Publications-Theses

題名 基於形態轉換的多種表情卡通肖像
Automatic generation of caricatures with multiple expressions using transformative approach
作者 賴建安
Lai, Chien An
貢獻者 廖文宏
Liao, Wen Hung
賴建安
Lai, Chien An
關鍵詞 影像內容分割
圖像變形
臉部動畫參數
人臉特徵分析
Image Content Segmentation
Image Warping and Morphing
Facial Animation Parameters
Facial Features Analysis
日期 2007
上傳時間 17-Sep-2009 14:07:22 (UTC+8)
摘要 隨著數位影像軟、硬體裝置上進步與普及,普羅大眾對於影像的使用不僅限於日常生活之中,更隨著網路分享概念等Web技術的擴張,這些數量龐大的影像,在使用上更朝向娛樂化、趣味化及個人化的範疇。本論文提出結合影像處理中的人臉特徵分析(Facial Features Analysis)資訊以及影像內容分割(Image Content Segmentation)及影像變形轉換(Image Warping and Morphing)等技術,設計出可以將真實照片中的人臉轉換成為卡通化的肖像,供使用者於各類媒體上使用。卡通化肖像不但具有隱藏影像細節,保留部份隱私的優勢,同時又兼具充份擁有個人化特色的表徵,透過臉部動畫的參數(Facial Animation Parameters)設定,我們提出的卡通化系統更容許使用者依心情,來合成喜、怒、哀、樂等不同表情。另外,運用兩種轉描式(Rotoscoping)及圖像變形(Morphing)法,以不同的合成技巧來解決不同裝置在限定顏色及效果偏好上的各類需求。
As the acquisition of digital images becomes more convenient, diversified applications of image collections have surfaced at a rapid pace. Not only have we witnessed the popularity of photo-sharing platforms, we have also seen strong demand for novel mechanism that offers personalized and creative entertainment in recent years. In this thesis, we proposed and implemented a personal caricature generator using transformative approaches. By combing facial feature detection, image segmentation and image warping/morphing techniques, the system is able to generate stylized caricature using only one reference image. The system can also produce multiple expressions by controlling the MPEG-4 facial animation parameters (FAP). Specifically, by referencing to various pre-drawn caricature in our database as well as feature points for mesh creation, personalized caricatures are automatically generated from the real photos using either rotoscoping or transformative approaches. The resulting caricature can be further modified to exhibit multiple facial expressions. Important issues regarding color reduction and vectorized representation of the caricature have also been discussed in this thesis.
參考文獻 [1] On-line Paper Doll Flash Game, MyScene.com
[2] “描邊式圖像卡通轉換系統之研發”,工業技術研究院分包學術機構計畫,主持人:廖文宏,96年
[3] S. Yamamoto, X. Mao and A. Imamiya, “Colored pencil filter with custom colors”, Proc. of the Pacific Conference on Computer Graphics and Applications, p.329- 338, 2004
[4] RotoScoping, http://en.wikipedia.org/wiki/Rotoscoping
[5] J. Puzicha, M. Held, J. Ketterer, J. M. Buhmann, and D. Fellner, “On Spatial Quantization of Color Images”, Technical Report IAI-TR-98-1, University of Bonn. 1998.
[6] P. Chiang, “Caricature Generation by Analyzing Facial Features”, Master’s thesis, NCCU, Taiwan, 2004
[7] J. Ruppert,, “A Delaunay Refinement Algorithm for Quality 2-Dimensional Mesh Generation”, Journal of Algorithms, Vol.18, No.3, p548-585, 1995.
