. (1)apply neuralbased pixels filter to identify the skin regions, (2)apply median filter to get rid of impulsive saltpepper noise, (3)apply morphological open/close operations to connect broken regions, and (4)The skin regions of areas smaller than predefined threshold,θ are deleted. These regions are too small to be counted as human skin. The main steps of the proposed skin classifier are shown in figure 4. (4) RGB image NN classifier As the sum of the three normalized components is known (r+g+b = 1), the third component does not hold any significant information and can be omitted, reducing the space dimensionality. The reason for using this color space is due to evidences that the human skin color is more compactly represented in it than it is in other color spaces, such as RGB, HSI, SCT and YQQ [PEE 03] [AHL 99] [LIT 97]. Here the two chromaticities r and g are used to describe the skin color Skin classifier in YCrCb space YCrCb is an encoded nonlinear RGB signal, commonly used by European television studios and for image compression work. Color is represented by luma (which is luminance, computed from nonlinear RGB, constructed as a weighted sum of the RGB values, and two color difference values Cr and Cb that are formed by subtracting luma from RGB red and blue components. Y = 0.299R G B, Cr = R Y, Cb = B Y (5) The transformation simplicity and explicit separation of luminance and chrominance components makes this color space attractive for skin color modeling [MEN 00] [YAN 98] [SAB 98]. Skin map Figure 4. Main steps of skin pixels classifier 3. Pornography detection Median filter Open/close filter Small skin regions removal One interesting application of skin pixel classification is as part of a larger system for detecting pornography in photos. A pornography detector that worked reliably to detect pornographic images could be a valuable tool for image search services in digital libraries [WAN 98], as well as for image categorization. The main goal of the proposed pornographic image classification system is to determine whether or not an input image contains a pornographic content by feeding the output of the skin classifier to an MLP classifier, which outputs a number between 0 and 1, with 1 for pornographic image and 0 for nonpornographic image. Figure 5 shows an overview of the proposed pornographic image classification system. 3

4 source image blocked image NN2 NN1 first phase second phase skin map Figure 5. An overview of pornographic image classification system Shape features extraction Many of the features used here are based on the fit ellipses calculated on the skin map, since they could meet the requirement for simplicity and capture some important shape information. It is observed from experiments that for approaches based on skin detection, portraits have a tendence to be classified as pornographic images since generally portraits expose plenty of skin as pornographic ones. The fit ellipses will hopefully at least help discriminate portraits from pornographic images. The features extracted from the skin map includes: average skin probability of the whole image, height and width of the largest region of skin, average skin probability inside the largest skin region, number of skin regions in the image, distance from the centroid of the largest skin region to the center of the image, edge of connected components of skin, percentage of pixels detected as skin, and number of connected components of skin Pornography recognition post processing images shape feature extraction The Multilevel Sigmoidal Neural Network (MUSNN) classifier used here is a semi linear multilayer feedforward network with two hidden layers. The basic model of the MUSNN is most similar to the classical network structures but with improving in the hiddenunit adaptive transfer function. Simulation results demonstrate that the performance of the MSNN in classification accuracies is significant and a computational time is faster than the standard sigmoidal NN models. The net outputs a number between 0 and 1, with 1 for pornographic image and 0 for not. The learning procedure starts off with a random set of weight values. For each training pattern p, the net evaluates the output yp in a feedforward manner. To decrease the error between the output yp and the true target tp, the net calculates the corrections of the weight 4 values using the backpropagation procedure. This procedure is repeated for all the patterns in the training set to yield the resulting corrections for all the weights for that one iteration. In a successful learning exercise, the system error will decrease with the number of iterations, and the procedure will converge to a stable set of weights, which will exhibit only small fluctuations in value as further learning is attempted. In the test phase, for each test pattern, the net calculates the output in one pass. A threshold T, 0<T<1 is then set, to get the binary decision. 4. Experimental results Due to the lack of any standard image databases for testing and comparison of pornographic image classification systems, the proposed system has been tested using our own images database. This database has 667 test pornographic images and 1580 assorted control images, containing some images of people but none of pornographic images. All images were taken of type RGB format with (nominal) 8 bits / pixels in each color channel. The test images were collected from the internet. They show a very wide range of postures. Some depict several people including naked or scantilydressed. Some depict only small parts of the bodies of one or more people. Most people in the images are Caucasian; a small number are Blacks or Asians. To evaluate the results of the proposed pornographic image classifier two different metrics are used. TP (true positive) is the number of pornographic images identified correctly divided by the number of all test images. FP (false positive) is the number of nonpornographic images identified as pornographic images divided by the number of all control images. Receiver operating characteristics (ROC) curve that shows the relationship between correct classification and false classification of the proposed pornographic image classifier as functions of a predefined threshold, T is shown in figure TP Figure 6. ROC curve of the proposed pornographic image classifier. Figure 7 shows the capability of the proposed FP

