Hasan Serhan YAVUZ, Hakan ÇEVİKALP, Rifat EDİZKAN

A comprehensive comparison of features and embedding methods for face recognition

Face recognition is an essential issue in modern-day applications since it can be used in many areas for several purposes. Many methods have been proposed for face recognition. It is a difficult task since variations in lighting, instantaneous mimic varieties, posing angles, and scaling differences can drastically change the appearance of the face. To suppress these complications, effective feature extraction and proper alignment of face images gain as much importance as the recognition method choice. In this paper, we provide an extensive comparison of the state-of-theart face recognition methods with the most well-known techniques used in feature representation. In order to test the performances of these various methods, we created a new face database, named the ESOGU face database, which includes frontal images of 100 people taken under different lighting and posing conditions. In addition to our new database, we also present experiments on the well-known AR face database to obtain more general and reliable results. Moreover, we investigate the automatic face detection and automatic normalization of the face images in the databases. Based on this, we discuss the use of such automatic methods for face recognition applications.

PDF

___

[1] Zhao W, Chellappa R, Phillips PJ, Rosenfeld A. Face recognition: a literature survey. ACM Comput Surv 2003;35: 399458.
[2] Jafri R, Arabnia HR. A survey of face recognition techniques. Journal of Information Processing Systems 2009; 5: 4168.
[3] Zhang X, Gao Y. Face recognition across pose: a review. Pattern Recogn 2009; 42: 28762896.
[4] Zhao W, Chellappa R. Image-based face recognition: Issues and methods. In: Javidi B, editor. Image Recognition and Classification: Algorithms, Systems, and Classifications. New York, NY, USA: Marcel Dekker Inc., 2002. pp. 375402.
[5] Hietmeyer R. Biometric identification promises fast and secure processing of airline passengers. International Civil Aviation Organization Journal 2000; 55: 1011.
[6] Yang MH, Kriegman DJ, Ahuja N. Detecting faces in images: a survey. IEEE T Pattern Anal 2002; 24: 3458.
[7] Viola P, Jones MJ. Robust real-time face detection. Int J Comput Vision 2004; 57: 137154.
[8] Levi K, Weiss Y. Learning object detection from a small number of examples. In: International Conference on Computer Vision and Pattern Recognition; 27 June2 July 2004. New York, NY, USA: IEEE. pp. 5360.
[9] Cevikalp H, Triggs B. Efficient object detection using cascades of nearest convex model classifiers. In: International Conference on Computer Vision and Pattern Recognition; 1621 June 2012. New York, NY, USA: IEEE. pp. 31383145.
[10] Zhang BL, Zhang H, Ge SS. Face recognition by applying wavelet subband representation and kernel associative memory. IEEE T Neural Networ 2004; 15: 166177.
[11] Shen L, Bai L. A review on Gabor wavelets for face recognition. Pattern Anal Appl 2006; 9: 273292.
[12] Tao D, Li X, Maybank SJ. General tensor discriminant analysis and Gabor features for gait recognition. IEEE T Pattern Anal 2007; 29: 17001715.
[13] Hafed ZM, Levine MD. Face recognition using the discrete cosine transform. Int J Comput Vision 2001; 43: 167188.
[14] Ekenel HK, Stiefelhagen R. Local appearance based face recognition using discrete cosine transform. In: European Signal Processing Conference; September 2005.
[15] Ahonen T, Hadid A, Pietikainen M. Face description with local binary patterns: application to face recognition. IEEE T Pattern Anal 2006; 28: 20372041.
[16] Tan X, Triggs B. Enhanced local texture feature sets for face recognition under difficult lighting conditions. IEEE T Image Process 2010; 19: 16351650.
[17] Turk M, Pentland AP. Eigenfaces for recognition. J Cognitive Neurosci 1991; 3: 7186.