[8] Z. Y. Wu, S. Zhang, L. H. Cai, and H. M. Meng, “Real-time Synthesis of Chinese Visual Speech and Facial Expressions using MPEG-4 FAP Features in a Three-dimensional Avatar”, Proc. Int. Conf. on Spoken Language Processing, p.1802-1805, 2006
[9] M. B. Stegmann, “The AAM-API: An Open Source Active Appearance Model Implementation”, Proc. of Medical Image Computing and Computer-Assisted Intervention, p.951-952, 2003
[10] AAM-API, C++ implementation of the Active Appearance Model framework http://www2.imm.dtu.dk/~aam/aamapi/
[11] A. Raouzaiou, N. Tsapatsoulis, K. Karpouzis, and S. Kollias, “Parameterized Facial Expression. Synthesis Based on MPEG-4.”, EURASIP Journal on Applied Signal Processing, Vol. 2002, No.10, p.1021-1038, 2002
[12] L. Malatesta, A. Raouzaiou, K. Karpouzis, and S. Kollias, “MPEG-4 Facial Expression Synthesis based on Appraisal Theory.”, 3rd IFIP conference in Artificial Intelligence Applications and Innovatios, 2006
[13] R. Hsu, and A. K. Jain, “Generating Discriminating Cartoon Faces Using Interacting Snakes”, IEEE Transactions on Pattern Analysis and Machine Intelligent, vol.25, p.1388 -1398, 2003
[14] D. Decarlo, and A. Santella, “Stylization and Abstraction of Photographs”, Proc.of SIGGRAPH 2002, p.769-776, 2002
[15] J. Wang, Y. Xu, H. Shum and M. Cohen, “Video Tooning”, Proc. of SIGGRAPH 2004, Vol. 23, No. 3, p.574-583, 2004
[16] H. Chen, Z. Liu, C. Rose, Y. Xu, H. Shum and D. Salesin, “Example-based Composite Sketching of Human Portraits”, Proc. of the 3rd International Symposium on Non-photorealistic Animation and Rendering, p.95-153, 2004
[17] A. Sacco, “Imitating A Scanner Darkly”, An Adobe Illustrator Tutorial, http://www.illustratortechniques.com/imitating-a-scanner-darkly.html
[18] S. Patterson, “Combining Reality With A Rotoscope-Style Painting”, An Adobe PhotoShop Tutorial, Photoshop Essentials.com http://www.photoshopessentials.com/photo-effects/rotoscope/
[19] J. Wang, B. Thiesson, Y. Xu, and M. F. Cohen, “Image and Video Segmentation by Anisotropic Kernel Mean Shift”, Proc. of European Conference on Computer Vision, 2004
[20] D. Comaniciu, and P. Meer, “Mean Shift: A Robust Approach toward Feature Space Analysis”, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.24, No.5, p.603-619, 2002
[21] D. Comaniciu, V. Ramesh, and P. Meer, “Real-time Tracking of Non-rigid Object Using Mean Shift”, Proc. of IEEE conference on Computer Vision and Pattern Recognition, p.142-151, 2000
[22] L. Guibas, and J. Stolfi, “Primitives for the Manipulation of General Subdivisions and the Computation of Voronoi Diagrams”, ACM Transactions on Graphics, Vol.4, No.2, p.74-123, 1985
[23] AutoTrace: converts bitmap to vector graphics, http://autotrace.sourceforge.net/
[24] J. R. Shewchuk, “Triangle: Engineering a 2D Quality Mesh Generator and Delaunay Triangulator”, Applied Computational Geometry: Towards Geometric Engineering, Vol. 1148 of Lecture Notes in Computer Science, p.203-222, 1996.
