人臉偵測研究主題在近十年一直有持續的進步，然而隨著攜帶式電子產品普及化，高效率且低複雜度的人臉偵測硬體實現需求變得越來越迫切。在人臉偵測演算法中，串聯級分類器(cascade of classifiers)已被證實是兼具速度和準確率之物件偵測演算法，然而卻少有文獻能將串聯級分類器加以實現成高效率的超大型積體電路(very-large-scale integration)設計。為了改善現存人臉偵測硬體電路之成本效益不彰問題，本篇論文首次整合顏色特徵和串聯級分類器，提出一基於掃描線之人臉偵測硬體電路架構。藉由結合膚色檢測機制，可以大幅減少 (i) 整張影像的搜尋計算時間 (ii)人臉分類所需之特徵數目。另外我們對輸入影像訊號採取動態取樣(dynamic down-sampling)進而克服人臉在不同影像中尺度變換之問題。與傳統硬體實現結果相比，我們所提出的硬體架構在處理160×120的彩色影像中，可以節省96%的記憶體存取時間並只需7%的分類特徵數目。實驗結果顯示，我們所提出的低硬體成本之電路架構可以實現快速且準確的人臉偵測功能。

Over the past decade, many advances have been made in the area of face detection. With the increasing usage of portable consumer devices, the low cost and high performance requirements are becoming more critical to face detection. Cascade of classifiers has been approved as one of the most accurate and high speed object detection methods. However, there are few researches which attempt to develop an effective VLSI architecture design of cascade of classifiers. In this thesis, a scanline based VLSI design is proposed to implement a cost-effective face detection system. This work presents a hybrid color feature and cascade of classifiers face detection algorithm. Using the skin color to recognize the region for the following face classification can dramatically reduce (i) the search range of the whole image (ii) the feature number for classification. We proposed a dynamic down-sampling framework which can merge the face segment between scanlines and overcome the scale variation problem between faces. The proposed work successfully save 96% frame memory access time and use only 7% of the classified features in processing 160×120 color images. Experimental result shows that the proposed scheme can achieve not only high processing speed and detection accuracy but also low hardware cost.

Reference
[1] P. Viola and M. Jones, “Robust real-time object detection,” Computer Vision, vol. 57, no. 2, pp. 137-154, July 2001.
[2] M. H. Yang, D. J. Kriegman, and N. Ahuja, “Detecting faces in images: a survey,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 1, pp.34-58, Jan. 2002.
[3] E. Hjelmås and B. K. Low, “Face detection: a survey,” Computer Vision and Image Understanding, vol. 83, no. 3, pp.236-274, Sept. 2001.
[4] D. Chetverikov and A. Lerch, “Multiresolution face detection,” Computer Vision and Image Understanding, vol. 23, no. 5, pp.469-477, May. 2005.
[5] H. P. Graf, T. Chen, E.Petajan, and E. Cosatto, “Locating faces and facial parts,” in Proc. IEEE Int. Conf. Automatic face and gesture recognition, pp.41-49, 1995.
[6] T. K. Leung, M. C. Burl, and P. Perona, “Finding faces in cluttered scenes using random labeled graph matching,” in Proc. IEEE Int. Conf. Computer Vision, pp. 637-644, 1995.
[7] R. L. Hsu, A. M. Mohamed, and A. K. Jain, “Face detection in color images,” IEEE Tran. Pattern Analysis and Machine Intelligence, vol. 24, no.5, pp. 696-706, May 2002.
[8] Q. B. Sun, W. M. Huang, and J. K. Wu, “Face detection based on color and local symmetry information,” in Proc. IEEE Int. Conf. Automatic face and gesture recognition, pp. 130-135, 1998.
[9] N. Herodotou, K. N. Plataniotis, and A. N. Venetsanopoulos, “Automatic location and tracking of the facial region in color video sequence,” Signal Processing: Image Communication, vol. 14, no. 5, pp. 359-388, Mar. 1999.
[10] H. Wang and S. F. Chang, “A highly efficient system for automatic face region detection in MPEG video,” IEEE Tran. Circuit and System for Video Technology, vol. 7, no. 4, pp. 615-628, Aug. 1997.
