臺灣博碩士論文加值系統

人臉辨識系統在生物識別領域中，已經是一個重要的研究領域。但是許多先進的臉部辨識系統只聚焦於辨識正面無偏角臉部影像的資料樣本，而對於頭部有上下偏轉或攝影機垂直視角偏轉所擷取到的臉部偏角影像無法進行有效且正確的辨識。

基於這個原因，在本論文中，我們提出一種低複雜度且高效率的快速仿三維垂直偏角回復方法，在單一張臉部影像輸入之後，會透過仿三維臉部建模方法計算出垂直視角偏轉的角度，接下來將欲辨識的臉部影像特徵回復成接近正面的臉部影像特徵，最後再將回復後的臉部影像與資料庫中的正面臉部影像資料進行辨識比對工作。此臉部辨識系統主要是基於我們所提出的快速仿三維垂直偏角回復方法，再結合枷柏小波特徵擷取(Gabor Wavelet Feature Extraction)所組成。從實驗結果我們可以發現，有使用快速仿三維垂直偏角回復方法的臉部影像與資料庫中正面視角的臉部影像的相似度都會提高，因而辨識準確率也會隨之提升。

Face recognition is the key part in biometric field because it can provide noninvasive and convenient features. Most of conventional face recognition systems just focus on the frontal face cases, but the fact is that the face data captured by the camera are often filled up with the pose variation, whether horizontal or vertical pose variations. It decreases the recognition accuracy and reliability.
Based on semi-3D face model, this paper proposes a simple but practical preprocessing method to recover the vertical pose variation simply from a single 2-D model view. The proposed method evaluates the angle of the vertical pose variation and thereby recovers the flanked face to the frontal face. Consequently, the recovered face data can be processed by the original face recognition system accurately and efficiently. In the experiment, we adopt the Gabor Wavelet transform for the feature extraction core of the face recognition system. The experimental result shows the proposed Fast Semi-3D Vertical Pose Recovery method can significantly help to raise both similarity and precision of the face recognition system.

摘 要 i
ABSTRACT iii
誌謝 v
目錄 vi
表目錄 viii
圖目錄 ix
一、 緒論 1
1.1 研究背景 1
1.2 研究動機與目的 1
1.3 人臉辨識流程 5
1.4 論文架構 6
二、 人臉辨識相關研究 7
2.1 快速仿三維水平偏角回復方法 7
2.2 基於Statistical Affine Transformation的水平偏角校正 12
三、 快速仿三維垂直偏角回復方法 16
四、 實驗分析 19
4.1 實驗架構 19
4.1.1 影像前置處理(Image Preprocessing) 21
4.1.2 臉部偵測演算法(Face Detection Algorithm) 22
4.1.3 特徵擷取演算法(Features Extraction Algorithm) 24
4.1.4 特徵比對演算法(Feature Matching Algorithm) 25
4.1.5 人臉辨識系統展示 27
4.2 實驗結果 28
五、 OMAP嵌入式系統實作 31
5.1 架構簡介 31
5.2 建置開發環境 33
5.2.1 Windows 環境 – 配置CCS 3.1 33
5.2.2 Linux 環境 – 安裝toolchain、kernel source與SDK 36
5.3 安裝bootloader、kernel與filesystem 38
5.3.1 下載設定bootloader 39
5.3.2 安裝kernel與filesystem 43
5.4 LDK5912應用程式展示 45
5.4.2 相機模組使用 48
5.5 軟體開發流程 50
5.5.1 ARM端應用程式開發 50
5.5.2 DSP端應用程式開發 54
5.6 臉部辨識技術相關開放原始碼的移植 57
5.6.1 OpenCV 開放原始碼簡介 57
5.6.2 OMAP5912嵌入式平台安裝OpenCV開放源程式庫 58
5.6.3 臉部辨識技術相關演算法在嵌入式平台實現成果 60
六、 結論與未來展望 66
參考文獻 68
簡歷 71