[25] R. C. Gonzalez, and R. E. Woods, “Chap3 Image Enhancement in Spatial Domain”, Digital Image Processing 2nd Edition, Prentice Hall, p.75-136, 2001
[26] P. Meer, and B. Georgescu, “Edge detection with embedded confidence.”, IEEE Trans. On Pattern Analysis and Machine Intelligence, Vol. 23, p.1351-1365, 2001
[27] P. Heckbert, “Color Image Quantization for Frame Buffer Display”, Proc. of the 9th annual conference on Computer graphics and interactive techniques, vol.16, no.3, p.297-307, 1982
[28] Z. Xiang and G. Joy, “Color Image Quantization by Agglomerative Clustering”, IEEE Computer Graphics and Applications, vol.14, no.3, p.44-48, 1994
[29] D. Clark, “Color Quantization using Octrees”, Dr. Dobb’s Journal, p.54-57 and 102-104, 1996
[30] R. Ulichney, “Dithering with Blue Noise”, Proc. of IEEE, vol.76, p.56-79, 1988
[31] R. Floyd and L. Steinberg, “An Adaptive Algorithm for Spatial Greyscale”, Proc. of Society for Information Display, vol. 17, no. 2, Wiley, 1976
[32] S. Lee, G. Wolberg, and S. Y. Shin, “Polymorph: Morphing Among Multiple Images”, IEEE Computer Graphics and Applications,Vol.18, p.58-71,1998
[33] M. Grundland and N. A. Dodgson, “Color Histogram Specification by Histogram Warping”, Proc. of Society of Photo-Optical Instrumentation Engineers, vol. 5667, p.610-621, 2005
[34] K. Perlin, Responsive Face Demo, http://mrl.nyu.edu/~perlin/facedemo/
[35] K. Balci, “Xface: MPEG-4 Based Open Source Toolkit for 3d Facial Animation”, Proc. of Advanced Visual Interfaces, p.399-204, 2004
[36] S. Garchery, A. Egges, and N. Magnenat-Thalmann, “Fast Facial Animation Design for Emotional Virtual Humans” Proc. of Measuring Behaviour, 2005
[37] P. Ekman, “Facial Expression and Emotion”, Am Psychologist, Vol.48, p.384-392, 1993
[38] A. Bevilacqua, and P. Azzari, “A High Performance Exact Histogram Specification Algorithm”, 14th International Conference on Image Analysis and Processing (ICIAP 2007) , p. 623-628, 2007
描述 碩士
國立政治大學
資訊科學學系
92753002
96
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0927530022
資料類型 thesis
dc.contributor.advisor 廖文宏zh_TW
dc.contributor.advisor Liao, Wen Hungen_US
dc.contributor.author (Authors) 賴建安zh_TW
dc.contributor.author (Authors) Lai, Chien Anen_US
dc.creator (作者) 賴建安zh_TW
dc.creator (作者) Lai, Chien Anen_US
dc.date (日期) 2007en_US
dc.date.accessioned 17-Sep-2009 14:07:22 (UTC+8)-
dc.date.available 17-Sep-2009 14:07:22 (UTC+8)-
dc.date.issued (上傳時間) 17-Sep-2009 14:07:22 (UTC+8)-
dc.identifier (Other Identifiers) G0927530022en_US
dc.identifier.uri (URI) https://nccur.lib.nccu.edu.tw/handle/140.119/32716-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 資訊科學學系zh_TW
dc.description (描述) 92753002zh_TW
dc.description (描述) 96zh_TW
dc.description.abstract (摘要) 隨著數位影像軟、硬體裝置上進步與普及,普羅大眾對於影像的使用不僅限於日常生活之中,更隨著網路分享概念等Web技術的擴張,這些數量龐大的影像,在使用上更朝向娛樂化、趣味化及個人化的範疇。本論文提出結合影像處理中的人臉特徵分析(Facial Features Analysis)資訊以及影像內容分割(Image Content Segmentation)及影像變形轉換(Image Warping and Morphing)等技術,設計出可以將真實照片中的人臉轉換成為卡通化的肖像,供使用者於各類媒體上使用。卡通化肖像不但具有隱藏影像細節,保留部份隱私的優勢,同時又兼具充份擁有個人化特色的表徵,透過臉部動畫的參數(Facial Animation Parameters)設定,我們提出的卡通化系統更容許使用者依心情,來合成喜、怒、哀、樂等不同表情。另外,運用兩種轉描式(Rotoscoping)及圖像變形(Morphing)法,以不同的合成技巧來解決不同裝置在限定顏色及效果偏好上的各類需求。zh_TW