5 classifier system to classify some clothed images in the test set. These images correctly classified as containing pornography content. (i) (ii) 5. Discussion and comparison of results This paper has shown that the pornographic images can be precisely classified using a combination of simple visual cuescolor, and human figure characteristics. The proposed system successfully classifies 89.9% of the test images, but only 3.3% of the control images. Arentz and Olstad [ARE 04] have proposed a method for helping to identify adult web sites by using the imagecontent as means of detecting erotic material. The average image classification error rates for offensive sites were 14.1%, as compared to 9.8% for nonoffensive. Table 1 summarizes the performance of [ARE 04] system and the proposed one. The figures in the table show that the proposed system improves the performance over the system developed by Arentz and Olstad in the context of classification rate and false positive rate. Table 1. Performance comparison for two pornographic images classifiers. Classifier TP FP (iii) P=0.981 p=0.998 p=0.999 p=0.975 Figure 7. Typical test images correctly classified as pornographic images: (i) Source images; (ii) Result of first phase; (iii) Result of second phase. Mistakes by the proposed pornography classifier occur for several reasons. In some images, the pornographic content is too small to detect. In others, most or all of the skin area is nonsaturated, so it fails the skin classifier. Some control images pass the skin classifier because they contain people, particularly several closeup portrait shots. Other control images contain material whose color closely resembles that of human skin; particularly wood, sand, and skin or fur of certain animals. Fig.8 shows some control images that the proposed system may fail to classify since they take a skinlike color and their average pornography probabilities are very high. p=0.552 p= p=0.563 p=0.791 Figure 8. Typical control images wrongly classified as pornographic images Arentz et al. classifier 85.9% 9.8% The proposed classifier 89.9% 3.3% REFERENCES [AHL 99] Ahlberg, J., A system for face localization and facial feature extraction, Tech. Rep. LiTHISYR 2172, Linkoping University, [ALS 96] Alshuth P., Hermes T., Klauck C., Kreyss J., and Roper M., Iris image retrieval for images and videos, =pdf [ANG 01] Angelopoulou E., Understanding the color of human skin, In Proc. SPIE Conf. On Human Vision and Electronic Imaging VI (SPIE) 2001, SPIE Vol. 4299, SPIE Press, pp , May [ARE 04] Arentz W.A. and Olstad B., Classifying offensive sites based on image content,computer Vision and Image Understanding, 94: , [BHA 07] Bhattacharyya S., Dutta P., Maulik U. and Nandi P. K., "Multilevel Activation Functions for True Color Image Segmentation Using a Self Supervised Parallel Self Organizing Neural Network (PSONN) Architecture: A Comparative Study", International Journal of Computer Science, vol 2, no. 1, pp. 0921, [BRA 00] Brand J., and Mason J., A comparative assessment of three approaches to pixellevel human skindetection, in: Proc. of the International Conference on Pattern Recognition, 2000, vol. 1, pp

6 [BRE 02] Bretzner L., Laptev I. and Lindeberg T., Hand gesture recognition using multiscale color features, hierarchical models and particle filtering, FG02.pdf [COH 97] Cohen S., and Guibas L., Shapebased image retrieval using geometric hashing, Proceedings of the ARPA Image Understanding Workshop, pp , [FOR 96] Forsyth David A., and Fleck Margaret M., Identifying nude pictures, IEEE Workshop on the Applications of Computer Vision, pp , [HSU 01] Hsu R.L., AbdelMottaleb M. and Jain A., Face detection in color images, IEEE Trans. Patt. Anal. Mach. Intell., pp , [JAI 96] Jain, Vailaya A., Image retrieval using color and shape, Pattern Recognition Journal, vol. 29, pp , [KRU 02] Kruppa H., Bauer M.A., and Schiele B., Skin Patch Detection in RealWorld Images, DAGM Symposium, Zurich, Switzerland, pp , [LIT 97] Littmann E., Ritter H., Adaptive color segmentation. A comparison of neural and statistical methods, IEEE Trans. Neural Networks, pp , [MEN 00] Menser B. and Wien M., Segmentation and tracking of facial regions in color image sequences, in: Proc. SPIE Visual Communications and Image Processing, pp , [OHT 80] Ohta YI, Kanade T., and Sakai T.. Color information for region segmentation, Comp. Graph. and Img. Proc., 13:222241, [PAR 01] Park J.S., and Chang D.H., 2d invariant descriptors for shapebased image retrieval, Pattern Recognition Letters, [PEE 03] Peer P.,, Kovac J.,, and Solina F.,, Human skin color clustering for face detection, In submitted to EUROCON 2003 International Conference on Computer as a Tool, [REH 99] Rehg J.M., Murphy K.P., and Fieguth P.W., Visionbased speaker detection using Bayesian networks, in: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Ft. Collins, Colorado, pp , [SAB 98] Saber E and Tekalp A., Frontalview face detection and facial feature extraction using color, shape and symmetry based cost functions, In Pattern Recognition Letters, vol. 9, pp , [SAF 00] Safar M., Shahabi C., and Sun X., Image retrieval by shape: a comparative study, in: IEEE Internat.Conf. on Multimedia and Expo (I), pp , [SHI 02] Shin M.C., Chang K.I., and Tsap L.V., Does colorspace transformation make any difference on skin detection? IEEE Workshop on Applications of Computer Vision, Orlando, FL, pp , December [STA 02] Starynkevitch B., Daoudi M., and et al.. Poesia software architecture definition document. Technical report Deliverable 3.1, POESIA consortium, December pdf. [STÖ 99] StÖrring M., Andersen H.J., and Granum E., Skin color detection under changing lighting conditions, in: H. Araujo, J. Dias (Eds.), 7th Internat. Symp.on Intelligent Robotic Systems, Coimbra, Portugal, pp , [VEL 99] Veltkamp R. and Hagedoorn M., Stateoftheart in shape matching, Technical Report, UUCS , Utrecht University, the Netherlands, 1999 [WAN 98] Wang J.Z., Li J., Wiederhold G., and Firschein O. Classifying objectionable websites based on image content. Notes in Computer Science, Special issue on iteractive distributed multimedia systems and telecommunication services, 21/15: , [YAN 98] Yang J., Lu W.,, and Wibel A., Skincolor modeling and adaptation. In Proceedings of ACCV 1998, pp , [ZHE 06] Zheng QingFang, Zeng Wei, Wang WeiQiang, and Wen Gao "Shapebased Adult Image Detection", Int. J. Image Graphics 6(1): ,

Multicolor Skin Modeling with Application. to Skin Detection

Multicolor Skin Modeling with Application. to Skin Detection Journal of Computations & Modelling, vol.3, no.1, 2012, 153-167 ISSN: 1792-7625 (print), 1792-8850 (online) Scienpress Ltd, 2013 Multicolor Skin Modeling with Application to Skin Detection Samy Sadek 1,

More information

Classifying offensive sites based on image content

Classifying offensive sites based on image content Computer Vision and Image Understanding 94 (2004) 295 310 www.elsevier.com/locate/cviu Classifying offensive sites based on image content Will Archer Arentz * and Bjørn Olstad Department of Computer and

