# 臺灣博碩士論文加值系統

(3.90.139.113) 您好！臺灣時間：2022/01/16 19:09

:::

### 詳目顯示

:

• 被引用:1
• 點閱:455
• 評分:
• 下載:92
• 書目收藏:0
 在這篇論文中，我們將會提出一個以影片內容為基底的影片檢索的方法，且這個方法不需對每段影片去找出具有代表性的影像。和那些方法不同的地方在於，我們的方法能將整段影片的資訊都使用到。我們所提出的方法是利用”主要的色彩矩量”和“主要的顏色”這兩個觀念去對每段影片擷取特徵。要從一段影片中取出”主要的色彩矩量”，首先將這段影片中的每一張影像分割成許多塊，然後對每一塊計算它的色彩矩量，再以這些矩量的值為基準將所有的塊分成很多群，每一群的中心向量就是這段影片的一個主要色彩矩量。要從一段影片中取出它的主要顏色，就是將這段影片中的每一點依據它們顏色的值去做分群，每一群裡面所有顏色的平均值就視為這段影片中的一個主要顏色。在對每段影片擷取出它們的特徵向量後，我們將會對主要的色彩矩量和主要的顏色分別提出一個計算兩段不同影片之間相似度的方法。然而，因為沒有一種方法是適合所有種類的影片，我們將會提出一個演算法，它能夠依據使用者所給的回應，自動的找出一個最適合的方法。
 In this paper, a content-based video retrieval method without using key-frame will be proposed. Unlike the key-frame based approach, the proposed method uses the whole information of a shot instead of selecting several key-frames to represent a shot. This method is based on the concept of the primitives of color moments and the dominant colors to extract features. To extract the primitives of color moments, first each frame in a shot is divided into several blocks. Then, the color moments of all blocks are extracted and clustered into several classes. The mean moments of each class are considered as a primitive of the shot. To extract the dominant colors, all pixel’s color in a shot are clustered into several classes, and the center of the colors in each class is treat as a dominant color. After extracting the feature vectors for each shot, we will propose two measures to compute the similarity between two different shots using primitives of color moments and dominant colors as features, respectively. Furthermore, since there is no feature that is proper for all kinds of shots, a relevance feedback algorithm is also provided to automatically determine the best method according to the user’s response.
 CHAPTER 1 INTRODUCTION.......................................1 1.1 Motivation.............................................1 1.2 Introduction of shot change detection..................2 1.3 Review of key-frame extraction methods.................4 1.4 Review of the features for content-based video/image retrieval..............................................7 1.5 The proposed method....................................8 CHAPER 2 THE PROPOSED METHOD................................10 2.1 Features extraction of video shots....................12 2.1.1 Primitives of color moment extraction...............12 2.1.2 Dominant color extraction...........................16 2.2 Video retrieval.......................................18 2.2.1 Similarity measure for primitives of color moments..18 2.2.2 Similarity measure for dominant colors..............20 2.2.3 Combination of primitives and dominant colors.......20 2.3 Relevance Feedback Algorithm..........................21 CHAPER 3 EXPERIMENTAL RESULTS...............................23 CHAPER 4 CONCLUSIONS........................................31 REFERENCE...................................................33
 [1] W. Xiong, J. C. M. Lee, and R. H. Ma, “Automatic Video Data Structuring Through Shot Partitioning and Key Frame Selection,” Machine Vision Application, Vol. 10, No. 2, 1997, pp. 51-65.[2] W. Xiong, and J. C. M. Lee, ”Efficient Scene Change Detection and Camera Motion Annotation for Video Classification,” Computer Vision and Image Undersatanding, Vol. 71, No. 2, 1998, pp. 166-181.[3] A. Nagasaka and Y. Tanaka, “Automatic Video Indexing and Full-Video Search for Object Appearances,” Visual Database System II, Elsevier Science Publishers, 1992, pp.113-127[4] K. Otsuji, Y. Tonomura, and Y. Ohba, “Video Browsing Using Brightness Data,” Visual Communications and Image Processing 1991, Bellingham WA: SPIE, vol. 1606, 1991, pp. 980-985.[5] Y. Tonomura, A. Akutsu, Y. Taniguchi, and G. Suzuki, “Structured Video Computing,” IEEE Multimedia, I(3), Fall 1994, pp. 34-43.[6] H. Zhang, A. Kankamhalli, and S. Smoliar, “Automatic Partitioning of Full-Motion Video,” ACM Multimedia System, New York: ACM Press, vol. 1, 1993, pp. 10-28.[7] W. Wolf, "Key Frame Selection By Motion Analysis," Proceedings, ICASSP’96, Vol. 2, 1996. pp. 1228-1231,[8] H. J. Zhang, J. H. Wu, D. Zhong and S. W. Smoliar, “An Integrated System For Content-Based Video Retrieval And Browsing,” Pattern Recognition, 30(4): 1997, pp. 643-658.[9] X. Sum, M. S. Kankanhalli, Y. Zhu and J. Wu, “Content-Based Representative Frame Extraction for Digital Video,” Multimedia Computing and System, 1998. Proceedings. IEEE International Conference on, 1998, pp. 190-193.[10] H. S. Chang, S. Sull and S. U. Lee, “Efficient Video Indexing Scheme for Content-Based Retrieval,” Circuits and Systems for Video Technology, IEEE Transactions on, Vol. 9 Issue: 8, Dec. 1999, pp. 1269-1279.[11] L. Zhao, W. Qi, S. Z. Li, S. Yang and H. J. Zhang, “Key-frame Extraction and Shot Retrieval Using Nearest Feature Line (NFL),” International Workshop on Multimedia Information Retrieval, in conjunction with ACM Multimedia 2000, Los Angeles, USA, 2000.[12] M. Sricker and M. Orengo, “Similarity of Color Images,” Proc. SPIE Storage and Retrieval for Still Image and Video Databases III, San Jose, CA, USA, February 1995, pp. 381-392.[13] Y. Deng, B.S. Manjunath, C. Kenney, M.S. Moore and H. Shin, “An Efficient Color Representation for Image Retrieval,” IEEE Tran. Image Processing, 10, (1), Jan. 2001, pp. 140-147.[14] J. L. Shih and L. H. Chen, “Color Image Retrieval Based On Primary Color Moments”, revised by IEE Proceedings Vision, Image and Signal Processing.[15] N. Akrout, R. Prost and R. Goutte, “Image Compression by Vector Quantization: A Review Focused on Codebook Generation,” Image and Vision Computing, 1994, 12, (10), pp. 627-637.
 電子全文
 國圖紙本論文
 推文當script無法執行時可按︰推文 網路書籤當script無法執行時可按︰網路書籤 推薦當script無法執行時可按︰推薦 評分當script無法執行時可按︰評分 引用網址當script無法執行時可按︰引用網址 轉寄當script無法執行時可按︰轉寄

