臺灣博碩士論文加值系統

摘 要

人性化電子相簿

林宏隆

數位相機已經在日常生活中越來越普遍，伴隨而來的即是數位相片管理方式的問題。當日積月累收集到龐大數量的數位相片時，相片若是沒有經過有意義的分類而加以儲存，日後若想要從這一堆雜亂無序的數位相片中，找出一張想要回顧的相片，必定要花費一番功夫才有可能找到。若有一個能幫助使用者將一堆數位相片分門別類的系統，而且分類的結果可以讓使用者在短時間內找到目標相片，則使用者在數位相片的尋找上，將會有相當好的效率。
人性化電子相簿即是一個將一堆數位相片做好分類的系統。首先分析數位相片的內容，之後再進行相片之間的計算，將差距最小的相片聚集在同一個分類中，聚集的結果也呈現讓使用者易於瀏覽的界面。經過實際測試發現，系統對於一千多張數位相片進行資料分析之後，一千多張相片進行合併分類所花費的時間僅控制在7秒鐘左右，算是很不錯的表現。分類之後使用者輸入一張相似的數位相片並由系統進行尋找，系統即能找出適合該張相片的分類資料夾，若使用者自行尋找也能快速地從相簿中找出目標相片，顯示人性化電子相簿有相當好的分類效果。

ABSTRACT

Personal Digital Photo Album

by

Hung-Lung Lin

Digital cameras have been more and more popular in daily life. The problem is the managing of digital photos. If you do not use meaning ways to cluster and save those photos, then you will not search the photo you want in other days. It will be a great help that if there is a system which can help users cluster those photos, and the results of clustering can help users search photos they want in a short time.
Personal digital photo album is a system which can cluster photos. At first, it will analyze the content of digital photos. After calculating photos’ content, it will aggregate similar photos into the same cluster. Of course, the results of aggregating show the convenience of users browsing interface. Approved by actual tests for the analyzing of more than one thousand photos, we find that the system only uses seven seconds to combine and cluster. It really did a good job. After clustering users can input one similar photo, and the system shows the appropriate cluster to the photo. Users can quickly get the photos they want in the album too. It shows this personal digital photo album has a quite well effect with clustering.

附圖目錄 viii
第一章　導論 1
第一節 研究動機 1
第二節 相關研究 3
第三節 研究方向及成果 5
第四節 章節安排 6
第二章　背景知識 7
第一節 S. Liapis and G. Tziritas的分類方法 7
第二節 S. J. Yang, K. S. Seo, and Y. M. Ro的分類方法 8
第三節 J. C. Platt的研究方法 9
第四節 R、G、B檔案格式 13
第五節 金字塔式組織及瀏覽方式 16
第六節 MPEG 7 18
第三章 實驗方法 20
第一節 正規化JPG圖像檔案 20
第二節 讀取圖像檔案並進行資料運算 23
第三節 資料儲存方式 25
第四節 合併數位相片 27
第五節 數位相片的尋找 33
第六節 實驗系統環境 33
第四章 實驗結果 36
第一節 以十張左右的數位相片作分析 36
第二節 以五十張左右的數位相片作分析 41
第三節 以一百張左右的數位相片作分析 50
第四節 以一千張左右的數位相片作分析 60
第五節 實驗數據總結整理 67
第五章 結論與展望 72
第一節 總結與討論 72
第二節 展望 74
參考文獻 75