dc.description.abstract (摘要) As the acquisition of digital images becomes more convenient, diversified applications of image collections have surfaced at a rapid pace. Not only have we witnessed the popularity of photo-sharing platforms, we have also seen strong demand for novel mechanism that offers personalized and creative entertainment in recent years. In this thesis, we proposed and implemented a personal caricature generator using transformative approaches. By combing facial feature detection, image segmentation and image warping/morphing techniques, the system is able to generate stylized caricature using only one reference image. The system can also produce multiple expressions by controlling the MPEG-4 facial animation parameters (FAP). Specifically, by referencing to various pre-drawn caricature in our database as well as feature points for mesh creation, personalized caricatures are automatically generated from the real photos using either rotoscoping or transformative approaches. The resulting caricature can be further modified to exhibit multiple facial expressions. Important issues regarding color reduction and vectorized representation of the caricature have also been discussed in this thesis.en_US
dc.description.tableofcontents 第一章 緒論
1.1 研究動機
1.2 需求分析
1.3 多種表情合成
1.4 論文架構
第二章 相關研究
2.1 非真實影像繪圖技術(Non-Photorealistic Rendering)
2.2 單張靜態影像卡通化效果(Image Cartoonization)
2.3 連續影像的卡通化效果 (Rotoscoping and Video Tooning) 第三章 卡通化肖像轉換流程
3.1 前處理 (Preprocessing)
3.2 圖像變形法(Image Morphing)
3.3 轉描法(Rotoscoping)
3.4 臉部動畫參數表情產生機制(Expression Generation by FAP)
3.5 向量化結果影像輸出格式(Vector Image Exporting)
第四章 以三角網格為基礎的圖像變形機制
4.1 三角網格產生方法(Triangular Mesh Creation)
4.2 質心座標轉換(Barycentric Coordinates)
4.3 以形狀比對為基礎的排序與混合藝術風格生成(Shape Matching Driven Polymorph and Dataset ordering)
第五章 轉描法及降色原理
5.1 邊緣偵測(Edge Detection)
5.2 Mean Shift協助內容分割(Segmentation by Mean Shift)
5.3 降色與影像內容抽象化(Color Quantization and Abstraction)
5.4 以直方圖規格化輔助色彩抽象化(Histogram Specification)
第六章 多種表情的生成
6.1 應用於二維影像的臉部動畫參數(2D Scenario FAP Set )
6.2 臉部動作元件動作定義(Facial Component Action Definition)
6.3 情緒表示及原型表情設定檔(Archetypal Expression Profile)
第七章 結論與未來研究方向
7.1 結論
7.2 未來研究方向
參考文獻
附錄
zh_TW
dc.format.extent 44407 bytes-
dc.format.extent 44620 bytes-
dc.format.extent 71444 bytes-
dc.format.extent 55229 bytes-
dc.format.extent 195783 bytes-
dc.format.extent 426857 bytes-
dc.format.extent 761174 bytes-
dc.format.extent 410605 bytes-
dc.format.extent 684563 bytes-
dc.format.extent 651996 bytes-
dc.format.extent 805354 bytes-
dc.format.extent 93589 bytes-
dc.format.extent 53560 bytes-
dc.format.extent 58480 bytes-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.format.mimetype application/pdf-
dc.language.iso en_US-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0927530022en_US
dc.subject (關鍵詞) 影像內容分割zh_TW
dc.subject (關鍵詞) 圖像變形zh_TW
dc.subject (關鍵詞) 臉部動畫參數zh_TW
dc.subject (關鍵詞) 人臉特徵分析zh_TW
dc.subject (關鍵詞) Image Content Segmentationen_US
dc.subject (關鍵詞) Image Warping and Morphingen_US
dc.subject (關鍵詞) Facial Animation Parametersen_US
dc.subject (關鍵詞) Facial Features Analysisen_US
dc.title (題名) 基於形態轉換的多種表情卡通肖像zh_TW
dc.title (題名) Automatic generation of caricatures with multiple expressions using transformative approachen_US
dc.type (資料類型) thesisen
dc.relation.reference (參考文獻) [1] On-line Paper Doll Flash Game, MyScene.comzh_TW
dc.relation.reference (參考文獻) [2] “描邊式圖像卡通轉換系統之研發”,工業技術研究院分包學術機構計畫,主持人:廖文宏,96年zh_TW