[18] Cevikalp H, Neamtu M, Wilkes M, Barkana A. Discriminative common vectors for face recognition. IEEE T Pattern Anal 2005; 27: 413.
[19] Belhumeur PN, Hespanha JP, Kriegman DJ. Eigenfaces vs. Fisherfaces: recognition using class specific linear projection. IEEE T Pattern Anal 1997; 19: 711720.
[20] Swets DL, Weng J. Using discriminant eigenfeatures for image retrieval. IEEE T Pattern Anal 1996; 18: 831836.
[21] Cevikalp H, Neamtu M, Wilkes M. Discriminative common vector method with kernels. IEEE T Neural Networ 2006; 17: 15501565.
[22] He X, Yan S, Hu Y, Niyogi P, Zhang HJ. Face recognition using Laplacianfaces. IEEE T Pattern Anal 2005; 27: 328340.
[23] Mika S, Ratsch G, Weston J, Scholkopf B, Muller KR. Fisher discriminant analysis with kernels. In: Proceedings of the 1999 IEEE Signal Processing Society Workshop; 2325 August 1999. New York, NY, USA: IEEE. pp. 4148.
[24] Baudat G, Anouar F. Generalized discriminant analysis using kernel approach. Neural Comput 2000; 12: 23852404.
[25] Kim KI, Jung K, Kim HJ. Face recognition using kernel principal component analysis. IEEE Signal Proc Let 2002; 9: 4042.
[26] Yang MH. Kernel eigenfaces vs. kernel Fisherfaces: face recognition using kernel methods. In: International Conference on Automatic Face and Gesture Recognition; 21 May 2002. New York, NY, USA: IEEE.
[27] Martinez AM. Recognizing imprecisely localized, partially occluded, and expression variant faces from a single sample per class. IEEE T Pattern Anal 2002; 24: 748763.
[28] Marcelja S. Mathematical description of the responses of simple cortical cells. J Opt Soc Am 1980; 70: 12971300.
[29] Daugman JG. Two-dimensional spectral analysis of cortical receptive field profile. Vision Res 1980; 20: 847856.
[30] Lee TS. Image representation using 2D Gabor wavelets. IEEE T Pattern Anal 1996; 18: 113.
[31] Ojala T, Pietikainen M, Harwood D. Performance evaluation of texture measures with classification based on Kullback discrimination of distributions. In: Proceedings of the 12th IAPR International Conference on Pattern Recognition; 913 October 1994. New York, NY, USA: IEEE. pp. 582585.
[32] Gonzalez RC, Woods RE. Digital Image Processing. 2nd ed. Upper Saddle River, NJ, USA: Prentice Hall, 2002.
[33] Chen Y, Jiang S, Abraham A. Face recognition using DCT and hybrid flexible neural tree. In: International Conference on Neural Networks and Brain; 1315 October 2005. New York, NY, USA: IEEE. pp. 14591463.
[34] Scholkopf B, Smola A, Muller K. Kernel principal component analysis. Lect Notes Comput Sc 1997; 1327: 583588.
[35] C¸ evikalp H. Feature extraction techniques in high-dimensional spaces: Linear and nonlinear approaches. PhD, Vanderbilt University, Nashville, TN, USA, 2005.
[36] Yang J, Frangi AF, Jin Z, Yang J. Essence of kernel Fisher discriminant: KPCA plus LDA. Pattern Recogn 2004; 37: 20972100.
[37] Martinez AM, Benavente R. The AR Face Database. CVC Technical Report #24. Barcelona, Spain: Computer Vision Center, 1998.
[38] Tax DMJ, Duin RPW. Support vector data description. Mach Learn 2004; 54: 4566.
[39] Dalal N, Triggs B. Histograms of oriented gradients for human detection. In: International Conference on Computer Vision and Pattern Recognition; 25 June 2005. New York, NY, USA: IEEE. pp. 886893.
[40] Cevikalp H, Yavuz HS, Edizkan R, Gunduz H, Kandemir CM. Comparisons of features for automatic eye and mouth localization. In: 2011 International Symposium on Innovations in Intelligent Systems and Applications; 1518 June 2011. New York, NY, USA: IEEE. pp. 576580.
[41] Everingham M, Sivic J, Zisserman A. Hello! My name is... Buffy Automatic naming of characters in TV video. In: Proceedings of the British Machine Vision Conference; 2006.
[42] Abate AF, Nappi M, Riccio D, Sabatino G. 2D and 3D face recognition: a survey. Pattern Recogn Lett 2007; 28: 18851906.