多視角之多重解析度人臉辨識

以作者查詢圖書館館藏

、以作者查詢臺灣博碩士

、以作者查詢全國書目

、勘誤回報

、線上人數：22

、訪客IP：18.191.225.80

姓名

李建輝(Jain-Huei Li) 查詢紙本館藏

畢業系所

資訊工程學系在職專班

論文名稱

多視角之多重解析度人臉辨識
(Multiresolution Face Recognition with Multiple Views)

相關論文

★ 適用於大面積及場景轉換的視訊錯誤隱藏法	★ 虛擬觸覺系統中的力回饋修正與展現
★ 多頻譜衛星影像融合與紅外線影像合成	★ 腹腔鏡膽囊切除手術模擬系統
★ 飛行模擬系統中的動態載入式多重解析度地形模塑	★ 以凌波為基礎的多重解析度地形模塑與貼圖
★ 多重解析度光流分析與深度計算	★ 體積守恆的變形模塑應用於腹腔鏡手術模擬
★ 互動式多重解析度模型編輯技術	★ 以小波轉換為基礎的多重解析度邊線追蹤技術(Wavelet-based multiresolution edge tracking for edge detection)
★ 基於二次式誤差及屬性準則的多重解析度模塑	★ 以整數小波轉換及灰色理論為基礎的漸進式影像壓縮
★ 建立在動態載入多重解析度地形模塑的戰術模擬	★ 以多階分割的空間關係做人臉偵測與特徵擷取
★ 以小波轉換為基礎的影像浮水印與壓縮	★ 外觀守恆及視點相關的多重解析度模塑

檔案

[Endnote RIS 格式]

[Bibtex 格式]

[相關文章]

[文章引用]

[完整記錄]

[館藏目錄]

[檢視]

[下載]

本電子論文使用權限為同意立即開放。
已達開放權限電子全文僅授權使用者為學術研究之目的，進行個人非營利性質之檢索、閱讀、列印。
請遵守中華民國著作權法之相關規定，切勿任意重製、散佈、改作、轉貼、播送，以免觸法。

摘要(中)

在人臉辨識的研究中，大多數人是以特徵擷取的主成份分析法 (principal component analysis, PCA) 及線性鑑別分析法 (linear discriminant analysis, LDA) 來辨識人臉。這二種方法在多視角 (multi-views) 辨識上各有其優缺點，本論文即整合這二者的優點，提出一個多視角分類法 (先以線性鑑別分析法做臉部視角分類，再以主成份分析法就選定的類別做辨識)，以提高不同視角臉部辨識的辨識率。為了執行效率，我們也利用離散小波轉換 (discrete wavelet transform) 做多重解析度影像分解，一方面降低影像解析度做分析，另一方面以高頻資訊擷取臉部明顯區域做分類。
在實驗中，我們以40人所組成的400張多視角人臉影像來測試本系統的效能；其中200張影像做訓練，另外200張做測試。我們共做了三種實驗：(i) 多視角分類法，(ii) 直接以主成份分析法做辨識，及 (iii) 直接以線性鑑別分析法做辨識；並比較這三者方法在多視角人臉辨識上的效能。實驗結果顯示在各種不同樣本集合測試下，多視角分類法的辨識率都優於主成份分析法；另外在訓練樣本數少於30人的情形下，多視角分類法也比線性鑑別分析法好。

摘要(英)

In the study of face recognition, PCA (principal component analysis) and LDA (linear discriminant analysis) are commonly used for recognizing human faces. Both methods have individually advantage and disadvantage for multi-view face recognition. We here proposed a recognition system to improve the recognition rate for multi-view face recognition by integrating the advantages of PCA and LDA. In the proposed recognition system, the LDA is used to classify facial views, and then PCA is used to recognize face images in a specified class. For efficiency, the discrete wavelet transform is used to reduce the image resolution for recognition as well as to extract the face region for classification based on the data in the high-frequency subbands.
In our experiments, 400 multi-view images of 40 persons were captured for training and test. We compared the performance of the three methods: (i) multi-view recognition, (ii) PCA, and (iii) LDA for multi-view face recognition. With the same face samples, the performances of multi-view recognition method are always better than that of PCA and LDA (at most 30 persons).

關鍵字(中)

★ 人臉辨識
★ 主成份分析法
★ 線性鑑別分析法
★ 多視角

關鍵字(英)

★ multiple views
★ principal component analysis
★ linear discriminant analysis
★ face recognition