dc.relation.reference (參考文獻) [3] S. Yamamoto, X. Mao and A. Imamiya, “Colored pencil filter with custom colors”, Proc. of the Pacific Conference on Computer Graphics and Applications, p.329- 338, 2004zh_TW
dc.relation.reference (參考文獻) [4] RotoScoping, http://en.wikipedia.org/wiki/Rotoscopingzh_TW
dc.relation.reference (參考文獻) [5] J. Puzicha, M. Held, J. Ketterer, J. M. Buhmann, and D. Fellner, “On Spatial Quantization of Color Images”, Technical Report IAI-TR-98-1, University of Bonn. 1998.zh_TW
dc.relation.reference (參考文獻) [6] P. Chiang, “Caricature Generation by Analyzing Facial Features”, Master’s thesis, NCCU, Taiwan, 2004zh_TW
dc.relation.reference (參考文獻) [7] J. Ruppert,, “A Delaunay Refinement Algorithm for Quality 2-Dimensional Mesh Generation”, Journal of Algorithms, Vol.18, No.3, p548-585, 1995.zh_TW
dc.relation.reference (參考文獻) [8] Z. Y. Wu, S. Zhang, L. H. Cai, and H. M. Meng, “Real-time Synthesis of Chinese Visual Speech and Facial Expressions using MPEG-4 FAP Features in a Three-dimensional Avatar”, Proc. Int. Conf. on Spoken Language Processing, p.1802-1805, 2006zh_TW
dc.relation.reference (參考文獻) [9] M. B. Stegmann, “The AAM-API: An Open Source Active Appearance Model Implementation”, Proc. of Medical Image Computing and Computer-Assisted Intervention, p.951-952, 2003zh_TW
dc.relation.reference (參考文獻) [10] AAM-API, C++ implementation of the Active Appearance Model framework http://www2.imm.dtu.dk/~aam/aamapi/zh_TW
dc.relation.reference (參考文獻) [11] A. Raouzaiou, N. Tsapatsoulis, K. Karpouzis, and S. Kollias, “Parameterized Facial Expression. Synthesis Based on MPEG-4.”, EURASIP Journal on Applied Signal Processing, Vol. 2002, No.10, p.1021-1038, 2002zh_TW
dc.relation.reference (參考文獻) [12] L. Malatesta, A. Raouzaiou, K. Karpouzis, and S. Kollias, “MPEG-4 Facial Expression Synthesis based on Appraisal Theory.”, 3rd IFIP conference in Artificial Intelligence Applications and Innovatios, 2006zh_TW
dc.relation.reference (參考文獻) [13] R. Hsu, and A. K. Jain, “Generating Discriminating Cartoon Faces Using Interacting Snakes”, IEEE Transactions on Pattern Analysis and Machine Intelligent, vol.25, p.1388 -1398, 2003zh_TW
dc.relation.reference (參考文獻) [14] D. Decarlo, and A. Santella, “Stylization and Abstraction of Photographs”, Proc.of SIGGRAPH 2002, p.769-776, 2002zh_TW
dc.relation.reference (參考文獻) [15] J. Wang, Y. Xu, H. Shum and M. Cohen, “Video Tooning”, Proc. of SIGGRAPH 2004, Vol. 23, No. 3, p.574-583, 2004zh_TW
dc.relation.reference (參考文獻) [16] H. Chen, Z. Liu, C. Rose, Y. Xu, H. Shum and D. Salesin, “Example-based Composite Sketching of Human Portraits”, Proc. of the 3rd International Symposium on Non-photorealistic Animation and Rendering, p.95-153, 2004zh_TW
dc.relation.reference (參考文獻) [17] A. Sacco, “Imitating A Scanner Darkly”, An Adobe Illustrator Tutorial, http://www.illustratortechniques.com/imitating-a-scanner-darkly.htmlzh_TW
dc.relation.reference (參考文獻) [18] S. Patterson, “Combining Reality With A Rotoscope-Style Painting”, An Adobe PhotoShop Tutorial, Photoshop Essentials.com http://www.photoshopessentials.com/photo-effects/rotoscope/zh_TW
dc.relation.reference (參考文獻) [19] J. Wang, B. Thiesson, Y. Xu, and M. F. Cohen, “Image and Video Segmentation by Anisotropic Kernel Mean Shift”, Proc. of European Conference on Computer Vision, 2004zh_TW
dc.relation.reference (參考文獻) [20] D. Comaniciu, and P. Meer, “Mean Shift: A Robust Approach toward Feature Space Analysis”, IEEE Trans. Pattern Analysis and Machine Intelligence, Vol.24, No.5, p.603-619, 2002zh_TW
