臺灣博碩士論文加值系統

本研究提出一個結合生物特徵與主成分分析法的人臉影像識別方法，並以此為基礎建立一個具有多種生物特徵的人臉影像識別系統來實驗所提出的識別方法。在此系統中，我們使用了雙色彩空間的模型來加強處理膚色分離以擷取人臉，並從所有候選人臉影像擷取出各個人臉的生物特徵，計算出各個候選人臉的人臉特徵差異向量，接著透過主成分分析法來找到特徵的權重向量，然後將這些人臉特徵差異向量及權重向量存到資料庫，當輸入一個欲辨識的人臉影像時，只要擷取出該人臉的生物特徵，計算出人臉特徵差異向量，就可以利用這些權重向量，依照我們提出的人臉識別流程，循序漸進的加權比對，找出最接近的人臉。
最後，我們將上述流程與方法以實驗進行實驗，不斷測試與校正流程後獲得初步的識別成功率，驗證以主成分分析法結合生物特徵確實可以對人臉進行識別，且因為是取用幾個具有識別力的生物特徵作為人臉識別依據，所以與過去其他研究先進所提之方法，以整張人臉像素為識別依據相比可以節省下更多的資料量與計算量。雖然現階段只提出了少數幾個生物特徵做為識別依據，但相信未來以此作為基礎，繼續參考其他學者針對生物特徵的相關研究來增加選用的生物特徵多樣性，應可持續提高識別的成功率，使整個人臉識別系統既快速又準確。

This study proposes a face recognition method by integrating the techniques of biometrics and principal component analysis (PCA). Based on this method, we construct a multi-face recognition system which is based on fourteen biometric features. In this system, improve the detection process by using two color space models to extract face regions from the picture. We capture the biometric features from every candidate of face image, calculate the difference of facial feature vector (DFFV) and find weights of feature vector by PCA. Then, these data are stored in facial database for face recognition. When a new face image is coming, we capture the biometric features can be captured from the coming face image, calculate DFFV, and compare them with DFFVs in database by progressively use the weights which obtained from the PCA to find the closest face. Finally, we continued test and regulate the experimental procedure, we obtain initial recognition success rate and confirmed our face recognition method which used PCA and biometrics can be used. And because this method use only some biometrics features to detection face, therefore, we can save more calculation time and amount of data.
In the future, we need to study more the other research on biometrics and improve amount of features, we think it can be improve success rate make the face recognition both fast and accurately.

目錄
摘要 I
Abstract II
致謝 III
圖目錄 VII
表目錄 VIII
第 1 章 緒論 1
1.1 研究背景 1
1.2 研究動機 1
1.3 研究目的 2
1.4 論文之架構 3
第 2 章 文獻探討 4
2.1 人臉偵測方法 4
2.1.1 色彩空間與膚色分離 4
2.1.2 RGB膚色分離 5
2.1.3 YCbCr膚色分離 5
2.1.4 Haar-Like Features特徵擷取 6
2.2 主成分分析法 6
第 3 章 主成分分析法進行人臉辨識 9
3.1 結合RGB與YCbCr進行人臉偵測 9
3.2 主成分分析法與生物特徵的權重 11
3.3 人臉特徵資料庫的建立 16
第 4 章 進行人臉辨識 21
第 5 章 實驗設計與成果 24
5.1、實驗架構 24
5.2、實驗成果 25
第 6 章 結論與未來研究 32
6.1結論 32
6.2未來工作 33
參考文獻 34



圖目錄
圖1、Haar-Like Features偵測模型[16] 6
圖2、RGB膚色像素與YCbCr膚色像素的文氏圖 10
圖3、同時考慮YCbCr色彩空間與RGB色彩空間的範例圖。 11
圖4、生物特徵示意圖 12
圖5、人臉特徵資料庫的建立的流程圖 17
圖6、人臉識別流程圖 21
圖7、人臉比對流程圖 23
圖8、人臉特徵框選成功圖示 26
圖9、人臉特徵框選失敗圖示 26
圖10、識別成功範例圖1 27
圖11、識別成功範例圖2 28
圖12、識別失敗範例圖1 28
圖13、識別失敗範例圖2 29


表目錄
表1、本研究的實驗環境 24
表2、本研究的評估因子 25
表3、人臉識別成功率 27
表4、Complexity Analysis 30
表5、實驗成果統計表 31