[1] R. Chellappa, C.L. Wilson and S. Sirohey, “Human and machine recognition of faces: a survey,” Proceedings of the IEEE, vol. 83, pp. 705-741, May 1995.
[2] A. Shashua and T. Riklin-Raviv, “The Quotient Image: Class-Based Re-Rendering And Recognition With Varying Illuminations,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, pp. 129-139, Feb. 2001.
[3] M.A. Turk and A.P. Pentland, “Face recognition using eigenfaces,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 586-591, Jun. 1991.
[4] P.N. Belhumeur, J.P. Hespanha and D.J. Kriegman, “Eigenfaces vs. Fisherfaces: recognition using class specific linear projection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.19, pp. 711-720, Jul. 1997.
[5] M. Kirby and L. Sirovich, ” Application of the Karhunen-Loeve procedure for the characterization of human faces,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, pp. 103-108, Jan. 1990.
[6] R.J. Baron, “Mechanism of human facial recognition,” International Journal of Man Machine Studies, vol. 15, pp. 137-178, 1981.
[7] R. Brunelli and T. Poggio, “Face recognition: features versus templates,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 15, pp. 1042-1052, Oct. 1993.
[8] F. Zuo and P.H.N. de With, “Real-time embedded face recognition for smart home,” IEEE Transactions on Consumer Electronics, vol. 51, pp. 183-190, Feb. 2005.
[9] A. Pentland, B. Moghaddam and T. Starner, “Face Recognition using View-Based and Modular Eigenspaces,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 84-91, Jun. 1994.
[10] L. Wiskott, J.M. Fellous, N. Kuiger and v.d.M. Christoph, “Face recognition by elastic bunch graph matching,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, pp. 775-779, Jul. 1997.
[11] V. Blanz and T. Vetter, “Face recognition based on fitting a 3D morphable model,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, pp. 1603-1074, Sep. 2003.
[12] A. Lanitis, C.J. Taylor and T.F. Cootes, “Automatic interpretation and coding of face images using flexible models,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, pp. 743-756, Jul. 1997.
[13] S. Baker, I. Matthews and J. Schneider, “Automatic construction of active appearance models as an image coding problem,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 26, pp. 1380-1384, Oct. 2004.
[14] X. Chai; S. Shan and W. Gao, “Pose normalization for robust face recognition based on statistical affine transformation,” Proceedings of IEEE International Conference on Information, Communications and Signal Processing, vol. 3, pp. 1413 - 1417, Dec. 2003.
[15] Y. Gao, M.K.H. Leung, W. Wang and S.C. Hui, “Fast face identification under varying pose from a single 2-D model view,” IEE Proceedings of Vision, Image and Signal Processing, vol. 148, pp. 248-253, Aug. 2001.
[16] K. Yow, “Automatic human face detection and localization,” Ph.D. Thesis at University of Cambridge, Department of Engineering, 1998.
[17] K.B. Vinay and B.S. Shreyas, “Face Recognition Using Gabor Wavelet,” Proceedings of ACSSC ''06 Fortieth Asilomar Conference on Signals, Systems and Computers, pp. 293-597, Oct. - Nov. 2006.
[18] S. Linlin, B. Li and P. Picton, “Facial recognition/verification using gabor wavelets and kernel methods,” Proceedings of International Conference on Image Processing, vol. 3, pp. 1433-1436, Oct. 2004.
[19] J. Chittoru, R. Munasinghe and A. Davari, “Edge detection and segmentation for machine vision,” Proceedings of the Thirty-Seventh Southeastern Symposium on System Theory, pp. 457-461, Mar. 2005.
[20] J.F. Canny, “A computational approach to edge detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 679-698, Nov. 1986.
[21] Q.C. Tian, P. Quan and Y. M. Cheng, “Fast algorithm and application of Hough transform in iris segmentation,” Proceedings of International Conference on Machine Learning and Cybernetics, vol. 7, pp. 3977-3980, Aug. 2004