 1 區域性影像檢索架構之研究

 1 29.張完珠，連鎖總部組織與職掌(下)，流通世界雜誌，第55期，第11頁(1995)。 2 23.張保隆、謝寶煖(1996)，「大學圖書館服務品質評估之研究」，中國圖書館學會會報，第56期，頁51-54。 3 26.陳清祥(民85)，「顧客滿意必須內外兼修」，管理雜誌，85年5月，263期，頁76-78。 4 31.楊錦洲(85)，「品質是競爭的最佳策略」，管理雜誌，2期，頁32-34。 5 39.戴久永(民85)，「品質就是滿足顧客需求?」，管理雜誌，85年11月269期，頁66-67。

 1 以影像內涵之形狀及色彩為基礎的影像檢索系統 2 在彩色文件分析中決定背景以及抽出物件並分類之研究 3 影片文字辨識及影片內容檢索 4 以物體為基礎的影片壓縮技術之研究 5 利用運動強度分析,影片片段辨識及畫面字幕偵測建構視訊影片內容結構之研究 6 以使用記錄分析探索網路使用者檢索興趣之研究 7 影像隱藏學之研究 8 家用機器人視覺系統之相機校正 9 整合家用資訊與服務系統之設計及實作 10 線性多重選擇性背包問題在網頁內容決選之應用 11 MyYouTube：根據影片的評論者與使用者的喜好推薦YouTube影片 12 電視廣告影片影音記憶效果之研究--以台灣衛生棉電視廣告影片為例 13 三度空間腦部結構校準 14 監控系統之研究 15 一個基於傅立葉轉換及小波轉換之紋理分析的研究

 簡易查詢 | 進階查詢 | 熱門排行 | 我的研究室