dc.relation.reference (參考文獻) [21] D. Comaniciu, V. Ramesh, and P. Meer, “Real-time Tracking of Non-rigid Object Using Mean Shift”, Proc. of IEEE conference on Computer Vision and Pattern Recognition, p.142-151, 2000zh_TW
dc.relation.reference (參考文獻) [22] L. Guibas, and J. Stolfi, “Primitives for the Manipulation of General Subdivisions and the Computation of Voronoi Diagrams”, ACM Transactions on Graphics, Vol.4, No.2, p.74-123, 1985zh_TW
dc.relation.reference (參考文獻) [23] AutoTrace: converts bitmap to vector graphics, http://autotrace.sourceforge.net/zh_TW
dc.relation.reference (參考文獻) [24] J. R. Shewchuk, “Triangle: Engineering a 2D Quality Mesh Generator and Delaunay Triangulator”, Applied Computational Geometry: Towards Geometric Engineering, Vol. 1148 of Lecture Notes in Computer Science, p.203-222, 1996.zh_TW
dc.relation.reference (參考文獻) [25] R. C. Gonzalez, and R. E. Woods, “Chap3 Image Enhancement in Spatial Domain”, Digital Image Processing 2nd Edition, Prentice Hall, p.75-136, 2001zh_TW
dc.relation.reference (參考文獻) [26] P. Meer, and B. Georgescu, “Edge detection with embedded confidence.”, IEEE Trans. On Pattern Analysis and Machine Intelligence, Vol. 23, p.1351-1365, 2001zh_TW
dc.relation.reference (參考文獻) [27] P. Heckbert, “Color Image Quantization for Frame Buffer Display”, Proc. of the 9th annual conference on Computer graphics and interactive techniques, vol.16, no.3, p.297-307, 1982zh_TW
dc.relation.reference (參考文獻) [28] Z. Xiang and G. Joy, “Color Image Quantization by Agglomerative Clustering”, IEEE Computer Graphics and Applications, vol.14, no.3, p.44-48, 1994zh_TW
dc.relation.reference (參考文獻) [29] D. Clark, “Color Quantization using Octrees”, Dr. Dobb’s Journal, p.54-57 and 102-104, 1996zh_TW
dc.relation.reference (參考文獻) [30] R. Ulichney, “Dithering with Blue Noise”, Proc. of IEEE, vol.76, p.56-79, 1988zh_TW
dc.relation.reference (參考文獻) [31] R. Floyd and L. Steinberg, “An Adaptive Algorithm for Spatial Greyscale”, Proc. of Society for Information Display, vol. 17, no. 2, Wiley, 1976zh_TW
dc.relation.reference (參考文獻) [32] S. Lee, G. Wolberg, and S. Y. Shin, “Polymorph: Morphing Among Multiple Images”, IEEE Computer Graphics and Applications,Vol.18, p.58-71,1998zh_TW
dc.relation.reference (參考文獻) [33] M. Grundland and N. A. Dodgson, “Color Histogram Specification by Histogram Warping”, Proc. of Society of Photo-Optical Instrumentation Engineers, vol. 5667, p.610-621, 2005zh_TW
dc.relation.reference (參考文獻) [34] K. Perlin, Responsive Face Demo, http://mrl.nyu.edu/~perlin/facedemo/zh_TW
dc.relation.reference (參考文獻) [35] K. Balci, “Xface: MPEG-4 Based Open Source Toolkit for 3d Facial Animation”, Proc. of Advanced Visual Interfaces, p.399-204, 2004zh_TW
dc.relation.reference (參考文獻) [36] S. Garchery, A. Egges, and N. Magnenat-Thalmann, “Fast Facial Animation Design for Emotional Virtual Humans” Proc. of Measuring Behaviour, 2005zh_TW
dc.relation.reference (參考文獻) [37] P. Ekman, “Facial Expression and Emotion”, Am Psychologist, Vol.48, p.384-392, 1993zh_TW
dc.relation.reference (參考文獻) [38] A. Bevilacqua, and P. Azzari, “A High Performance Exact Histogram Specification Algorithm”, 14th International Conference on Image Analysis and Processing (ICIAP 2007) , p. 623-628, 2007zh_TW