論文目次

摘要 iii
目錄 iv
圖目錄 vii
表目錄 viii
第一章簡介 1
1.1 研究動機 1
1.2 人臉辨識的演進 2
1.3 相關技術 3
1.4 人臉辨識流程 4
1.4.1 人臉辨識訓練流程 4
1.4.2 人臉辨識工作流程 5
1.5 論文架構 6
第二章相關研究探討 8
2.1 多重解析度轉換 8
2.1.1 多重解析空間 8
2.1.2 離散小波轉換 10
2.1.3 二維離散小波轉換 11
2.2 主成份分析法 13
2.3 線性鑑別分析法 15
2.4 距離函數 15
第三章分類與辨識 17
3.1 多視角分類 17
3.2 線性鑑別分析法轉換 20
3.3 改良式的線性鑑別分析法 23
3.4 主成份分析法轉換 25
第四章實驗 29
4.1 人臉資料庫 29
4.1.1 自建多視角人臉資料庫 29
4.1.2 ORL人臉資料庫 29
4.2 多視角分類法實驗流程說明 30
4.2.1 分類訓練流程 31
4.2.2 人臉辨識訓練流程 32
4.2.3 分類辨識流程 33
4.2.4 分類後人臉辨識流程 34
4.3 實驗結果 35
4.3.1 多視角分類結果 35
4.3.2 主成份分析法之人臉辨識結果 36
4.3.3 各種視角之主成份分析法辨識結果 37
4.3.4 線性鑑別分析法之人臉辨識結果 38
4.3.5 三種辨識方法結果比較 39
4.3.6 主成份分析法與線性鑑別分析法採用ORL人臉資料庫辨識結果 41
4.3.7 分類訓練樣本採用臉部明顯區域 42
第五章結論與未來研究 45
5.1 結論 45
5.2 未來研究 47
參考文獻 48
附錄一、自建多視角人臉資料庫 50
附錄二、ORL人臉資料庫 54

參考文獻

[1] Chang, S. L., Face Recognition Using Principal Facial-Factor Analysis, Master Thesis, CSIE Dept., Univ. of Tatung, Taiwan, 2001.
[2] Chen, G. S., Two-Stage Recognition of Multi-orientation Faces, Master Thesis, CSIE Dept., Univ. of Dong Hwa, Taiwan, 2001.
[3] Gonzalez, R. C. and R. E. Woods, Digital Image Processing Second Edition, Addison-Wesley Publishing, NY, 2002.
[4] Hong, Z. Q. and J. Y. Yang, "Optimal discriminant plane for a small number of samples and design method of classifier on the plane," Pattern Recognition , vol.24, no.4, pp.317-324, 1991.
[5] Kouzani, A. Z., F. He, and K. Sammut, "Multiresolution eigenface-component," in Proc. IEEE Conf. on Speech and Image Technologies for Computing and Telecommunication, vol.1, Dec.2-4, 1997, pp.353-356.
[6] Lee, W. S., H.J. Lee, and J.H. Chung, "Wavelet-based FLD for face recognition," in Proc. 43rd IEEE Midwest Symp. on Circuits and Systems, vol.2, Aug.8-11, 2000, pp.734-737.
[7] Lin, H. T. Implementation of A Face Recognition System Base on The Fisherface Algorithm, Master Thesis, Elect. and Con. Eng. Dept., Univ. of Chiao Tung, Taiwan, 2001.
[8] Lin, S. S. On Improving Linear Discriminant Analysis for Face Recognition with Small Sample Size Problem, Master Thesis, CSIE Dept., Univ. of Cheng Kung, Taiwan, 2001.
[9] Liu, C. and H. Wechsler, "Enhanced Fisher linear discriminant models for face recognition," in Proc. IEEE Int. Conf. on Pattern Recognition, vol.2, 1998, pp.1368-1372.
[10] Lizama, E., D. Waldoestl, and B. Nickolay, "An eigenfaces-based automatic face recognition system," in Proc. IEEE Int. Conf. on Computational Cybernetics and Simulation, vol.1, Oct.12-15, 1997, pp.174-177.
[11] Stollnitz, E. J., T. D. Derose and D. H. Salesin, Wavelets for Computer Graphics Theory and Applications, Morgan Kaufman Publishers, Inc., San Francisco, CA, 1996.
[12] Turk, M. A. and A. P. Pentland, "Face recognition using eigenfaces," in Proc. IEEE Conf. CVPR, June 3-6, 1991, pp.586-591.
[13] Wu, G. Z., Face Recognition Using Discriminant Wavelet Features, Master Thesis, CSIE Dept., Univ. of Cheng Kung, Taiwan, 2000.
[14] Xu, Y., X. Brolly, and J.-P. Ronc, Face Detection with Color Eigenfaces, Face Detection Project, Elect. Eng. Dept., Univ. of Stanford, 2002.
[15] Yang, J. and J. Y. Yang, "Why can LDA be performed in PCA transformer space," Rapid and Brief Communication on Pattern Recognition, pp.563-566, 2003.
[16] Yilmaz, A . and M. Gokmen, "Eigenhill vs. eigenface and eigenedge," in Proc. 15th Int. Conf. on Pattern Recognition, vol.2, Sep. 3-7, 2000, pp.827-830.
[17] Yoo, T. and Y. Kim, Face Detection Using Skin Colors and Eigenfaces, EE386 Project, Elect. Eng. Dept., Univ. of Stanford, 2002.
[18] Zhang, J., Y. Yan, and M. Lades, "Face recognition: eigenface, elastic matching, and neural nets," Proc. IEEE, vol.85, no.9, pp.1422-1422, Sep. 1997.
[19] Zhao, W. and N. Nandhakumar, "Linear discriminant analysis of MPF for face recognition," in Proc. 14th Int. Conf. on Pattern Recognition, vol.1, Aug. 16-20, 1998, pp.185-188.
[20] Zhujie, and Y. L. Yu, "Face recognition with eigenfaces," in Proc. IEEE Int. Conf. on Industrial Technology, Dec.5-9, 1994, pp.434-438.
[21] http://www.uk.research.att.com/facedatabase.html.
[22] 單維彰，凌波初步，全華科技圖書公司，台北，1998。

指導教授

曾定章(Din-ChangTseng)

審核日期

2004-7-13

推文