人臉偵測技術是影像處理應用中一個相當重要的話題。它已經廣泛地被使用於許多的應用，比如：人臉追蹤系統、自動門禁系統、銀行與海關監控系統等等。本論文提出一個改良型人臉偵測電路架構，我們改良傳統的人臉偵測演算法，採用縮小影像技術取代傳統放大矩形特徵大小的方式，達到放大子視窗大小的功能與降低暫存器使用的目的，同時利用固定點數運算取代浮點數運算，達到降低bit數的使用並增加運算速度。最後，我們應用層級交換技術，來大量節省硬體成本的消耗。實驗結果顯示，我們的方法在影像的偵測品質上跟OPENCV結果相當接近，而且我們提出的硬體架構，可以讓我們的電路在處理影像時更快且更有效率。根據合成模擬的結果，在 TSMC 0.18μm 製程下，我們的電路可以到達 40MHz的運作速度，在輸入影像大小640×480的情況下，人臉偵測電路的處理速度可達每秒40張影像。

Face detection is a very important issue in the field of image processing. It has been used in many applications such as face tracking system, auto door-dog system, bank and custom surveillance system and so on. In this thesis, we propose a modified cascaded face detection circuit. Instead of scaling-up feature size, we use scaling-down image technique to get the effect of scaling-up sub-window and to avoid a lot of unnecessary registers. Besides, we use fixed-point operation to replace floating-point operation to reduce the hardware cost and achieve higher working speed. Finally, we adopt the stage switch technique to achieve lower hardware cost. Experiment results show that the performance of our design is almost the same as OPENCV. Furthermore, the proposed hardware architecture can implement face detection quickly and efficiently. According to our simulation, the design can operate at 40 MHz properly with the TSMC 0.18μm technology and process a video resolution of 640×480 at 40 fps in real time.

[1] P. Viola and M. J. Jones, "Robust real-time face detection," International Journal of Computer Vision, vol. 57, pp. 137-154, 2004.
[2] E. Hjelmas and B. K. Low, "Face detection: A survey," Computer Vision and Image Understanding, vol. 83, pp. 236-274, 2001.
[3] Y. Z. Lu, J. L. Zhou, and S. S. Yu, "A survey of face detection, extraction and recognition," Computing and Informatics, vol. 22, pp. 163-195, 2003.
[4] M. H. Yang, D. J. Kriegman, and N. Ahuja, "Detecting faces in images: A survey," Ieee Transactions on Pattern Analysis and Machine Intelligence, vol. 24, pp. 34-58, 2002.
[5] H. A. Rowley, S. Baluja, and T. Kanade, "Neural network-based face detection," Ieee Transactions on Pattern Analysis and Machine Intelligence, vol. 20, pp. 23-38, 1998.
[6] M. Sugisaka and X. J. Fan, "An effective search method for neural network based face detection using particle swarm optimization," Ieice Transactions on Information and Systems, vol. E88D, pp. 214-222, 2005.
[7] H. S. Kim, W. S. Kang, J. I. Shin, and S. H. Park, "Face detection using template matching and ellipse fitting," Ieice Transactions on Information and Systems, vol. E83D, pp. 2008-2011, 2000.
[8] J. G. Wang and T. N. Tan, "A new face detection method based on shape information," Pattern Recognition Letters, vol. 21, pp. 463-471, 2000.
[9] J. O. Kim, S. J. Seo, C. H. Chung, J. Hwang, and W. Lee, "Face detection by facial features with color images and face recognition using PCA," Computational Science and Its Applications - Iccsa 2004, Pt 1, vol. 3043, pp. 1-8, 2004.
[10] Y. H. Liu, Y. T. Chen, and S. S. Lu, "Face detection using kernel PCA and imbalanced SVM," Advances in Natural Computation, Pt 1, vol. 4221, pp. 351-360, 2006.
[11] A. Jorgensen, "AdaBoost and Histograms for Fast Face Detection," 2006.
[12] Z. Y. Ou, X. S. Tang, T. M. Su, and P. F. Zhao, "Cascade AdaBoost classifiers with stage optimization for face detection," Advances in Biometrics, Proceedings, vol. 3832, pp. 121-128, 2006.
[13] X. S. Tang, Z. Y. Ou, T. M. Su, and P. F. Zhao, "Cascade AdaBoost classifiers with stage features optimization for cellular phone embedded face detection system," Advances in Natural Computation, Pt 3, Proceedings, vol. 3612, pp. 688-697, 2005.
[14] J. M. Jan Sochman, "AdaBoost with Totally Corrective Updates for Fast Face Detection," in Proceedings of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition, 2004.
[15] J. M. J.Mit ´ eran, E. Bourennane, M. Paindavoine, J. Dubois, "Automatic Hardware Implementation Tool for a Discrete Adaboost-Based Decision Algorithm," EURASIP Journal on Applied Signal Processing, p. 12, 2005.
[16] X. B. Yu Wei, and Charayaphan Chareonsak, "FPGA IMPLEMENTATION OF ADABOOST ALGORITHM FOR DETECTION-OF FACE BIOMETRICS," in IEEE International Workshop on Biomedical Circuits & Systems, 2004.
[17] Y. Hori and T. Kuroda, "A 0.79-mm(2) 29-mW real-time face detection core," Ieee Journal of Solid-State Circuits, vol. 42, pp. 790-797, 2007.
[18] N. V. T. Theocharides, M. J. Irwin, "A PARALLEL ARCHITECTURE FOR HARDWARE FACE DETECTION," in Proceedings of the 2006 Emerging VLSI Technologies and Architectures, 2006.
[19] G.-D. S. BO-YA CHEN, YA-FENG DENG, "2-CHANNEL PARALLEL FACE DETECTION BOARD USING TWO TMS320C6201 DSPS," in Proceedings of the Fourth International Conference on Machine Learning and Cybernetics Guangzhou, 2005.
[20] K. N. Masayuki Hiromoto, Hiroki Sugano, "A Specialized Processor Suitable for AdaBoost-Based Detection with Haar-like Features," in IEEE, 2007.
[21] F. Z. Yuehua Shi, Zhong Zhang, "Hardware Implementation of ADABOOST ALGORITHM and Verification," in 22nd International Conference on Advanced Information Networking and Applications, 2008.
[22] R. C. G. a. R. E. Woods, "Digital Image Processing. Reading, MA: Addison-Wesley," 1992.
[23] S. Fifman, "Digital rectification of ERTS multispectral imagery," in in Proc. Significant Results Obtained from Earth Resources Technology Satellite-1, pp. 1131-1142., 1973.
[24] Y. Freund and R. E. Schapire, "A decision-theoretic generalization of on-line learning and an application to boosting," Journal of Computer and System Sciences, vol. 55, pp. 119-139, 1997.