A study on face recognition by extracting CT-based color values

Authors:
Jae-Gu Song;Sungmo Jung;Yohwan So;Seoksoo Kim
Affiliations:
Department of Multimedia, Hannam University, Daejeon-city, Korea and School of Computing & Information System, Tasmania University, Australia;Department of Multimedia, Hannam University, Daejeon-city, Korea;Department of Multimedia, Hannam University, Daejeon-city, Korea;Department of Multimedia, Hannam University, Daejeon-city, Korea
Venue:
CSECS '10 Proceedings of the 9th WSEAS international conference on Circuits, systems, electronics, control & signal processing
Year:
2010

Citing 5
Cited 0

Automatic recognition and analysis of human faces and facial expressions: a survey

Pattern Recognition
Face Detection in Color Images

IEEE Transactions on Pattern Analysis and Machine Intelligence
Face detection and tracking in video sequences using the modifiedcensus transformation

Image and Vision Computing
Illumination compensation and normalization for robust face recognition using discrete cosine transform in logarithm domain

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Face segmentation using skin-color map in videophone applications

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

This is basic research for extracting face by analyzing color values, and the purpose of this study is to secure expression data with more clear color values extracted by the light sources. For this purpose, how to apply CT algorithm that processes color values efficiently by the light to the existing color value analysis algorithm (RGB. YcbCr, HIS), was suggested. While designing the order of color-based facial expression recognition tracking in 6 steps and applying this to the program, this study assured the efficiency of the detection area. The result shows that the facial region becomes relatively distinct when illumination is focused exclusively on the facial region, than under the global illumination condition.