[11] J. C. Terrillon, M. N. Shirazi, N. Fukamachi, and S.Akamatsu, “Comparative performance of different skin chrominance models and chrominance spaces for the automatic detection of human faces in color image,” in Proc. IEEE Int. Conf. Automatic face and gesture recognition, pp. 54-61, 2000.
[12] E. Saber and A. M. Tekalp, “Frontal-view face detection and facial feature extraction using color, shape and symmetry based cost functions,” Pattern Recognition Letters, vol. 19, no. 8, pp. 669-680, June 1998.
[13] K. Sobottka and I. Pitas, “Face localization and feature extraction based on shape and color information,” in Proc. IEEE Int. Conf. Image Processing, pp. 483-486, 1996.
[14] M. H. Yang and N. Ahuja, “Detecting human faces in color image,” in Proc. IEEE Int. Conf. Image processing, pp.127-130, 1998.
[15] I. Craw, H. Ellis, and J. Lishman, “Automatic extraction of face features,” Pattern recognition Letters, vol. 5, no. 2, pp. 183-187, Feb. 1987.
[16] V. Govindaraju, “Locating human faces in photographs,” Computer Vision, vol. 19, no. 2, pp. 129-146, Aug. 1996.
[17] J. Wang and H. Yang, “Face detection based on template matching and 2DPCA algorithm,” in Proc. IEEE Int. Conf. Congress on Image and Signal Processing, pp. 575-579, 2008.
[18] A. Lanitis, C. J. Taylor, and T. F. Cootes, “A automatic face identification system using flexible appearance models,” Image and Vision Computing, vol. 13, no. 5, pp. 393-401, June 1995.
[19] J.Miao, B. Yin, K. Wang, L. Shen, and X. Chen, “A hierarchical multiscale and mulatiangle system for human face detection in a complex background using gravity-center template,” Pattern Recognition, vol. 32, no.7, pp.1237-1248, July 1999.
[20] B. Moghaddam and A. Pentland, “Probabilistic visual learning for object recognition,” IEEE Tran. Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 696-710, July 1997.
[21] M. Kirby and L. Sirovich, “Application of the Karhunen-loeve procedure for the characterization on human faces,” IEEE Tran. Pattern Analysis and Machine Intelligence, vol.12, no. 1, pp. 103-108, Jan. 1990.
[22] K. K. Sung and T. Poggio, “Example-based learning for view-based human face detection,” IEEE Tran. Pattern Analysis and Machine Intelligence, vol. 20, no. 1, pp.39-51, Jan. 1998.
[23] H. Rowley, S. Baluja, and T. Kanade, “Neural network-based face detection,” IEEE Tran. Pattern Analysis and Machine Intelligence, vol. 20, no. 1, pp. 23-38, Jan. 1998.
[24] H. Schneiderman and T. Kanade, “Probabilistic modeling of local appearance and spatial relationship for object recognition,” in Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, pp. 45-51, 1998.
[25] E. Osuna, R. Freund, and F. Girosi, “Training support vector machines: an application to face detection,” in Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, pp. 130-136, 1997.
[26] F. Samaria and S. Young, “HMM based architecture for face identification,” Image and Vision Computing, vol. 12, no.8, pp. 537-543, Oct. 1994.
[27] Y. Freund and R. E. Schapire, “Experiments with a new boosting algorithm,” in Proc. IEEE Int. Conf. Machine Learning, pp.148-156, 1996.
[28] Y. Freund and R. E. Schapire, “A short introduction to boosting,” Japan Tran. Artificial Intelligence, vol. 14, no. 5, pp.771-780, Sep. 1999.
[29] X. Bing, Y. Wei, and C. Charoensak, “Face contour tracking in video,” in Proc. IEEE Int. Conf. Image Processing, pp. 24-27, 2004.
[30] Y. Wei, X. Bing, and C. Charoensak, “FPGA implementation of AdaBoost algorithm for detection of face biometric,” in Proc. IEEE Int. Conf. Biomedical Circuit and Systems, pp.17-20, 2004.
