快速人臉偵測演算法之研究 莊國楨、黃登淵
E-mail: [email protected]
摘 要
在生物特徵辨識技術中,近年來以人臉為特徵的偵測與辨識技術發展十分迅速。相對而言,人臉辨識(face recognition)是一 種更直接、更友好、更容易被人們接受的非侵犯性辨識方法。作為人臉自動辨識系統的第一步,人臉偵測(face detection)技 術有著十分重要的作用,它為後續的人臉分類提供了待辨識人臉的具體資訊。人臉偵測常常作為人臉追蹤與辨識的前置作 業,是一個複雜且困難的研究課題,其結果足以影響整個系統的效能,人臉偵測要走向實際應用,準確率和速度是很重要 的兩個關鍵因素。 本研究首先取得欲偵測人臉之數位影像,下一步則利用影像中的彩色資訊進行光線補償(lighting
compensation),顏色分割(color segmentation),以分析出影像中膚色(skin color)的部份,然後透過影像二值化(image binary)之 技術可得出類似人臉之區塊,為使人臉區塊更加完整,本研究亦採用形態學(morphology)之侵蝕(erosion)與膨脹(dilation)等 方法,來進行影像中雜點的清除與連通區域的擴大。緊接著利用連通區域標定(connected-component label)之方法,以區分 出最為可能之人臉區域,並進行人臉區域之標定。最後則利用面積閥值與?高比來定位出可能的人臉區域。本研究利用前 述自行開發之演算法,應用於複雜背景、多重人臉之數位影像上,確實能快速且正確地檢測出多重人臉存在的區域,並能 快速地標定出各別人臉之位置。
關鍵詞 : 人臉偵測 ; 光線補償 ; 顏色分割 ; 形態學 ; 連通區域 目錄
封面內頁 簽名頁 授權書.........................iii 中文摘要............
............iv 英文摘要........................v 誌謝.........
.................vi 目錄..........................vii 圖目錄...
......................x 表目錄.........................xiv 第 一章 緒論 1.1 前言.................. . ....1 1.2 研究目的...............
. . ....2 1.3 人臉偵測相關研究方法.......... .....3 1.3.1 基於知識的方法(Knowledge-based methods).. .4 1.3.2 基於特徵方法(Feature-based methods)..... 5 1.3.3 板模匹配的方法(Template matching methods)
..6 1.3.4 基於表像的方法(Appearance-based methods)...8 1.4 論文架構....................
..10 第二章 數位影像處理相關的技術 2.1 簡介....................... 11 2.2 影像強化處理
....................12 2.2.1 亮度的調整....................13 2.2.2 對 比的調整....................14 2.3 色彩分割與色彩空間................
.14 2.3.1 色彩分割............ ........ 15 2.3.2 色彩空間................
.....15 2.3.2.1 正規化RGB...................16 2.3.2.2 HSL色彩空間.........
....... .17 2.3.2.3 HSV色彩空間................. 18 2.3.2.4 HIS色彩空間.......
......... .20 2.3.2.5 YCbCr色彩空間............... .21 2.3.2.6 YIQ色彩空間.....
........... .21 2.4 影像二值化.....................22 2.4.1 整體臨界值法(global thresholding).......23 2.4.2 適應性臨界值法(adaptive thresholding).... 24 2.5 影像形態學.........
............24 2.5.1 膨脹(dilation) ................ 25 2.5.2 侵蝕(erosion) ......
...........26 2.5.3 斷開(open) ............. .....27 2.5.4 閉合(close) .......
...........27 2.6 影像拓撲學(image topology) ...........28 2.7 二值影像幾何學特徵參數..
..... .......31 第三章 人臉偵測與定位技術 3.1 光線補償(Lighting Compensation). .......33 3.2 利用膚色分析進行顏色分割....... ......36 3.3 使用影像二值化 .................
.44 3.4 使用二值影像形態學處理....... .......46 3.5 人臉區域判定............. ..
....47 3.6 人臉影像區域標定與擷取............. .49 第四章 實驗研究結果與討論 4.1 實驗結果..
.................. .52 4.2 實驗討論................... ..61 第五章 結 論與未來研究方向 5.1 結論...................... .65 5.2 未來研究方向.........
......... .66 參考文獻........................67 參考文獻
[1]G. Yang, and T. S. Huang, “Human face detection in complex background,“ Pattern Recognition, Vol. 27, No. 1, pp.53-63, 1994.
