Face Recognition Using ATP Feature Set under Difficult Lighting Conditions
- 1.2k Downloads
Recognizing face image under difficult lighting conditions is a challenging task in the Face Recognition system. Existing feature extraction using the Local Binary Pattern (LBP) fails to detect the eye position and is sensitive to noise in uniform image regions. These issues have been considered in our proposed Advanced Ternary Pattern (ATP) Feature set. The detection of eye position is based on the construction of eye model and localization of eye coordinates. Further, normalization technique attempts to solve the low sensitivity to noise in uniform image regions such as cheeks and forehead under difficult lighting. ATP feature set uses the Efficient Feature Orientation (EFO) method for effectiveness of inaccurate face normalization. The proposed scheme improves the False Acceptance Rate (FAR) up to 90% for the less dark images and about 78% in the fully dark images, thus improvising the previous results. Experimental results show that the proposed technique is promising in achieving the illumination invariant for facial images.
KeywordsFeature extraction illumination advanced ternary pattern noise removal image classification
Unable to display preview. Download preview PDF.
- 2.Liao, W.-H.: Region Description Using Extended Local Ternary Patterns. In: International Conference on Pattern Recognition, Taiwan, pp. 1003–1006 (2010)Google Scholar
- 3.Akhlouf, M.A., Bendada, A.: Locally adaptive texture features for multispectral face recognition. In: Computer Vision and Systems Laboratory, Laval University, pp. 3308–3314 (2010)Google Scholar
- 5.Bendada, A., Akhloufi, M.A.: Multispectral Face Recognition in Texture Space. In: Canadian Conference Computer and Robot Vision, pp. 101–106 (2010)Google Scholar
- 6.Zhao, L., Chan, P.P.K., Ng, W.W.Y., Yeung, D.l.S.: A Novel Gradient Synthesis-based Illumination Formalization Method For Face Verification Under Varying Lighting Conditions. In: Proceedings of the Ninth International Conference on Machine Learning and Cybernetics, Qingdao, pp. 669–674 (2010)Google Scholar
- 7.Tan, X., Triggs, B.: Enhanced Local Texture Feature Sets for Face Recognition under Difficult Lighting Conditions. IEEE Transactions on Image Processing, 1635–1650 (2010)Google Scholar
- 8.Cai, L.-b., Ying, Z.-l.: Face Recognition with Locally Linear Embedding on Local Binary Patterns. In: 1st International Conference on Information Science and Engineering (ICISE 2009), pp. 1246–1249 (2009)Google Scholar
- 9.Pang, Y., Yuan, Y., Li, X.: Gabor-Based Region Covariance Matrices for Face Recognition. IEEE Transactions on Circuits and Systems for Video Technology 18(7) (2008)Google Scholar
- 10.Kim, S., Chung, S.-T., Jung, S., Oh, D., Kim, J., Cho, S.: Multi-Scale Gabor Feature Based Eye Localization. In: World Academy of Science, Engineering and Technology (2007)Google Scholar
- 11.Lee, K.-C., Ho, J., Kriegman, D.J.: Acquiring Linear Subspaces for Face Recognition under Variable Lighting. IEEE Transactions on Pattern Analysis And Machine Intelligence 27(5) (2005)Google Scholar
- 12.Belhumeur, P.N., Hespanha, J.P., Kriegman, D.J.: Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection. IEEE Transactions on Pattern Analysis and Machine Intelligence 19(7) (1997)Google Scholar
- 13.Adini, Y., Moses, Y., Ullman, S.: Face Recognition: The Problem of Compensating for Changes in Illumination Direction. IEEE Transactions on Pattern Analysis and Machine Intelligence 19(7) (1997)Google Scholar