More information

Smart Content Recognition from Images Using a Mixture of Convolutional Neural Networks *

Smart Content Recognition from Images Using a Mixture of Convolutional Neural Networks * Smart Content Recognition from Images Using a Mixture of Convolutional Neural Networks * Tee Connie *, Mundher Al-Shabi *, and Michael Goh Faculty of Information Science and Technology, Multimedia University,

More information

Dynamic skin detection in color images for sign language recognition

Dynamic skin detection in color images for sign language recognition Dynamic skin detection in color images for sign language recognition Michal Kawulok Institute of Computer Science, Silesian University of Technology, Akademicka 16, 44-100 Gliwice, Poland michal.kawulok@polsl.pl

More information

Real-Time Skin Detection and Tracking based on FPGA

Real-Time Skin Detection and Tracking based on FPGA Real-Time Skin Detection and Tracking based on FPGA Saranya.S 1, 1 Student,M.E, Applied electronics, Kingston Engineering College, Vellore Keerthikumar.D.N 2 2 Assistant Professor, Kingston Engineering

More information

Arabic Sign Language Alphabet Recognition Methods Comparison, Combination and implementation

Arabic Sign Language Alphabet Recognition Methods Comparison, Combination and implementation Arabic Sign Language Alphabet Recognition Methods Comparison, Combination and implementation Mohamed Youness Ftichi 1, Abderrahim Benabbou 1, Khalid Abbad 1 1 Dept. of Intelligent Systems and Applications

More information

COMBINING NEURAL NETWORKS FOR SKIN DETECTION

COMBINING NEURAL NETWORKS FOR SKIN DETECTION COMBINING NEURAL NETWORKS FOR SKIN DETECTION Chelsia Amy Doukim 1, Jamal Ahmad Dargham 1, Ali Chekima 1 and Sigeru Omatu 2 1 School of Engineering and Information Technology, Universiti Malaysia Sabah,

More information

Skin Detection - a Short Tutorial

Skin Detection - a Short Tutorial Skin Detection - a Short Tutorial Ahmed Elgammal, Crystal Muang and Dunxu Hu Department of Computer Science, Rutgers University, Piscataway, NJ, 08902, USA Skin detection is the process of finding skin-colored

More information

Comparative Study of Statistical Skin Detection Algorithms for Sub-Continental Human Images

Comparative Study of Statistical Skin Detection Algorithms for Sub-Continental Human Images Comparative Study of Statistical Skin Detection Algorithms for Sub-Continental Human Images M. R. Tabassum, A. U. Gias, M. M. Kamal, H. M. Muctadir, M. Ibrahim, A. K. Shakir, A. Imran, S. Islam, M. G.

More information

Color-based Face Detection using Combination of Modified Local Binary Patterns and embedded Hidden Markov Models

Color-based Face Detection using Combination of Modified Local Binary Patterns and embedded Hidden Markov Models SICE-ICASE International Joint Conference 2006 Oct. 8-2, 2006 in Bexco, Busan, Korea Color-based Face Detection using Combination of Modified Local Binary Patterns and embedded Hidden Markov Models Phuong-Trinh

More information

Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers

Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers A. Salhi, B. Minaoui, M. Fakir, H. Chakib, H. Grimech Faculty of science and Technology Sultan Moulay Slimane

More information

Face Detection Using a Dual Cross-Validation of Chrominance/Luminance Channel Decisions and Decorrelation of the Color Space

Face Detection Using a Dual Cross-Validation of Chrominance/Luminance Channel Decisions and Decorrelation of the Color Space Face Detection Using a Dual Cross-Validation of Chrominance/Luminance Channel Decisions and Decorrelation of the Color Space VICTOR-EMIL NEAGOE, MIHAI NEGHINĂ Depart. Electronics, Telecommunications &

More information

Mouse Pointer Tracking with Eyes

Mouse Pointer Tracking with Eyes Mouse Pointer Tracking with Eyes H. Mhamdi, N. Hamrouni, A. Temimi, and M. Bouhlel Abstract In this article, we expose our research work in Human-machine Interaction. The research consists in manipulating

More information

Computers and Mathematics with Applications. An embedded system for real-time facial expression recognition based on the extension theory

Computers and Mathematics with Applications. An embedded system for real-time facial expression recognition based on the extension theory Computers and Mathematics with Applications 61 (2011) 2101 2106 Contents lists available at ScienceDirect Computers and Mathematics with Applications journal homepage: www.elsevier.com/locate/camwa An

More information

Automatic Shadow Removal by Illuminance in HSV Color Space

Automatic Shadow Removal by Illuminance in HSV Color Space Computer Science and Information Technology 3(3): 70-75, 2015 DOI: 10.13189/csit.2015.030303 http://www.hrpub.org Automatic Shadow Removal by Illuminance in HSV Color Space Wenbo Huang 1, KyoungYeon Kim

More information

A Hybrid Face Detection System using combination of Appearance-based and Feature-based methods

A Hybrid Face Detection System using combination of Appearance-based and Feature-based methods IJCSNS International Journal of Computer Science and Network Security, VOL.9 No.5, May 2009 181 A Hybrid Face Detection System using combination of Appearance-based and Feature-based methods Zahra Sadri

More information

Face Quality Assessment System in Video Sequences

Face Quality Assessment System in Video Sequences Face Quality Assessment System in Video Sequences Kamal Nasrollahi, Thomas B. Moeslund Laboratory of Computer Vision and Media Technology, Aalborg University Niels Jernes Vej 14, 9220 Aalborg Øst, Denmark

More information

Learning based face hallucination techniques: A survey

Learning based face hallucination techniques: A survey Vol. 3 (2014-15) pp. 37-45. : A survey Premitha Premnath K Department of Computer Science & Engineering Vidya Academy of Science & Technology Thrissur - 680501, Kerala, India (email: premithakpnath@gmail.com)

More information

Short Survey on Static Hand Gesture Recognition

Short Survey on Static Hand Gesture Recognition Short Survey on Static Hand Gesture Recognition Huu-Hung Huynh University of Science and Technology The University of Danang, Vietnam Duc-Hoang Vo University of Science and Technology The University of

