影像分類的目的是為了建立影像的索引資料，但傳統方式需要耗費龐大的人力與時間，來為影像或影片註解。本論文使用整體式類神經網路取代人工分類，以投票方式讓影像的分類可以自動化。整體式類神經網路結合數個類神經網路，整合各個模型的辨識結果，因此可修正單一類神經網路之辨識錯誤。本論文將動態影像與靜態影像採用相同的方法做分類，但動態影片先透過場景的切割與關鍵畫面的擷取，再以關鍵畫面做為分類依據。而每張影像在辨識階段僅需數秒鐘即可完成辨認，大幅縮短了註解所需的時間。

Content-based image retrieval is the research that creates indices of images. Early studies usually extract low-level image features as indices. Image classification is one of various salient approaches to mine semantic information in image and video. This paper presents a classification approach that adopts classified results as indices for the retrieval of images and videos. After video segmentation and key frame extraction, a lot of features are extracted for each shot. These features include color and texture features. A classification framework using backpropagation neural networks as multiple binary classifiers is applied to classify images. 100 of 2000 images and 1029 video shots are selected randomly and used to train the neural networks, and all of the images and video shots are experimented to testify the feasibility of our method. Images are classified into four semantic classes. The best experimental results can achieve high recognition rate at 95.12%, which indicates that our approach can produce high-level indices with high reliability.

中文摘要 i
英文摘要 ii
誌謝 iii
目錄 iv
表目錄 vi
圖目錄 vii
第一章 導論 1
1.1 研究動機 1
1.2 文獻回顧 1
1.3 研究目的 4
第二章 系統與論文架構 6
2.1 特徵的萃取 7
2.2 影像分類 8
2.3 論文架構 9
第三章 特徵萃取 10
3.1 膚色特徵 11
3.2 頻率特徵 14
3.3 邊緣特徵 19
第四章 類別分析 22
4.1 室內(Indoor) 22
4.2特寫(Close-up) 24
4.3建築(Building) 26
4.4風景(Landscape) 28
第五章 整體式類神經網路分類 31
5.1倒傳遞類神經網路 31
5.2 整體式類神經網路之架構 35
第六章 實驗結果 39
6.1 實驗環境與資料 39
6.2 實驗步驟 41
6.3 實驗結果 43
第七章 結論 51
參考文獻 52