[1] J. Annesley, J. Orwell, and J. P. Renno, “Evaluation of MPEG 7 color descriptors for visual surveillance retrieval”, Proceedings Second Joint IEEE International Workshop on VS-PETS Beijing, pp. 105-112, 15-16 Oct. 2005.
[2] R. Chellapa, C. Wilson, and S. Sirohey, “Human and machine recognition of faces: a survey”, Proceeding of IEEE, vol. 83, pp. 705-740, May 1995.
[3] J. Chen, A. Bouman, and J. C. Dalton, “Similarity pyramids for browsing and organization of large image databases”, Proceedings of SPIE/IS&T Conference on Human Vision and Electronic Imaging III, vol. 3299, pp. 563-575, 1998.
[4] T. T. A. Combs and B. B. Bederson, “Does zooming improve image browsing?”, In Proceedings of ACM Digital Libraries, pages 130–137, 1999.
[5] M. Cooper, J. Foote, A. Girgensohn, and L. Wilcox, “Temporal event clustering for digital photo collections”, ACM TOMCCAP 2005, vol. 1, no. 3, pp. 269-288, August 2005.
[6] I. J. Cox, M. L. Miller, S. M. Omohundro, and P. N. Yianilos, “PicHunter: Bayesian relevance feedback for image retrieval”, In Proceedings of ICPR, pp. 361-369, 1996.
[7] M. Flicker, H. Sawhney, W. Niblack, J. Ashley, etc., “Query by image and video content: the QBIC system”, IEEE Computer, vol. 28, no. 9, pp. 23-32, Sept. 1995.
[8] A. Graham, H. Garcia-Molina, A. Paepcke, and T. Winograd, “Time as essence for photo browsing through personal digital libraries”, Proceedings of JCDL 2002, pp. 326-335, July 2002.
[9] V. N. Gudivada and V. V. Raghavan, “Content based image retrieval systems”, IEEE Computer, vol. 28, issue 9, Sept. 1995.
[10] A. Gupta and R. Jain, “Visual information retrieval”, Communication of the ACM, vol. 40, no. 5, pp. 70-79, May 1997.
[11] H. Kang and B. Shneiderman, “Visualization methods for personal photo collections: Browsing and searching in the PhotoFinder”, In Proceedings of IEEE Intl. Conf. on Multimedia and Expo, 2000.
[12] S. Liapis and G. Tziritas, “Color and texture image retrieval using chromaticity histograms and wavelet frames”, IEEE Trans. Multimedia, vol. 6, no. 5, pp. 676-686, Oct. 2004.
[13] J. H. Lim, Q. Tian, and P. Mulhem, “Home photo content modeling for personalized event-based retrieval”, IEEE Trans. Multimedia, vol. 10, no. 4, pp. 24-37, 2003.
[14] A. Loui and A. Savakis, ”Automated event clustering and quality screening of consumer pictures for digital albuming”, IEEE Trans. Multimedia, pp. 390-402, Sept. 2003.
[15] B. Manjunath, J. –R. Ohm, V. Vasudevan, and A. Yamada, “Color and texture descriptors”, IEEE Trans. Circuits Syst. Video Technol., vol. 11, pp. 703-715, June 2001.
[16] M. A. Mottaleb and L. Chen, “Content-based photo album management using faces' arrangement”, ICME 2004, vol 3, pp. 2071-2074, 27-30 June 2004.
[17] V. Ogle and M. Stonebraker, “Chabot: retrieval from a relational database of images”, IEEE Computer, vol. 28, no. 9, pp. 40-48, Sept. 1995.
[18] S. M. Omohundro, “Best-first model merging for dynamic learning and recognition”, Advances in Neural Information Processing Systems, vol. 4, pp. 958-969, 1992.
[19] A. Pentland, W. Picard, and S. Sclaroff, “Photobook: content-based manipulation of image databases”, Int. J. Computer Vision, vol.18, no. 3, pp. 233-254, 1996.
[20] J. C. Platt, “AutoAlbum: Clustering digital photographs using probabilistic model merging”, Proceedings of IEEE Workshop on Content-Based Access of Image and Video Libraries, pp. 96-100, 2000.

[21] J. C. Platt, M. Czerwinski, and B. A. Field, “PhotoTOC: automatic clustering for browsing personal photographs”, In Proceedings of Fourth IEEE Pacific Rim Conference, vol. 1, pp. 6-10, 2003.
[22] G. Qiu, “Indexing chromatic and achromatic patterns for content-based image retrieval”, Pattern Recognition, vol. 35, issue 8, pp. 1675-1686, August 2002.
[23] G. Qiu, “Appearance indexing”, In Proceedings of ICASSP 2003, vol. III, pp. 597-600, April 2003.
[24] G. Qiu, “Image and feature co-clustering”, ICPR 2004, vol. 4, pp. 991-994, 2004.
[25] L. R. Rabiner, “A tutorial on hidden markov models and selected applications in speech recognition”, In Proceedings of the IEEE, vol. 77, no. 2, pp. 257-286, 1989.
[26] K. Rodden. “How do people organize their photographs?”, Proceedings of BCS IRSG 21st Annual Colloquium on Information Retrieval Research, April 1999.
[27] K. Rodden, W. Basalaj, D. Sinclair, and K. Wood, “Does organization by similarity assist image browsing?”, In Proceedings of ACM CHI 2001, pp. 190-197, 2001.
[28] Y. Rui, T. S. Huang, and S. F. Chang, “Image retrieval: current techniques, present directions, and open issues”, J. Visual Communications and Image Representation, vol. 10, pp. 39-62, 1999.
[29] T. Sikora, “The MPEG-7 visual standard for content description—an overview”, IEEE Trans. on Circuits and Systems for Video Technology, vol. 11, no. 6, pp. 696-702, June 2001.
[30] A. Stolcke and S. Omohundro, “Hidden markov model induction by bayesian model merging”, Advances in Neural Information Processing Systems, vol. 5, pp. 11-18, 1993.
[31] S. J. Yang, K. S. Seo, and Y. M. Ro, “Automated situation clustering of home photos for digital albuming”, SPIE Electronic Imaging, vol. 5682, pp. 212-223, Jan. 2005.
[32] S. J. Yang, K. S. Seo, and Y. M. Ro, “User-centric digital home photo album”, ISCE 2005, pp. 226-229, 14-16 June 2005.
[33] S. J. Yang, K. S. Seo, and Y. M. Ro, “Person-identity-based clustering for digital photo albuming”, In Proceedings of WIAMIS, 2005.
[34] Google圖片搜尋(2006)。2006年8月22日，取自http://images.google.com.tw
[35] DaubNET: File Formats Collection: BMP. (n. d.). Retrieved August 22, 2006, from http://www.daubnet.com/formats/BMP.html
[36] efg’s Chromaticity Diagrams Lab Report. (n. d.). Retrieved August 22, 2006, from http://www.efg2.com/Lab/Graphics/Colors/Chromaticity.htm