More information

Fast Face Detection Assisted with Skin Color Detection

Fast Face Detection Assisted with Skin Color Detection IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661,p-ISSN: 2278-8727, Volume 18, Issue 4, Ver. II (Jul.-Aug. 2016), PP 70-76 www.iosrjournals.org Fast Face Detection Assisted with Skin Color

More information

Face Detection by Means of Skin Detection

Face Detection by Means of Skin Detection Face Detection by Means of Skin Detection Vitoantonio Bevilacqua 1,2, Giuseppe Filograno 1, and Giuseppe Mastronardi 1,2 1 Department of Electrical and Electronics, Polytechnic of Bari, Via Orabona, 4-7125

More information

Face Detection Using Convolutional Neural Networks and Gabor Filters

Face Detection Using Convolutional Neural Networks and Gabor Filters Face Detection Using Convolutional Neural Networks and Gabor Filters Bogdan Kwolek Rzeszów University of Technology W. Pola 2, 35-959 Rzeszów, Poland bkwolek@prz.rzeszow.pl Abstract. This paper proposes

More information

Facial Expression Recognition using Principal Component Analysis with Singular Value Decomposition

Facial Expression Recognition using Principal Component Analysis with Singular Value Decomposition ISSN: 2321-7782 (Online) Volume 1, Issue 6, November 2013 International Journal of Advance Research in Computer Science and Management Studies Research Paper Available online at: www.ijarcsms.com Facial

More information

Color Local Texture Features Based Face Recognition

Color Local Texture Features Based Face Recognition Color Local Texture Features Based Face Recognition Priyanka V. Bankar Department of Electronics and Communication Engineering SKN Sinhgad College of Engineering, Korti, Pandharpur, Maharashtra, India

More information

Robust color segmentation algorithms in illumination variation conditions

Robust color segmentation algorithms in illumination variation conditions 286 CHINESE OPTICS LETTERS / Vol. 8, No. / March 10, 2010 Robust color segmentation algorithms in illumination variation conditions Jinhui Lan ( ) and Kai Shen ( Department of Measurement and Control Technologies,

More information

Text Information Extraction And Analysis From Images Using Digital Image Processing Techniques

Text Information Extraction And Analysis From Images Using Digital Image Processing Techniques Text Information Extraction And Analysis From Images Using Digital Image Processing Techniques Partha Sarathi Giri Department of Electronics and Communication, M.E.M.S, Balasore, Odisha Abstract Text data

More information

Face Recognition Using Long Haar-like Filters

Face Recognition Using Long Haar-like Filters Face Recognition Using Long Haar-like Filters Y. Higashijima 1, S. Takano 1, and K. Niijima 1 1 Department of Informatics, Kyushu University, Japan. Email: {y-higasi, takano, niijima}@i.kyushu-u.ac.jp

More information

Face Objects Detection in still images using Viola-Jones Algorithm through MATLAB TOOLS

Face Objects Detection in still images using Viola-Jones Algorithm through MATLAB TOOLS Face Objects Detection in still images using Viola-Jones Algorithm through MATLAB TOOLS Dr. Mridul Kumar Mathur 1, Priyanka Bhati 2 Asst. Professor (Selection Grade), Dept. of Computer Science, LMCST,

More information

Latest development in image feature representation and extraction

Latest development in image feature representation and extraction International Journal of Advanced Research and Development ISSN: 2455-4030, Impact Factor: RJIF 5.24 www.advancedjournal.com Volume 2; Issue 1; January 2017; Page No. 05-09 Latest development in image

More information

Face Detection Using Color Based Segmentation and Morphological Processing A Case Study

Face Detection Using Color Based Segmentation and Morphological Processing A Case Study Face Detection Using Color Based Segmentation and Morphological Processing A Case Study Dr. Arti Khaparde*, Sowmya Reddy.Y Swetha Ravipudi *Professor of ECE, Bharath Institute of Science and Technology

More information

AN ENHANCED ATTRIBUTE RERANKING DESIGN FOR WEB IMAGE SEARCH

AN ENHANCED ATTRIBUTE RERANKING DESIGN FOR WEB IMAGE SEARCH AN ENHANCED ATTRIBUTE RERANKING DESIGN FOR WEB IMAGE SEARCH Sai Tejaswi Dasari #1 and G K Kishore Babu *2 # Student,Cse, CIET, Lam,Guntur, India * Assistant Professort,Cse, CIET, Lam,Guntur, India Abstract-

More information

Color Space Projection, Feature Fusion and Concurrent Neural Modules for Biometric Image Recognition

Color Space Projection, Feature Fusion and Concurrent Neural Modules for Biometric Image Recognition Proceedings of the 5th WSEAS Int. Conf. on COMPUTATIONAL INTELLIGENCE, MAN-MACHINE SYSTEMS AND CYBERNETICS, Venice, Italy, November 20-22, 2006 286 Color Space Projection, Fusion and Concurrent Neural

More information

Content Based Image Retrieval Using Color Quantizes, EDBTC and LBP Features

Content Based Image Retrieval Using Color Quantizes, EDBTC and LBP Features Content Based Image Retrieval Using Color Quantizes, EDBTC and LBP Features 1 Kum Sharanamma, 2 Krishnapriya Sharma 1,2 SIR MVIT Abstract- To describe the image features the Local binary pattern (LBP)

More information

Image enhancement for face recognition using color segmentation and Edge detection algorithm

Image enhancement for face recognition using color segmentation and Edge detection algorithm Image enhancement for face recognition using color segmentation and Edge detection algorithm 1 Dr. K Perumal and 2 N Saravana Perumal 1 Computer Centre, Madurai Kamaraj University, Madurai-625021, Tamilnadu,

More information

Why MultiLayer Perceptron/Neural Network? Objective: Attributes:

Why MultiLayer Perceptron/Neural Network? Objective: Attributes: Why MultiLayer Perceptron/Neural Network? Neural networks, with their remarkable ability to derive meaning from complicated or imprecise data, can be used to extract patterns and detect trends that are

