臺灣博碩士論文加值系統

此次論文，用了許多影像處理技巧，有平均低通濾波器、Sobel高通濾波器、影像灰階轉換、小波轉換等，可常見於國內外影像方面論文，對於影像方面研究是必備的基礎知識。

本篇論文定位方法主要有動態物件偵測、人臉膚色分析與橢圓樣板定位人臉，主要針對動態影像，快速定位人臉。辨識採用統計的方式，主要將資料庫中，同一人不同表情的視為同一類，利用LDA(Linear Discriminant Analysis)線性鑑別式分析，將不同類的人距離拉開，並拉近同一類的人，亦即將資料庫樣本全部分類到新的向量空間中，然後再將待測人臉投影到此新的向量空間中，以歐式距離計算出與空間中哪類最接近，來判斷是否為同一類裡的同一個人。

This thesis was built by using many important image processing technologies such as average filter, Sobel high-pass filter, gray-level transform, and wavelet, etc. Those technologies are basic knowledge through image processing which can be seen in many papers.

This thesis proposed a fast face detection method using active object detection, face skin color analysis, and elliptical template. This method was built by statistical learning theory which using Linear Discriminant Analysis (LDA) to separate different faces. That is, it classifies all patterns in database into new vector space by LDA algorithm. After that, the proposed method will decides whether the tester is in the same class by calculating the Euclidean distance between the tester vector and the training vectors.

摘要 I
Abstract II
誌謝 III
目錄 IV
圖目錄 VI
表目錄 VIII
第一章 緒論 1
1-1 研究動機 1
1-2 研究重點 2
1-3 論文架構 2
第二章 系統架構 3
2-1 系統架構流程圖 3
2-2 系統軟硬體介紹 4
2-3 MATLAB Guide介紹 5
2-4 結論 7
第三章 人臉偵測定位 8
3-1 人臉特性分析 8
3-2 人臉動態物件分析 9
3-3 人臉膚色分析 10
3-4 人臉橢圓模型分析 11
3-4-1 影像前置處理 12
3-4-1-1 低通濾波器 12
3-4-1-2 高通濾波器 14
3-4-2 橢圓模型偵測定位 16
3-4-3 橢圓模型定位之有無前置處理比較 19
第四章 人臉辨識 21
4-1 離散小波轉換 22
4-2二維小波影像分析原理 26
4-3 PCA轉換 28
4-3-1 基本運作原理 28
4-3-2 PCA缺點 32
4-4 LDA轉換 33
4-5 改良式LDA轉換 39
4-6 歐式距離 44
4-7 結論 44
第五章 實驗結果與討論 45
5-1 主GUI介面 45
5-2 介面功能操作說明 46
5-2-1 手動操作模式流程 47
5-2-2 自動操作模式流程 49
5-3 實驗結果 50
5-4 討論 65
第六章 結論與未來方向 66
參考文獻 67

[1] R. C. Gonzalez and R. E. Woods, Digital image processing, 2nd edition, Prentice -Hall, New Jersey 07458, 2001.
[2] 黃泰祥, 具備人臉追蹤與辨識功能的一個智慧型數位監視系統, 私立中原大學電子工程學系碩士學位論文, 西元2004年6月
[3] 戴顯權, 陳政一, JPEG 2000, 紳藍出版社, 西元2002年11月
[4] 黃朝宗, 曾博志, 離散小波轉換之積體電路架構, 台大電子所DSP/IC實驗室
[5] L. L. Shen and B. Li, “Gabor Feature Based Face Recognition Using Kernel Methods,” Proc. of the Sixth IEEE International Conference on Automatic Face and Gesture Recognition (FGR’04), 0-7695-2122-3/04, pp. 170-176, 2004.
[6] M. Turk and A. Pentland, “Face Recognition using Eigenfaces,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 586-591, 1991.
[7] 林咸仁, 改良線性鑑別式分析在少量訓練樣本下之人臉辨識研究, 國立成功大學資訊工程學系碩士學位論文, 西元2002年7月
[8] K. Baek, B. Draper, J. R. Beveridge, K. She, “PCA vs. ICA: A Comparison on the FERET Data Set,” Proc. of the Fourth International Conference on Computer Vision, Pattern Recognition and Image Processing, Durham, NC, USA, pp. 824-827, 2002.
[9] B. A. Draper, K. Baek, M. S. Bartlett and J. R. Beveridge, “Recognizing Faces with PCA and ICA,” Computer Vision and Image Understanding, vol. 91, no. 1, pp. 115-137, 2003.
[10] A. Hyvarinen and E. Oja, “Independent component analysis: algorithms and applications,” Neural Networks, vol. 13, Issue 4, pp. 411--430, 2000.
[11] L. I. Smith, “A tutorial on Principal Components Analysis,” Technical Report, February 26, 2002.
[12] Y. O. Li, T. Adali and V. D. Calhoun, “Independent Component Analysis with Feature Selective Filtering,” in Proc. IEEE Workshop on Machine Learning and Signal Processing (MLSP 2004), Sao Luis, Brazil.
[13] J. Yao, P. Krolak, and C. Steele, “The Generalized Gabor Transform," IEEE Trans. on image processing, vol. 4, no. 7, July 1995.
[14] C. Liu, “Gabor-Based Kernel PCA with Fractional Power Polynomial Models for Face Recognition,” IEEE Trans. on pattern analysis and machine intelligence, vol. 26, no. 5, May 2004.
[15] D. C. Lee, “Adaptive Processing for Feature Extraction: Application of Two-Dimensional Gabor Function,” Korean Journal of Remote Sensing, vol. 17, no. 4, pp. 319~334, 2001.
[16] C. Liu, H. Wechsler, “A Gabor Feature Classifier for Face Recognition,” Proceedings Eighth IEEE International Conference on Volume Computer Vision ICCV 2001, pp. 270 -275, 2001.
[17] H. Yu, J. Yang, “A Direct LDA Algorithm for High-Dimensional Data with Application Face Recognition,” Pattern Recognition 34(10), pp. 2067-2070, 2001.
[18] W. S. Zheng, J. H. Lai and P. C. Yuen, “GA-Fisher: A New LDA-based Face Recognition Algorithm with Selection of Principal Components,” IEEE Trans. on Systems, Man and Cybernetics Part B, vol. 35, no. 5, October, pp. 1065-1078, 2005.
[19] L. Chen, H. Liao, M. Ko, J. Lin and G. Yu, “A new LDA based face recognition system which can solve the small sample size problem,” Pattern Recognition, vol. 33, no. 10, pp. 1713–1726, 2000.
[20] T. Xiong and V. Cherkassky, “A Combined SVM and LDA Approach for Classification, oral presentation,” International Joint Conference on Neural Networks, 2005.