[2]L. H. Zhao, X. L. Sun, J. H. Liu, and X. H. Xu, “Face Detection Based On Skin Color,” Proceedings of the Third International Conference on Machine Learning and Cybemetics, Shanghai, pp.26-29, August 2004.
[3]S. A. Sirohey, “Human Face Segmentation, and Identification,” Technical Report CS-TR-3176, Univ. of Maryland, 1993.
[4]H. P. Graf, T. Chen, E. Petajan, and E. Cosatto, “Locating Faces and Facial Parts,” Proc. First Int’l Workshop Automatic Face and Gesture Recognition, pp.41-46, 1995.
[5]K. C. Yow, and R. Cipolla, “Feature-based human face detection. “ Image and Vision Computing, Vol. 15, No. 9, pp.713-735, 1997.
[6]K. Sandeep, and A. N. Rajagopalan, ”Human Face Detection in Cluttered Color Image Using Skin Color and Edge Information,” Indian Conference on Computer Vision, Graphics and Image Processing(ICVGIP'02), Ahmedabad, India , 2002.
[7]R. Bruneli, and T. Poggio, ”Face recognition: Features versus templates,“ IEEE Transactions on pattern analysis and machine intelligence, Vol. 15, No. 10, pp. 1042-1052, 1993.
[8]A. Yullie, P. Hallinan, and D. Cohen, ”Feature exaction from faces using deformable templates,“ International Journal of Computing Vision, Vol. 8, No. 2, pp.99-111, 1992.
[9]A. K. Jain, Y. Zhong, and M. P. Dubuission-Jolly, “Deformable template models: A review,“ Signal Processing, Vol. 71, No. 2, pp. 109-129, 1998.
[10]K. K. Sung, and T. Poggio, “Example-based learning for view-based human face detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 20, No. 1, pp.39-51, 1998.
[11]M. Turk, and A. Pentland, “Eigenfaces for recognition,” Journal of cognitive neuroscience, Vol. 3, No. 1, pp.71-86, 1991.
[12]A. Pentland, B. Moghaddam, and T. Starner, “View-based and modular eigenspaces for face recognition,“ International Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, WA, pp.21-23, 1994.
[13]B. Moghaddam, and A. Pentland, “Face recognition using view-based and modular eigenspaces,” International Proceedings of SPIE 2257, pp.12-21, 1994.
[14]H. A. Rowley, S. Baluja, and T. Kanade, “Neural network-based face detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 20, No. 1, pp.23-38, 1998.
[15]H. A. Rowley, S. Baluja, and T. Kanade, “Rotation invariant neural network-based face detection,“ International Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, pp.38-44, 1998.
[16]H. Erik, and K. L. Boon, “face detection: a survey,” Computer Vision and Image Understanding 83, pp.236-274, 2001.
[17]R. L. Hsu, A.M. Mohamed, and A. K. Jain, “Face Detection in Color Image,” IEEE Transactions on patter analysis and machine intelligence, Vol. 24, No. 5, pp.696-704, 2002.
[18]M. Soriano, B. Martinkauppi, S. Huovinen, and M. Laaksonen, “Skin color modeling under varying illumination conditions using the skin locus for selecting training pixels,” Proceedings of IEEE Nordic Signal Processing Symposium, pp.383-386, 2000.
[19]M. Soriano, M. Martinkauppi, S. Huovinen, and M. Laaksonen, “Skin detection in video under changing illumination conditions,”
Proceedings of the 15th International Conference on Pattern Recognition, Vol.1, pp.839-842, 2000.
[20]Rafael C. Gonzalez, and Richard E. Woods, “Digital Image Processing,” 2nd Edition, Pearson, 2002.
[21]Alasdair McAndrew, “Introduction to Digital Image Processing with Matlab,” Thomson Learning, 2004.
[22]吳上立與林宏墩譯,”C語言數位影像處理”,全華科技,2003。
[23]王建權,”以數位影像處理搭配動態攝影機做即時人臉追蹤之研究”,國立成功大學碩士論文,91年。
[24]黃敏峰,”人臉追蹤法應用於監控系統之研究”,國立成功大學碩士論文,92年。
[25]陳錦輝,C/C++初學指引,金禾資訊,2005。
[26]蔡孟凱、雷穎傑、與黃昭維,”C++Builder6完全攻略”,金禾資訊,2003。
[27]Fu Chang, and Chun-Jen Chen, “A Component-Labeling Algorithm Using Contour Tracing Technique,” Proceedings of the IEEE Seventh International Conference on Document Analysis and Recognition, Edinburgh, 2003.
[28]Bernd Girod, “Digital Image Processing,” http://www.stanford.edu /class/ee368