More information

Consistent Line Clusters for Building Recognition in CBIR

Consistent Line Clusters for Building Recognition in CBIR Consistent Line Clusters for Building Recognition in CBIR Yi Li and Linda G. Shapiro Department of Computer Science and Engineering University of Washington Seattle, WA 98195-250 shapiro,yi @cs.washington.edu

More information

A NOVEL APPROACH TO ACCESS CONTROL BASED ON FACE RECOGNITION

A NOVEL APPROACH TO ACCESS CONTROL BASED ON FACE RECOGNITION A NOVEL APPROACH TO ACCESS CONTROL BASED ON FACE RECOGNITION A. Hadid, M. Heikkilä, T. Ahonen, and M. Pietikäinen Machine Vision Group Infotech Oulu and Department of Electrical and Information Engineering

More information

Image Compression: An Artificial Neural Network Approach

Image Compression: An Artificial Neural Network Approach Image Compression: An Artificial Neural Network Approach Anjana B 1, Mrs Shreeja R 2 1 Department of Computer Science and Engineering, Calicut University, Kuttippuram 2 Department of Computer Science and

More information

Face Recognition for Mobile Devices

Face Recognition for Mobile Devices Face Recognition for Mobile Devices Aditya Pabbaraju (adisrinu@umich.edu), Srujankumar Puchakayala (psrujan@umich.edu) INTRODUCTION Face recognition is an application used for identifying a person from

More information

Image retrieval based on bag of images

Image retrieval based on bag of images University of Wollongong Research Online Faculty of Informatics - Papers (Archive) Faculty of Engineering and Information Sciences 2009 Image retrieval based on bag of images Jun Zhang University of Wollongong

More information

Cellular Learning Automata-Based Color Image Segmentation using Adaptive Chains

Cellular Learning Automata-Based Color Image Segmentation using Adaptive Chains Cellular Learning Automata-Based Color Image Segmentation using Adaptive Chains Ahmad Ali Abin, Mehran Fotouhi, Shohreh Kasaei, Senior Member, IEEE Sharif University of Technology, Tehran, Iran abin@ce.sharif.edu,

More information

Robot localization method based on visual features and their geometric relationship

Robot localization method based on visual features and their geometric relationship , pp.46-50 http://dx.doi.org/10.14257/astl.2015.85.11 Robot localization method based on visual features and their geometric relationship Sangyun Lee 1, Changkyung Eem 2, and Hyunki Hong 3 1 Department

More information

MULTI ORIENTATION PERFORMANCE OF FEATURE EXTRACTION FOR HUMAN HEAD RECOGNITION

MULTI ORIENTATION PERFORMANCE OF FEATURE EXTRACTION FOR HUMAN HEAD RECOGNITION MULTI ORIENTATION PERFORMANCE OF FEATURE EXTRACTION FOR HUMAN HEAD RECOGNITION Panca Mudjirahardjo, Rahmadwati, Nanang Sulistiyanto and R. Arief Setyawan Department of Electrical Engineering, Faculty of

More information

Skin and Face Detection

Skin and Face Detection Skin and Face Detection Linda Shapiro EE/CSE 576 1 What s Coming 1. Review of Bakic flesh detector 2. Fleck and Forsyth flesh detector 3. Details of Rowley face detector 4. Review of the basic AdaBoost

More information

Image Classification Using Wavelet Coefficients in Low-pass Bands

Image Classification Using Wavelet Coefficients in Low-pass Bands Proceedings of International Joint Conference on Neural Networks, Orlando, Florida, USA, August -7, 007 Image Classification Using Wavelet Coefficients in Low-pass Bands Weibao Zou, Member, IEEE, and Yan

More information

Face Recognition Using Vector Quantization Histogram and Support Vector Machine Classifier Rong-sheng LI, Fei-fei LEE *, Yan YAN and Qiu CHEN

Face Recognition Using Vector Quantization Histogram and Support Vector Machine Classifier Rong-sheng LI, Fei-fei LEE *, Yan YAN and Qiu CHEN 2016 International Conference on Artificial Intelligence: Techniques and Applications (AITA 2016) ISBN: 978-1-60595-389-2 Face Recognition Using Vector Quantization Histogram and Support Vector Machine

More information

A Robust Hand Gesture Recognition Using Combined Moment Invariants in Hand Shape

A Robust Hand Gesture Recognition Using Combined Moment Invariants in Hand Shape , pp.89-94 http://dx.doi.org/10.14257/astl.2016.122.17 A Robust Hand Gesture Recognition Using Combined Moment Invariants in Hand Shape Seungmin Leem 1, Hyeonseok Jeong 1, Yonghwan Lee 2, Sungyoung Kim

More information

Skin Detection using Neighborhood Information

Skin Detection using Neighborhood Information Skin Detection using Neighborhood Information Javier Ruiz-del-Solar and Rodrigo Verschae Dept. of Electrical Engineering, Universidad de Chile, Santiago, CHILE E-mail: jruizd@cec.uchile.cl, rverscha@ing.uchile.cl

More information

An Introduction to Pattern Recognition

An Introduction to Pattern Recognition An Introduction to Pattern Recognition Speaker : Wei lun Chao Advisor : Prof. Jian-jiun Ding DISP Lab Graduate Institute of Communication Engineering 1 Abstract Not a new research field Wide range included

More information

CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS

CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS CHAPTER 4 CLASSIFICATION WITH RADIAL BASIS AND PROBABILISTIC NEURAL NETWORKS 4.1 Introduction Optical character recognition is one of

More information

Bayes Risk. Classifiers for Recognition Reading: Chapter 22 (skip 22.3) Discriminative vs Generative Models. Loss functions in classifiers

Bayes Risk. Classifiers for Recognition Reading: Chapter 22 (skip 22.3) Discriminative vs Generative Models. Loss functions in classifiers Classifiers for Recognition Reading: Chapter 22 (skip 22.3) Examine each window of an image Classify object class within each window based on a training set images Example: A Classification Problem Categorize

