在人臉偵測的數位影像系統中，膚色與唇色為人臉特徵中最明顯的資訊。但由於分析一張影像的整體色彩資訊相當的複雜且需要較大量的運算，因此許多人臉偵測技術並不適合直接實現於硬體中。
本篇論文研發出一個高效率且適合實現於硬體上的色彩分割演算法。在此演算法中，我們使用子色彩空間模型來取代整體色彩資訊，並且可以準確地偵測到膚色與唇色的色彩空間範圍。而在子色彩空間模型設計中，使用無浮點數運算的設計，如此一來不僅可以直接減少大量的運算，並且可節省設計的成本。此外，為了符合硬體設計程序此演算法也採用了模組化設計概念，以提升硬體架構之設計彈性。本篇論文所提出的演算法使用重要的膚色與唇色特徵分布，因此可以準確地促進人臉偵測之精準度。
為了驗證此演算法的硬體效率，我們將演算法實現於元件可程式邏輯閘陣列(FPGA)系統中，並且與現代先進的技術進行比較。實驗結果證實，我們所提出的演算法在元件可程式邏輯閘陣列(FPGA)系統中僅需使用3,202個邏輯閘，並且擁有較高的人臉偵測率。

Skin and lip color features of a human face are the most significant information for the face detection of the emerging applications in digital image systems. However, many face detection techniques may not be suitable for direct hardware implementation due to the high level of complexity for analyzing the overall color information in an image.
This paper develops a hardware-efficient color segmentation algorithm that is especially suitable to implement on hardware for face detection. We proposed the color sub-space model to detect the accurate skin/lip color ranges instead of the overall color information for efficient hardware design. Note that color sub-spaces are developed without floating-point operation to directly reduce the computational cost. Furthermore, the modulized design for the hardware design procedure is also adopted in the proposed algorithm. The significant skin/lip color features distribution can be accurately detected by using our proposed algorithm to facilitate the face detection.
The proposed algorithm was implemented on a field-programmable gate array (FPGA) system for verifying its efficiency. Compared with other state-of-the-art algorithms, the proposed algorithm can significantly decrease the computational cost of the hardware implementation by using color segmentation instead of the overall analysis of the color distribution. Experimental results have verified that our proposed FPGA system occupies only 3,202 logic cells, or about five times less than the current comparable FPGA system with better detection rate.

[1] The Champion Database, http://cat.hfu.edu.tw/˜b8903004/1999/
breakfast_champions_1999.htm.
[2] E. Akagunduz and I. Ulusoy, 3D face detection using transform invariant features,
Electronics Letters 46 (2010), no. 13, 905–907.
[3] Roberto Brunelli and Tomaso Poggio, Face recognition: features versus templates,
IEEE Transactions on Pattern Analysis and Machine Intelligence 15 (1993), no. 10,
1042–1052.
[4] I. Craw, H. Elis, and J. R. Lishman, Automatic extraction of face-features, Pattern
Recognition Letters 5 (1987), no. 2, 183–187.
[5] C. Gao, S.-L.L. Lu, T. Suh, and H. Lim, Field programmable gate array-ased haar
classifier for accelerating face detection algorithm, Image Processing, IET 4 (2010),
no. 3, 184–194.
[6] Christophe Garcia and Manolis Delakis, Convolutional face finder: a neural architecture
for fast and robust face detection, IEEE Transactions on Pattern Analysis and
Machine Intelligence 26 (2004), no. 11, 1408–1423.
[7] R. M. Haralick, S. R. Sternberg, and X. Zhuang, Image analysis using mathematical
morphology, IEEE Transactions on Pattern Analysis andMachine Intelligence archive
9 (1987), no. 4, 532–550.
[8] Tony Jebara, Kenneth Russell, and Alex Pentland, Mixtures of Eigenfeatures for Real-
Time Structure from Texture, In Proceedings of the International Conference on Computer
Vision, January 1998, pp. 128–135.
[9] R. Kjeldsen and J. Kender, Finding skin in color images, Proceedings of the 2nd
International Conference on Automatic Face and Gesture Recognition, 1996, p. 312.
[10] Zhenhua Li, Zhongliang Jing, Xuhong Yang, and Shaoyuan Sun, Color transfer based
remote sensing image fusion using non-separable wavelet frame transform, Pattern
Recognition Letters 26 (2005), no. 13, 2006–2014.
[11] Rob McCready, Real-Time Face Detection on a Configurable Hardware System, Proceedings
of the The Roadmap to Reconfigurable Computing, 10th InternationalWorkshop
on Field-Programmable Logic and Applications, 2000, pp. 157–162.
[12] Loris Nanni and Alessandra Lumini, A multi-expert approach for wavelet-based face
detection, Pattern Recognition Letters 28 (2007), no. 12, 1541–1547.
[13] Duy Nguyen, David Halupka, Student Member, Parham Aarabi, Ali Sheikholeslami,
and Senior Member, Real-Time Face Detection and Lip Feature Extraction Using
Field-Programmable Gate Arrays, IEEE Transactions on System, Man, and
Cybernetics-Part B: Cybernetics 36 (2006), no. 4, 902–912.
[14] Erik Reinhard, Michael Ashikhmin, Bruce Gooch, and Peter Shirley, Color transfer
between images, IEEE Computer Graphics and Applications 21 (2001), no. 5, 34–41.
[15] Henry A. Rowley, Shumeet Baluja, and Takeo Kanade, Neural Network-Based Face
Detection, IEEE Transactions On Pattern Analysis and Machine intelligence 20
(1998), no. 1, 23–38.
[16] I. Sajid, M. M. Ahmed, and I. Taj, Design and Implementation of a Face Recognition
System Using Fast PCA, IEEE Proceedings of the International Symposium on
Computer Science and its Applications, October 2008, pp. 126–130.
[17] Shin’ichi Satoh, Yuichi Nakamura, and Takeo Kanade, Name-It: Naming and Detecting
Faces in News Videos, IEEE Transactions on Multimedia 6 (1999), no. 4, 22–35.
[18] Paul Viola andMichael J. Jones, Robust real-time face detection, International Journal
of Computer Vision 57 (2004), no. 2, 137–154.
[19] Hualu Wang and Shih-Fu Chang, A highly efficient system for automatic face region
detection in MPEG video, IEEE Transactions on Circuits and Systems for Video
Technology 7 (1997), no. 4, 615–628.
[20] Guangzheng Yang and Thomas S Huang, Human face detection in a complex background,
Pattern Recognition 27 (1994), no. 1, 53–93.