[1] S. F. Chang, W. Chen, H. J. Meng, H. Sundaram, and D. Zhong, “VideoQ: an automated content-based video search system using visual cues,” Proceedings of ACM Multimedia, ACM, New York, USA, pp. 313-24, Nov. 1997.
[Online] http://www.ctr.Columbia.edu/videoq
[2] M. G. Christel, H. D. Wactlar, and A. G. Hauptmann, “Informedia digital video library accomplishments and future directions,” Carnegie Mellon University, Oct. 1999.
[Online] http://www.informedia.cs.cmu.edu
[3] N. Haering, R. J. Qian, and M. I. Sezan, “A semantic event-detection approach and its application to detecting hunts in wildlife video,” IEEE Transactions on Circuits and system for video technology, Vol. 10, No. 6, pp. 857-868, Sept. 2000.
[4] G. Sudhir, J. C. M. Lee, and A. K. Jain, “Automatic classification of tennis video for high-level content-based retrieval,” IEEE International Workshop on Content-Based Access of Image and Video Database, pp. 81-90, 1998.
[5] H. Zhang, Y. Gong, S. W. Smoliar and S. Y. Tan, “A computational approach to semantic event detection,” Computer Vision and pattern Recognition, Vol. 1, pp. 23-25, June 1999.
[6] H. Y. Lee, H. K. Lee and Y.H. Ha, “Spatial color descriptor for image retrieval and video segmentation,” IEEE Transactions on Multimedia, Vol. 5, No. 3, pp.358-367, Sept. 2003.
[7] A. M. Ferman, A. M. Tekalp, and R. Mehrotra, “Robust color histogram descriptors for video segment retrieval and identification,” IEEE Transactions on Image Processing, Vol. 11, No. 5, pp. 497-508, May 2002.
[8] A. Divakaran, A. Vetro, K. Asai, and H. Nishikawa, “Video browsing system based on compressed domain feature extraction,” IEEE Transactions on Consumer Electronics, Vol. 46, Issue 3, pp. 637-644, Aug. 2000.
[9] J. Fan, A. K. Elmagarmid, X. Zhu, W. G. Aref, L. Wu, “ClassView : hierarchical video shot classification, indexing, and accessing,” IEEE Transactions on Multimedia, Vol. 6 , Issue 1 , pp. 70-86, Feb. 2004.
[10] A. D. Doulamis, N. D. Doulamis and S. D. Kollias, “Relevance feedback for content-based retrieval in video databases : a neural network approach,” IEEE International Conference on Proceedings of ICECS ''99, Vol. 3, pp 1745-1748, Sept. 1999.
[11] A. D. Doulamis, N. D. Doulamis and S. D. Kollias, ”A neural network based scheme for unsupervised video object segmentation,” IEEE International Conference on Image Processing, Vol. 2 , pp. 632-636, Oct. 1998.
[12] L. Bruzzone, M. Marconcini, U. Wegmuller and A. Wiesmann, “An advanced system for the automatic classification of multitemporal SAR images,” IEEE Transaction on Geoscience and Remote sensing, Vol. 42, No 6, pp. 1321-1334, June 2004.
[13] C.S. Pattichis and A.G. Constantinides, “Medical imaging with neural networks,” Neural Networks for Signal Processing [1994] IV. Proceedings of the 1994 IEEE Workshop , pp. 431-440, Sept. 1994.
[14] C. H. Chen and Z. Xiaohui, “Using neural networks for fiber content analysis,” International Joint Conference on Neural Networks, vol. 6, pp. 3913-3916, July 1999.
[15] D.Z Badal, “Neural network based object recognition in images,” IEEE International Conference on Neural Networks, vol. 3, pp. 1283-1288, Mar. 1993.
[16] Y. Jianming, Y. Suematsu and S. Shimizu, “An application of neural networks for recognition of traffic marks in the images of wide angle vision sensors with high distortion lens,” 6th IEEE International Workshop on Robot and Human Communication, pp.176-181, Sept. 1997.
[17] B. Sridhar, A. Phatak and G. Chatterji, “Texture-based segmentation of natural images using neural networks,” IEEE International Conference on Systems, Man and Cybernetics, vol. 1, pp. 727-732, Oct. 1992.
[18] Y. K. Wang, and W. C. Shih, “ Semantics classification for video retrieval,” Third International Workshop on Content-Based Multimedia Indexing, Rennes, France, Sept. 2003.
[19] S. L. Phung, A. Bouzerdoum, and D. Chai, “A novel skin color model in YCbCr color space and its application to human face detection,” IEEE International Conference on Image Processing, Vol. 1, pp. 289-292, Sept. 2002.
[20] D. Chai, and A. Bouzerdoum, “A bayesian approach to skin color classification in YCbCr color space,” IEEE Proceedings on TENCON 2000, Vol. 2, pp. 421-424, Sept. 2000.
[21] J. C. Terrillon, M. N. Shirazi, H. Fukamanchi, and S. Akamatsu, “Comparative performance of different skin chrominance models and chrominance spaces for the automatic detection of human faces in color images,” Fourth IEEE International Conference on Automatic Face and Gesture Recognition, pp. 54-61, March 2000.
[22] S. L. Phung, D. Chai, and A. Bouzerdoum, “A universal and robust human skin color model using neural networks,” IEEE International Joint Conference on Neural Networks, Vol. 4 , pp. 2844-2849, July 2001.
[23] G. Giacinto and F. Roli, “Design of effective neural network ensembles for image classification,” Image and Vision Computing Journal, Vol. 19, pp. 699-707, 2001.
[24] R. Battiti, and A. M. Colla, “Democracy in neural nets: voting schemes for classification,” Neural Networks, Vol. 7, Issue 4, pp. 691-707, 1994.
[25] T. K. Ho, J. J. Hull, and S. N. Srihari, “descision combination in multiple classifier system,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 18, pp. 66-75, 1994.