More information

Detector of Image Orientation Based on Borda-Count

Detector of Image Orientation Based on Borda-Count Detector of Image Orientation Based on Borda-Count Loris Nanni and Alessandra Lumini DEIS, IEIIT CNR, Università di Bologna Viale Risorgimento 2, 40136 Bologna, Italy lnanni@deis.unibo.it Abstract. Accurately

More information

HUMAN COMPUTER INTERFACE BASED ON HAND TRACKING

HUMAN COMPUTER INTERFACE BASED ON HAND TRACKING Proceedings of MUSME 2011, the International Symposium on Multibody Systems and Mechatronics Valencia, Spain, 25-28 October 2011 HUMAN COMPUTER INTERFACE BASED ON HAND TRACKING Pedro Achanccaray, Cristian

More information

IRIS SEGMENTATION OF NON-IDEAL IMAGES

IRIS SEGMENTATION OF NON-IDEAL IMAGES IRIS SEGMENTATION OF NON-IDEAL IMAGES William S. Weld St. Lawrence University Computer Science Department Canton, NY 13617 Xiaojun Qi, Ph.D Utah State University Computer Science Department Logan, UT 84322

More information

A System for Joining and Recognition of Broken Bangla Numerals for Indian Postal Automation

A System for Joining and Recognition of Broken Bangla Numerals for Indian Postal Automation A System for Joining and Recognition of Broken Bangla Numerals for Indian Postal Automation K. Roy, U. Pal and B. B. Chaudhuri CVPR Unit; Indian Statistical Institute, Kolkata-108; India umapada@isical.ac.in

More information

A New Feature Local Binary Patterns (FLBP) Method

A New Feature Local Binary Patterns (FLBP) Method A New Feature Local Binary Patterns (FLBP) Method Jiayu Gu and Chengjun Liu The Department of Computer Science, New Jersey Institute of Technology, Newark, NJ 07102, USA Abstract - This paper presents

More information

Classifiers for Recognition Reading: Chapter 22 (skip 22.3)

Classifiers for Recognition Reading: Chapter 22 (skip 22.3) Classifiers for Recognition Reading: Chapter 22 (skip 22.3) Examine each window of an image Classify object class within each window based on a training set images Slide credits for this chapter: Frank

More information

FACE DETECTION AND RECOGNITION OF DRAWN CHARACTERS HERMAN CHAU

FACE DETECTION AND RECOGNITION OF DRAWN CHARACTERS HERMAN CHAU FACE DETECTION AND RECOGNITION OF DRAWN CHARACTERS HERMAN CHAU 1. Introduction Face detection of human beings has garnered a lot of interest and research in recent years. There are quite a few relatively

More information

Visual object classification by sparse convolutional neural networks

Visual object classification by sparse convolutional neural networks Visual object classification by sparse convolutional neural networks Alexander Gepperth 1 1- Ruhr-Universität Bochum - Institute for Neural Dynamics Universitätsstraße 150, 44801 Bochum - Germany Abstract.

More information

A Quantitative Approach for Textural Image Segmentation with Median Filter

A Quantitative Approach for Textural Image Segmentation with Median Filter International Journal of Advancements in Research & Technology, Volume 2, Issue 4, April-2013 1 179 A Quantitative Approach for Textural Image Segmentation with Median Filter Dr. D. Pugazhenthi 1, Priya

More information

A Novel Image Retrieval Method Using Segmentation and Color Moments

A Novel Image Retrieval Method Using Segmentation and Color Moments A Novel Image Retrieval Method Using Segmentation and Color Moments T.V. Saikrishna 1, Dr.A.Yesubabu 2, Dr.A.Anandarao 3, T.Sudha Rani 4 1 Assoc. Professor, Computer Science Department, QIS College of

More information

Color Content Based Image Classification

Color Content Based Image Classification Color Content Based Image Classification Szabolcs Sergyán Budapest Tech sergyan.szabolcs@nik.bmf.hu Abstract: In content based image retrieval systems the most efficient and simple searches are the color

More information

Masked Face Detection based on Micro-Texture and Frequency Analysis

Masked Face Detection based on Micro-Texture and Frequency Analysis International Journal of Current Engineering and Technology E-ISSN 2277 4106, P-ISSN 2347 5161 2015 INPRESSCO, All Rights Reserved Available at http://inpressco.com/category/ijcet Research Article Masked

More information

Texture Image Segmentation using FCM

Texture Image Segmentation using FCM Proceedings of 2012 4th International Conference on Machine Learning and Computing IPCSIT vol. 25 (2012) (2012) IACSIT Press, Singapore Texture Image Segmentation using FCM Kanchan S. Deshmukh + M.G.M

More information

A Method of Annotation Extraction from Paper Documents Using Alignment Based on Local Arrangements of Feature Points

A Method of Annotation Extraction from Paper Documents Using Alignment Based on Local Arrangements of Feature Points A Method of Annotation Extraction from Paper Documents Using Alignment Based on Local Arrangements of Feature Points Tomohiro Nakai, Koichi Kise, Masakazu Iwamura Graduate School of Engineering, Osaka

More information

Biometric Security System Using Palm print

Biometric Security System Using Palm print ISSN (Online) : 2319-8753 ISSN (Print) : 2347-6710 International Journal of Innovative Research in Science, Engineering and Technology Volume 3, Special Issue 3, March 2014 2014 International Conference

More information

A New Fast Skin Color Detection Technique

A New Fast Skin Color Detection Technique World Academy of Science, Engineering and Technology A New Fast Skin Color Detection Technique Tarek M. Mahmoud Abstract Skin color can provide a useful and robust cue for human-related image analysis,

More information

Real time facial expression recognition from image sequences using Support Vector Machines

Real time facial expression recognition from image sequences using Support Vector Machines Real time facial expression recognition from image sequences using Support Vector Machines I. Kotsia a and I. Pitas a a Aristotle University of Thessaloniki, Department of Informatics, Box 451, 54124 Thessaloniki,