[31] H. C. Lai, M. Saccides, and T. Chen, “Proposed FPGA hardware architecture for high frame rate (>100 fps ) face detection using feature cascade classifiers,” in Proc. IEEE Int. Conf. Biometrics: Theory, Application, and Systems, pp. 1-6, 2007.
[32] M. Hiromoto, H. Sugano, and R. Miyamoto, “Partially parallel architecture for AdaBoost-based detection with Haar-like features,” IEEE Tran. Circuits and Systems for Video Technology, vol. 19, no. 1, pp. 41-52, Jan. 2009.
[33] C. Kyrkou and T. Theocharides, “A flexible parallel hardware architecture for AdaBoost-based real-time object detection,” IEEE Tran. Very Large Scale Integration System, vol. 19, no. 6, pp.1034-1047, June 2001.
[34] C. R. Chen, W. S. Wong, and C. T. Chiu, ‘A 0.64 mm2 real-time cascade face detection design based on reduces two-field extraction,” IEEE Tran. Very Large Scale Integration, vol. 19, no. 11, pp.1937-1948, Nov. 2001.
[35] Y. Hanai, Y. Hori, J. Nishimura, and T. Kuroda, “A versatile recognition processor employing Haar-like feature and cascaded classifier,” in Proc. IEEE Int. Conf. Solid-State Circuit, pp.148-150, 2009.
[36] P.Vadakkepat, P. Lim, L. C. Silva, L. Jing, and L. L. Ling, “Multimodal approach to human-face detection and tracking,” IEEE Tran. Industry Electronics, vol. 55, no. 3, pp. 1385-1393, Mar. 2008.
[37] C. F. Juang, S. H. Chiu, and S. J. Shiu, “Fuzzy system learned through fuzzy clustering and support vector machine for human skin color segmentation,” IEEE Tran. System and Human, vol. 37, no. 6, pp.1077-1087, Nov. 2007.
[38] S. L. Phung, A. Bouzerdoum, and D. Chai, “Skin segmentation using color pixel classification: analysis and comparison,” IEEE Tran. Pattern Analysis and Machine Learning, vol. 27, no. 1, pp. 148-154, Jan. 2005.
[39] J. A. Tomaschitz and J. Facon, “Skin detection applied to multi-racial images,” in Proc. IEEE Int. Conf. System, Signal, and Image Processing, pp.1-3, 2009.
[40] Y. D. Wang and H. He, “Multi-race face detection based on skin color and eyes,” in Proc. IEEE Int. Conf. Machine Learning and Cybernetics, pp. 659-663, 2010.
[41] C. H. Lee, J. S. Kim, and K. H. Park, "Automatic human face location in a complex background using motion and color information," Pattern Recognition, vol. 29, no. 11, pp. 1877-1889, Nov. 1996.
[42] R. Frischholz, “Bao face database at the face detection homepage,” 2008. [Online]. Available: http://www.facedetection.com/downloads/BaoDataBase.zip
[43] J. Serra, Image analysis and mathematical morphology: Orlando: Academic Press, 1983.
[44] MIT, Cambridge, “MIT center for biological and computation learning,” 2000. [Online]. Available: http://cbcl.mit.edu/cbcl/soft-ware-datasets/FaceData2.html
[45] K. Imagawa, K. Iwasa, T. Kataoka, T. Nishi, and H. Matsuo, “Real-time face detection with MPEG4 codec LSI for a mobile multimedia terminal,” in Proc. IEEE Int. Conf. Consumer Electronic, pp.16–17, 2003.
[46] Y. Hori, Y. Hanai, and T. Kuroda, “A 0.79-mm2-mW real-time face detection core,” in Proc. IP-SOC Conf. Electronic Sysem and Exhibition, pp. 790–797, 2007.
[47] K. Korekado, T. Morie, O. Nomura, T. Nakano, M. Matsugu, and A. Iwata, “An image filtering processor for face/object recognition using merged/mixed analog digital architecture,” in Proc. IEEE Int. Symp. VLSI Circuits Digest of Technical Papers, pp. 220–223, 2005.
[48] T. Theocharides, G. Link, N. Vijaykrishnan, M. J. Irwin, and W. Wolf, “Embedded hardware face detection,” in Proc. IEEE Int. Conf. VLSI Design, pp. 133–138, 2004.