ICTACT Journal on Image and Video Processing

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Detection of Human Faces in Color Images and Performance Analysis of Different Skin Chrominance Spaces and Skin Chrominance Models


Affiliations
1 Health Science Department, Leidos (Legacy Lockheed Martin Information Systems and Global Solutions), United States
     

   Subscribe/Renew Journal


The overall objective of the project is to build a system that detects human faces in a given color image and to compare performance of different chrominance models and chrominance spaces. For face detection, approach is to detect skin color and segment given image into skin and non-skin regions. In a skin segmented image, the region of skin whose height to width ratio falls under well-known Golden ratio = (1 +√5)) / 2 ± some tolerance, the probability of that region to be considered as face is very high. In this implementation, evaluation of this assumption has been performed. To be able to find out what skin looks like, system has to generate statistical model of skin color. A training set of 54 skin samples (37,020 pixels) and 28 background samples (23,229 pixels) used to generate such models. This paper discusses two types of statistical models - Single Gaussian Model and Gaussian Mixture Model. Performance of both these model has been compared and the best fit model for given dataset has been used. Training dataset was collected using University of Stirling’s face database and several images from internet is used. Since dataset comes from different sources, it might result in some unknowns in dataset. One way to eliminate such unknowns is to separate color information from intensity or try to reduce effect of illumination by normalizing color information. To reduce effect of unknowns, this paper uses normalized-rgb (Red, Green, Blue) (illumination is normalized across three color, so effect is reduced), HSV (Hue, Saturation, Value) space (intensity and chromaticity part are independent) and CIE-xyz (Commission Internationale de l'Elcairage) (Machine independent) color spaces. Chrominance models in all three color spaces have been generated and compared to find which color space best suits the selected dataset.

Keywords

Bayes Rules, Face Detection, Golden Ratio, Normalized RGB.
Subscription Login to verify subscription
User
Notifications
Font Size

  • Erik Hjelmas and Boon Kee Low, “Face Detection: A Survey”, Computer Vision and Image Understanding, Vol. 83, No. 3, pp. 236-274, 2001.

  • Stan Z. Li and Anil K. Jain, “Handbook of Face Recognition”, 2nd Edition, Springer, 2011.

  • V. Govindaraju, “Locating Human Faces in Photographs”, International Journal of Computer Vision, Vol. 19, No. 2, pp. 129-146, 1996.

  • K. Sandeep and A.N. Rajagopalan. “Human Face Detection in Cluttered Color Images using Skin Color and Edge Information”, Available at: https://www.cse.iitb.ac.in/~sharat/icvgip.org/icvgip2002/proceedings/166.pdf.

  • Tiberio S. Caetano, Silvia D. Olabarriaga and Dante A.C. Barone, “Performance Evaluation of Single and Multiple-Gaussian Models for Skin Color Modelling”, Proceedings of 15th Brazilian Symposium on Computer Graphics and Image Processing, pp. 112-117, 2002.

  • Jean-Christophe Terrillon, Mahdad N. Shirazi, Hideo Fukamachi and Shigeru Akamatsu. “Comparative Performance of Different Skin Chrominance Models and Chrominance Spaces for the Automatic Detection of Human Faces in Color Images”, Proceedings of 4th IEEE International Conference on Automatic Face and Gesture Recognition, pp. 105-109, 2000.

  • Adrian Ford and Alan Roberts, “Color Space Conversions”, Available at: https://poynton.ca/PDFs/coloureq.pdf

  • J.C. Terrillon, Y. Niwa and K. Yamamoto, “On the Selection of an Efficient Chrominance Space for Skin Color-based Image Segmentation with an Application to Face Detection”, Proceedings of International Conference on Quality Control by Artificial Vision, Vol. 1, pp. 354-361, 2001.

  • Alberto Albiol, Luis Torres and Edward J. Delp, “An Unsupervised Color Image Segmentation Algorithm for Face Detection Applications”, Proceedings of International Conference on Image Processing, pp. 23-27, 2001.

  • Sanjay Kr. Singh, D. S. Chauhan, Mayank Vatsa and Richa Singh; “A Robust Skin Color based Face Detection Algorithm”; Tamkang Journal of Science and Engineering, Vol. 6, No. 4, pp. 227-234, 2003.

  • Sangoh Jeong, “Histogram-Based Color Image Retrieval”, Available at: https://ece.uwaterloo.ca/~nnikvand/Coderep/ColorHist/Histogram-Based%20Color%20Image%20Retrieval.pdf

  • Michael Walter, “Extreme Value Theory for Visual Recognition”, Available at: http://cs.uccs.edu/~jkalita/work/reu/REU2014/FinalPapers/Moore.pdf

  • HSV Color Space, Available at: https://en.wikipedia.org/wiki/HSL_and_HSV.