More information

A Novel Technique to Detect Face Skin Regions using YC b C r Color Model

A Novel Technique to Detect Face Skin Regions using YC b C r Color Model A Novel Technique to Detect Face Skin Regions using YC b C r Color Model M.Lakshmipriya 1, K.Krishnaveni 2 1 M.Phil Scholar, Department of Computer Science, S.R.N.M.College, Tamil Nadu, India 2 Associate

More information

Gender Classification Technique Based on Facial Features using Neural Network

Gender Classification Technique Based on Facial Features using Neural Network Gender Classification Technique Based on Facial Features using Neural Network Anushri Jaswante Dr. Asif Ullah Khan Dr. Bhupesh Gour Computer Science & Engineering, Rajiv Gandhi Proudyogiki Vishwavidyalaya,

More information

Face Detection using Hierarchical SVM

Face Detection using Hierarchical SVM Face Detection using Hierarchical SVM ECE 795 Pattern Recognition Christos Kyrkou Fall Semester 2010 1. Introduction Face detection in video is the process of detecting and classifying small images extracted

More information

Human Upper Body Pose Estimation in Static Images

Human Upper Body Pose Estimation in Static Images 1. Research Team Human Upper Body Pose Estimation in Static Images Project Leader: Graduate Students: Prof. Isaac Cohen, Computer Science Mun Wai Lee 2. Statement of Project Goals This goal of this project

More information

Toward Part-based Document Image Decoding

Toward Part-based Document Image Decoding 2012 10th IAPR International Workshop on Document Analysis Systems Toward Part-based Document Image Decoding Wang Song, Seiichi Uchida Kyushu University, Fukuoka, Japan wangsong@human.ait.kyushu-u.ac.jp,

More information

CORRELATION BASED CAR NUMBER PLATE EXTRACTION SYSTEM

CORRELATION BASED CAR NUMBER PLATE EXTRACTION SYSTEM CORRELATION BASED CAR NUMBER PLATE EXTRACTION SYSTEM 1 PHYO THET KHIN, 2 LAI LAI WIN KYI 1,2 Department of Information Technology, Mandalay Technological University The Republic of the Union of Myanmar

More information

Content-based Image Retrieval (CBIR)

Content-based Image Retrieval (CBIR) Content-based Image Retrieval (CBIR) Content-based Image Retrieval (CBIR) Searching a large database for images that match a query: What kinds of databases? What kinds of queries? What constitutes a match?

More information

Hand Gesture Recognition Using PCA and Histogram Projection

Hand Gesture Recognition Using PCA and Histogram Projection Hand Gesture Recognition Using PCA and Histogram Krishnakant C. ule & Anilkumar N. Holambe TPCT s COE,Osmanabad, H, India E-mail : mulekc@gmail.com, anholambe@gmail.com Abstract The recognition problem

More information

Nearest Clustering Algorithm for Satellite Image Classification in Remote Sensing Applications

Nearest Clustering Algorithm for Satellite Image Classification in Remote Sensing Applications Nearest Clustering Algorithm for Satellite Image Classification in Remote Sensing Applications Anil K Goswami 1, Swati Sharma 2, Praveen Kumar 3 1 DRDO, New Delhi, India 2 PDM College of Engineering for

More information

Block Mean Value Based Image Perceptual Hashing for Content Identification

Block Mean Value Based Image Perceptual Hashing for Content Identification Block Mean Value Based Image Perceptual Hashing for Content Identification Abstract. Image perceptual hashing has been proposed to identify or authenticate image contents in a robust way against distortions

More information

Last week. Multi-Frame Structure from Motion: Multi-View Stereo. Unknown camera viewpoints

Last week. Multi-Frame Structure from Motion: Multi-View Stereo. Unknown camera viewpoints Last week Multi-Frame Structure from Motion: Multi-View Stereo Unknown camera viewpoints Last week PCA Today Recognition Today Recognition Recognition problems What is it? Object detection Who is it? Recognizing

More information

Object detection using non-redundant local Binary Patterns

Object detection using non-redundant local Binary Patterns University of Wollongong Research Online Faculty of Informatics - Papers (Archive) Faculty of Engineering and Information Sciences 2010 Object detection using non-redundant local Binary Patterns Duc Thanh

More information

Fabric Defect Detection Based on Computer Vision

Fabric Defect Detection Based on Computer Vision Fabric Defect Detection Based on Computer Vision Jing Sun and Zhiyu Zhou College of Information and Electronics, Zhejiang Sci-Tech University, Hangzhou, China {jings531,zhouzhiyu1993}@163.com Abstract.

More information

TEXTURE CLASSIFICATION METHODS: A REVIEW

TEXTURE CLASSIFICATION METHODS: A REVIEW TEXTURE CLASSIFICATION METHODS: A REVIEW Ms. Sonal B. Bhandare Prof. Dr. S. M. Kamalapur M.E. Student Associate Professor Deparment of Computer Engineering, Deparment of Computer Engineering, K. K. Wagh

More information

Unsupervised Human Members Tracking Based on an Silhouette Detection and Analysis Scheme

Unsupervised Human Members Tracking Based on an Silhouette Detection and Analysis Scheme Unsupervised Human Members Tracking Based on an Silhouette Detection and Analysis Scheme Costas Panagiotakis and Anastasios Doulamis Abstract In this paper, an unsupervised, automatic video human members(human

More information

Locating 1-D Bar Codes in DCT-Domain

Locating 1-D Bar Codes in DCT-Domain Edith Cowan University Research Online ECU Publications Pre. 2011 2006 Locating 1-D Bar Codes in DCT-Domain Alexander Tropf Edith Cowan University Douglas Chai Edith Cowan University 10.1109/ICASSP.2006.1660449

More information

Experimentation on the use of Chromaticity Features, Local Binary Pattern and Discrete Cosine Transform in Colour Texture Analysis

