隨著科技的進步，生物辨識在我們的日常生活中已被廣泛的應用，尤其是以人臉辨識為智慧身份驗證中最受青睞的方法。線性迴歸分類法為人臉辨識演算法中一知名且有效的方法，並且有許多改良式線性迴歸分類法的版本被提出。然而，部分遮蔽的人臉影像對於大部分的人臉辨識演算法將造成巨大辨識品質下降問題。本論文應用模塊線性迴歸分類法，並將彩色直方圖推得模塊加權以弱化汙染的模塊。因此，我們提出之彩色直方圖加權模塊線性迴歸分類法成功提高了部分遮蔽人臉辨識的表現。為了評估提出方法的效能，我們使用兩個人臉資料庫並合成具有部分人臉遮蔽的影像的來驗證並與其他知名的人臉辨識演算法作比較。實驗結果顯示，彩色直方圖加權模塊線性迴歸分類法在辨識部分人臉遮蔽的表現優於其他先進的演算法。此外，在實務應用上，我們於Android平台架構實現所提之人臉辨識演算法，於真實世界環境來測試其辨識能力。

With the advance of technologies, biometrics recognition has been widely applied in our daily lives. Especially, face recognition is the most popular approach for intelligent identification. Linear regression classification (LRC) is a famous and powerful approach for face recognition. There are many modified LRC approaches with some improvements have been proposed. Nevertheless, face images with partially-occluded areas degrade the performance a lot for most face recognition algorithms. In this paper, the module LRC by referring color histogram with module weights is proposed to weaken the contaminated modules. Thus, the weighted module linear regression classification based on color histogram (WMLRC-CH) successfully overcomes the partially-occluded problem. In order to evaluate the effectiveness of the proposed method, two face databases with synthesized occlusions are used to validate face recognition performances in comparisons to the well-known methods. Experimental results show that the proposed method almost achieves the best recognition performance to recognize partially-occluded faces. Moreover, for practical applications, we realize the proposed WMLRC-CH method on Android platform to test face recognition capability in real-world environments.

[1] J. Lu, V. E. Liong, G. Wang, and P. Moulin, “Joint Feature Learning for Face Recognition,” IEEE Trans. on Information Forensics and Security, vol. 10, no. 7, pp. 1371-1383, July 2015.
[2] D. Mery and K. Bowyer, “Face Recognition via Adaptive Sparse Representations of Random Patches,” Proc. of IEEE International Workshop on Information Forensics and Security, pp. 13-18, 2014.
[3] J. Lu, V. E. Liong, X. Zhou, and J. Zhou, “Learning Compact Binary Face Descriptor for Face Recognition,” IEEE Trans. on Pattern Analsis. and Machine Intelligence, vol. 37, no. 10, pp. 2041-2056, 2015.
[4] X. Peng, L. Zhang, X. Yi, and K. K. Tan, “Learning Locality-Constrained Collaborative Representation for Robust Face Recognition,” Pattern Recognition, vol. 47, no. 9, pp. 2794-2806, 2014.
[5] Z. Jie, J. Qiang, and N. George, “A Comparative Study of Local Matching Approach for Face Recognition,” IEEE Trans. on Image Proc., vol. 16, no. 10, pp. 2617–2628, 2007.
[6] A. M. Martinez and A. C. Kak, “PCA versus LDA,” IEEE Trans. on Pattern Anal. and Mach. Intell., vol. 23, no. 2, pp. 228-233, 2001.
[7] R. Gottumukkal and V. K. Asari. “An improved face recognition technique based on modular PCA approach”. Pattern Recognition Letters, vol. 25, no. 4, pp 429-436, 2004.
[8] J. Wright, A. Y. Yang and A. Ganesh. “Robust face recognition via sparse representation, ”. IEEE transactions on pattern analysis and machine intelligence, vol. 31 no .2, pp 210-227, 2009.
[9] I. Naseem, R. Togneri, M. Bennamoun, “Linear Regression for Face Recognition,” IEEE Trans. on Pattern Anal. and Mach. Intell., vol. 32, no. 11, pp. 2106-2112, 2010.
[10] F. Dornaika, Y. EL. Traboulsi and A. Assoum. “Adaptive two phase sparse representation classifier for face recognition,” International Conference on Advanced Concepts for Intelligent Vision Systems. Springer International Publishing. pp. 182-191, 2013.
[11] L. Zhang, M. Yang, X. Feng, Y. Ma and D. Zhang, Collaborative representation based classification for face recognition. arXiv preprint arXiv:1204.2358, 2012.
[12] S. M. Huang and J. F. Yang. “Improved principal component regression for face recognition under illumination variations”, IEEE signal processing letters, vol. 19, no .4, pp.179-182, 2012.
[13] S. M. Huang and J. F. Yang, “Unitary Regression Classification with Total Minimum Projection Error for Face Recognition,” IEEE Signal Proc. Let., vol. 20, no. 5, pp. 443-446, 2013.
[14] Y. T. Chou and J. F. Kevin Yang “Identity recognition based on generalized linear regression classification for multi-component images, ” IET Computer Vision, 10.1 pp.18 – 27 ,2016
[15] Y. T. Chou, S. M. Huang and J. F. Yang “Class-specific kernel linear regression classification for face recognition under low-resolution and illumination variation conditions ,” EURASIP Journal on Advances in Signal Processing, 2016
[16] Y. T. Chou and J. F. Yang “Partially-occluded face recognition using weighted module linear regression classification, ” IEEE International Symposium on Circuits and Systems (ISCAS),pp. 578-581, 2016
[17] G. Liu, Y. Yan and H. Wang “Robust Modular Linear Regression Based Classification for Face Recognition with Occlusion” ICIG '13 Proceedings of the 2013 Seventh International Conference on Image and Graphics ,pp.509-514, 2013
[18] P .J. Huber “Robust statistics,” Springer Berlin Heidelberg ,pp.1248-1251, 2011.
[19] X. He and P. Niyogi “Locality preserving projections,” Advances in neural information processing systems, p. 153-160, 2004.
[20] X. He, D Cai, S Yan and H. J. Zhang “Neighborhood preserving embedding,” Computer Vision, 2005. ICCV 2005. Tenth IEEE International Conference on. IEEE, p. 1208-1213, 2005.
[21] T. Ahonen, H. Abdenour, and M. Pietikäinen. “Face recognition with local binary patterns”. Computer vision-eccv, pp. 469-481, 2004.