  • CIE1931 Color Space, Available at: http://en.wikipedia.org/wiki/CIE_1931_color_space.

  • Psychological Image Collection at Stirling, Available at: http://pics.psych.stir.ac.uk/cgi-bin/PICS/New/pics.cgi?filename=shop-wuwwEh&shop=clear

  • JPEG Files, Available at: http://www.csit.fsu.edu/~burkardt/data/jpg/jpg.html

  • JPEG Format, Available at: http://en.wikipedia.org/wiki/JPEG

  • Ruye Wang, “The Color Space”, Available at: http://fourier.eng.hmc.edu/e180/handouts/color1/node27.html, Accessed on 2002.

  • Pascal Getreuer, “Color Space”, Available at: http://www.mathworks.com/matlabcentral/files/7744/content/colorspace/doc/colorspace.html.

  • Color Conversion Algorithms, Available at: http://www.cs.rit.edu/~ncs/color/t_convert.html

  • Ian. T. Nabney. “Netlab Algorithms for Pattern Recognition”, 1st Edition, Springer, 2002.

  • Kevin Murphy, “A Brief Introduction to Bayes Rule”, Available at: http://www.cs.ubc.ca/~murphyk/Bayes/bayesrule.html.

  • Alex Pentland and Tanzeem Choudhury, “Personalizing Smart Environments: Face Recognition for Human Interaction”, Available at: http://vismod.media.mit.edu/tech-reports/TR-516/ieee_computer.html.

  • Yi Chan, Richard Harvey and Dan Smith, “Building Systems to Block Pornography”, Available at: http://www.bcs.org/upload/pdf/ewic_im99_paper8.pdf.

  • Paul Bourke, “RGB color space”, Available at: http://local.wasp.uwa.edu.au/~pbourke/color/colorspace/, Accessed on 1995.

  • Demir Gokalp, “Learning Skin pixels in Color Images using Gaussian Mixture”, Available at: http://www.cs.bilkent.edu.tr/~guvenir/courses/CS550/Workshop/Demir_Gokalp.pdf.

  • Ming-Hsuan Yang and Narendra Ahuja, “Gaussian Mixture Model for Human Skin Color and its Applications in Image and Video Database”, Available at: https://pdfs.semanticscholar.org/ee04/945d25f21fc1a7cc457610a6aff0dee34420.pdf.

  • Kardi Technomo, “Numerical Example of K-Means”, Available at: http://people.revoledu.com/kardi/tutorial/kMean/NumericalExample.htm.


Abstract Views: 361

PDF Views: 6




  • Detection of Human Faces in Color Images and Performance Analysis of Different Skin Chrominance Spaces and Skin Chrominance Models

Abstract Views: 361  |  PDF Views: 6

Authors

Poorvi Bhatt
Health Science Department, Leidos (Legacy Lockheed Martin Information Systems and Global Solutions), United States

Abstract


The overall objective of the project is to build a system that detects human faces in a given color image and to compare performance of different chrominance models and chrominance spaces. For face detection, approach is to detect skin color and segment given image into skin and non-skin regions. In a skin segmented image, the region of skin whose height to width ratio falls under well-known Golden ratio = (1 +√5)) / 2 ± some tolerance, the probability of that region to be considered as face is very high. In this implementation, evaluation of this assumption has been performed. To be able to find out what skin looks like, system has to generate statistical model of skin color. A training set of 54 skin samples (37,020 pixels) and 28 background samples (23,229 pixels) used to generate such models. This paper discusses two types of statistical models - Single Gaussian Model and Gaussian Mixture Model. Performance of both these model has been compared and the best fit model for given dataset has been used. Training dataset was collected using University of Stirling’s face database and several images from internet is used. Since dataset comes from different sources, it might result in some unknowns in dataset. One way to eliminate such unknowns is to separate color information from intensity or try to reduce effect of illumination by normalizing color information. To reduce effect of unknowns, this paper uses normalized-rgb (Red, Green, Blue) (illumination is normalized across three color, so effect is reduced), HSV (Hue, Saturation, Value) space (intensity and chromaticity part are independent) and CIE-xyz (Commission Internationale de l'Elcairage) (Machine independent) color spaces. Chrominance models in all three color spaces have been generated and compared to find which color space best suits the selected dataset.

Keywords


Bayes Rules, Face Detection, Golden Ratio, Normalized RGB.

References