Experimentation on the use of Chromaticity Features, Local Binary Pattern and Discrete Cosine Transform in Colour Texture Analysis Experimentation on the use of Chromaticity Features, Local Binary Pattern and Discrete Cosine Transform in Colour Texture Analysis N.Padmapriya, Ovidiu Ghita, and Paul.F.Whelan Vision Systems Laboratory,

More information

I. INTRODUCTION. Figure-1 Basic block of text analysis

I. INTRODUCTION. Figure-1 Basic block of text analysis ISSN: 2349-7637 (Online) (RHIMRJ) Research Paper Available online at: www.rhimrj.com Detection and Localization of Texts from Natural Scene Images: A Hybrid Approach Priyanka Muchhadiya Post Graduate Fellow,

More information

Pedestrian counting in video sequences using optical flow clustering

Pedestrian counting in video sequences using optical flow clustering Pedestrian counting in video sequences using optical flow clustering SHIZUKA FUJISAWA, GO HASEGAWA, YOSHIAKI TANIGUCHI, HIROTAKA NAKANO Graduate School of Information Science and Technology Osaka University

More information

Tracking facial features using low resolution and low fps cameras under variable light conditions

Tracking facial features using low resolution and low fps cameras under variable light conditions Tracking facial features using low resolution and low fps cameras under variable light conditions Peter Kubíni * Department of Computer Graphics Comenius University Bratislava / Slovakia Abstract We are

More information

Face Detection in Color Images Using Skin Segmentation

Face Detection in Color Images Using Skin Segmentation Face Detection in Color Images Using Skin Segmentation Submitted: 6 th July 2014; accepted: 15 th July 2014 Mohammadreza Hajiarbabi, Arvin Agah DOI: 10.14313/JAMRIS_3-2014/26 Abstract: Face detection which

More information

Classification of Face Images for Gender, Age, Facial Expression, and Identity 1

Classification of Face Images for Gender, Age, Facial Expression, and Identity 1 Proc. Int. Conf. on Artificial Neural Networks (ICANN 05), Warsaw, LNCS 3696, vol. I, pp. 569-574, Springer Verlag 2005 Classification of Face Images for Gender, Age, Facial Expression, and Identity 1

More information

Semi-Supervised PCA-based Face Recognition Using Self-Training

Semi-Supervised PCA-based Face Recognition Using Self-Training Semi-Supervised PCA-based Face Recognition Using Self-Training Fabio Roli and Gian Luca Marcialis Dept. of Electrical and Electronic Engineering, University of Cagliari Piazza d Armi, 09123 Cagliari, Italy

More information

Combining Top-down and Bottom-up Segmentation

Combining Top-down and Bottom-up Segmentation Combining Top-down and Bottom-up Segmentation Authors: Eran Borenstein, Eitan Sharon, Shimon Ullman Presenter: Collin McCarthy Introduction Goal Separate object from background Problems Inaccuracies Top-down

More information

Edge Histogram Descriptor, Geometric Moment and Sobel Edge Detector Combined Features Based Object Recognition and Retrieval System

Edge Histogram Descriptor, Geometric Moment and Sobel Edge Detector Combined Features Based Object Recognition and Retrieval System Edge Histogram Descriptor, Geometric Moment and Sobel Edge Detector Combined Features Based Object Recognition and Retrieval System Neetesh Prajapati M. Tech Scholar VNS college,bhopal Amit Kumar Nandanwar

More information

Training-Free, Generic Object Detection Using Locally Adaptive Regression Kernels

Training-Free, Generic Object Detection Using Locally Adaptive Regression Kernels Training-Free, Generic Object Detection Using Locally Adaptive Regression Kernels IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIENCE, VOL.32, NO.9, SEPTEMBER 2010 Hae Jong Seo, Student Member,

More information

Countermeasure for the Protection of Face Recognition Systems Against Mask Attacks

Countermeasure for the Protection of Face Recognition Systems Against Mask Attacks Countermeasure for the Protection of Face Recognition Systems Against Mask Attacks Neslihan Kose, Jean-Luc Dugelay Multimedia Department EURECOM Sophia-Antipolis, France {neslihan.kose, jean-luc.dugelay}@eurecom.fr

More information

An Efficient Semantic Image Retrieval based on Color and Texture Features and Data Mining Techniques

An Efficient Semantic Image Retrieval based on Color and Texture Features and Data Mining Techniques An Efficient Semantic Image Retrieval based on Color and Texture Features and Data Mining Techniques Doaa M. Alebiary Department of computer Science, Faculty of computers and informatics Benha University

More information

CS6220: DATA MINING TECHNIQUES

CS6220: DATA MINING TECHNIQUES CS6220: DATA MINING TECHNIQUES Image Data: Classification via Neural Networks Instructor: Yizhou Sun yzsun@ccs.neu.edu November 19, 2015 Methods to Learn Classification Clustering Frequent Pattern Mining

More information

A NEW FEATURE BASED IMAGE REGISTRATION ALGORITHM INTRODUCTION

A NEW FEATURE BASED IMAGE REGISTRATION ALGORITHM INTRODUCTION A NEW FEATURE BASED IMAGE REGISTRATION ALGORITHM Karthik Krish Stuart Heinrich Wesley E. Snyder Halil Cakir Siamak Khorram North Carolina State University Raleigh, 27695 kkrish@ncsu.edu sbheinri@ncsu.edu

More information

A METHOD FOR CONTENT-BASED SEARCHING OF 3D MODEL DATABASES

A METHOD FOR CONTENT-BASED SEARCHING OF 3D MODEL DATABASES A METHOD FOR CONTENT-BASED SEARCHING OF 3D MODEL DATABASES Jiale Wang *, Hongming Cai 2 and Yuanjun He * Department of Computer Science & Technology, Shanghai Jiaotong University, China Email: wjl8026@yahoo.com.cn

More information

Face Tracking in Video

Face Tracking in Video Face Tracking in Video Hamidreza Khazaei and Pegah Tootoonchi Afshar Stanford University 350 Serra Mall Stanford, CA 94305, USA I. INTRODUCTION Object tracking is a hot area of research, and has many practical

More information