[1]吳明芳、李振興、王炳聰、詹慧珊、黃建邦(2011)，「多人臉影像視覺辨識技術」，Journal of Kun Shan University，No. 8，第75-95頁。
[2]陳榮昌、盧菁、劉賀平(2009)，「基於人臉座標系統的人臉識別」，第十四屆人工智慧與應用研討會論文集，台中，第30-31頁。
[3]陳榮昌、楊凱麟、陳原尉(2013)，「結合面相學與人臉特徵分析來進行面相與個性關係之研究」，第七屆資訊科技國際研討會論文集，台中，第146頁。
[4]陳繼棠(2006)，結合區域膚色分割與主要成分分析於多人臉部辨識，碩士論文，台灣海洋科技大學機械與機電工程學系，高雄。
[5]顏于嘉(2006)，生物特徵與資訊隱私權—從國家利用個人生物特徵辨識人民身分談起，碩士論文，台灣大學法律系，台北。
[6]薛傑仁(2010)，生物辨識之人臉辨識的方法，碩士論文，亞洲大學生物與醫學資訊系碩士學位論文，台中。
[7]黃一庭(2002)，規則導向之多人人臉即時偵測，碩士論文，東華大學資訊工程學系，花蓮。
[8]M. M. Aznaveh, H. Mirzaei, E. Roshan, and M. Saraee(2008), “A New Color Based Method for Skin Detection Using RGB Vector Space,＂ Human System Interactions Conference, pp. 932-935.
[9]M. A. Berbar, H. M. Kelash, and A. A. Kandeel(1993), “Faces and Facial Features Detection in Color Images,” Geometric Modeling and Imaging, pp. 209-214.
[10]R. C. Chen and K. L. Yang(2012), “Using Floating Parameter to Achieve Adaptive Facial Feature,” International Conference on Innovation and Management (IAM2012), Palau.
[11]A. P. Chen, L. Pan, Y. B. Tong, and N. Ning(2010), “Face Detection Technology Based in Skin Color Segmentation and Template Matching,” Second International Workshop on Education Technology and Computer Science (ETCS), No. 2, pp. 708-711.
[12]J. I. Girado, D. J. Sandin, T. A. DeFanti, L. K. Wolf(2003), “Real-time Camera-based Face Detection using a Modified LAMSTAR Neural Network System,” Applications of Artificial Neural Networks in Image Processing VIII, pp. 20-24.
[13]S. H. Jeng, H. Y. Liao, Y. T. Liu, and M. Y. Chen(1996), “An Efficient Approach for Facial Feature Detection Using Geometrical Face Model,” Proceedings of the 13th International Conference on Pattern Recognition, No. 3, pp. 426-430.
[14]Q. R. Jiang and H. L. Li(2010), “Robust Human Face Detection in Complicated Color Images,” Information Management and Engineering (ICIME), pp. 218-221.
[15]I. T. Jolliffe(2002), Principal Component Analysis, Series: Springer Series in Statistics, 2nd ed., Springer, NY, XXIX, 487, pp. 28.
[16]T. Mita, T. Kaneko, and O. Hori(2005), “Joint Haar-like Features for Face Detection,” 10thIEEE International Conference on Computer Vision(ICCV), Vol. 2, pp. 1619-1626.
[17]M. Matsugu, K. Mori, M. Ishii, and Y. Mitari(2002), “Convolutional Spiking Neural Network Model for Robust Face Detection,” Proceedings of the 9th International Conference on Neural Information Processing(ICONIP), Vol. 2, pp. 660-664.
[18]J. H. Park, J. W. Seo, D. G. An, and S. J.Chung(2000), “Detection of Human Faces Using Skin Color And Eyes,” IEEE International Conference on Multimedia and Expo (ICME), No. 1, pp. 133-136.
[19]P. Peer, J. Kovac, and F. Solina(2003), “Human Skin Color Clustering for Face Detection,” EUROCON 2003. Computer as a Tool. The IEEE Region 8, Vol. 2, pp. 144-148.
[20]H. A. Rowley, S. Baluja, and T. Kanade(1998), “Neural Network Based Face Detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, pp. 23-38.
[21]L. Tai and H. B. Wang (2007), “Detecting and Locating Human Eyes in Face Images Based on Progressive Thresholding,” IEEE International Conference on Robotics and Biomimetics, pp. 708-711.
[22]M. Turk and A. Pentland(1991), “Eigenfaces for Recognition,” J. Cognitive Neuroscience, Vol. 3, No. 1, pp. 71-86.
[23]M. Turk and A. Pentland(1991), “Face Recognition Using Eigenfaces,” IEEE Conf. on Computer Vision and Pattern Recognition, pp. 586-591.
[24]J. Wang, Z. Z. Song, H. L. Zhao, B. Liu, and D. F. Chen(2009), “Eye Detection Algorithm Base on Area-Blocks pairing and Multi-angle Template Matching,” Control and Decision Conference, pp. 661-664.
[25]M. Turk and A. Pentland(1991), “Face Recognition Using Eigenfaces,” IEEE Conf. on Computer Vision and Pattern Recognition, pp. 586-591.

[26]J. Wang, Z. Z. Song, H. L. Zhao, B. Liu, and D. F. Chen(2009), “Eye Detection Algorithm Base on Area-Blocks Pairing and Multi-angle Template Matching,” Control and Decision Conference, pp. 661-664.