臺灣博碩士論文加值系統

在這篇論文中，我們提出了一個使用啟發式最佳化演算法-自適應式和絃搜尋演算法(SAHS)的電影類型分類系統來各別選取出與電影類型有較佳關聯度之特徵。接下來，個別的一對一支援向量機(SVM)的模型使用這些被選出的特徵值來建立，再使用多數決投票機制來決定預測之電影類型。我們從每一部預告片中，總共取出277維聲音及影像的特徵，然而，不超過25個特徵被取出來辨識兩兩預告片的類型。根據實驗的結果，平均可以達到91.9%的準確率，這些被計算出來較為珍貴的特徵，可以使用來幫助我們得到更好的電影類型分類的結果。

In this paper, we propose a movie genre classification system using a meta-heuristic optimization algorithm called Self-Adaptive Harmony Search (i.e., SAHS) to select local features for corresponding movie genres. Then, each one-against-one Support Vector Machine (i.e., SVM) classifier is fed with the corresponding local feature set and the majority voting method is used to determine the prediction of each movie. Totally, we extract 277 features from each movie trailer, including visual and audio features. However, no more than 25 features are used to discriminate each pair of movie genres. The experimental results show that the overall accuracy reaches 91.9%, and this demonstrates more precise features can be selected for each pair of genres to get better classification results.

目錄
中文摘要 i
英文摘要 ii
誌謝 iii
目錄 iv
表目錄 v
圖目錄 vi
一、緒論 1
二、 相關研究 2
三、 系統概述 3
3.1 視覺特徵 4
3.1.1 分鏡邊界偵測 4
3.1.2 鍵框選取 5
3.1.3時間性特徵 5
3.1.4 空間性特徵 6
3.2音訊特徵 6
3.2.1 強度 6
3.2.2 音色 7
3.2.3節奏 8
四、使用SAHS做特徵選取 9
4.1和弦搜尋演算法 9
4.1.1 一般和弦搜尋演算法 9
4.1.2自我調適和弦搜尋演算法 10
4.2 相對關聯 11
五、實驗結果 13
5.1使用特徵選取的分類結果 13
5.1.1 只使用視覺特徵 14
5.1.2 只使用音訊特徵 16
5.1.3 使用視覺與音訊特徵 18
5.2 與所有方法比較 20
六、結論 22
參考文獻 23

[1]A. Baskar, M. PrabuKumar, and S. Sathishkumar, “Improved adaptive skip algorithm for video shot boundary detection,” Proc. the International Conference on Signal Processing, Communications and Networking, pp. 492-496, 2007.
[2]R. B. Bhatt, P. Krishnamoorthy, and S. Kumar, “Efficient general genre video abstraction scheme for embedded devices using pure audio cues,” Proc. the 7th International Conference on ICT and Knowledge Engineering, pp. 63-67, 2009.
[3]Chin-Chung Chang and Chih-Jen Lin, “LIBSVM: a library for support vector machines,” software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm.
[4]Shih-Fu Chang, T. Sikora, and A. Puri, “Overview of the MPEG-7 standard,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 11, No. 6, pp. 688-695, 2001.
[5]M. Deriche, “Feature selection using ant colony optimization,” Proc. the 6th International Multi-conference on Systems, Signals, and Devices, pp. 1-4, 2009.
[6]Ren Diao and Qiang Shen, “Two new approaches to feature selection with harmony search,” Proc. the IEEE International Conference on Fuzzy Systems, pp. 1-7, 2010.
[7]Z. W. Geem, J. H. Kim, and G. V. Loganathan, “A new heuristic optimization algorithm: harmony search,” Simulation, Vol. 76, No. 2, pp. 60-68, 2001.
[8]M. A. Hall and L. A. Smith, “Practical feature subset selection for machine learning,” Proc. the 21st Australian Computer Science Conference, pp. 181-191, 1998.
[9]H. Y. Huang, W. S. Shih, and W. H. Hsu, “Movie classification using visual effect features,” Proc. the IEEE Workshop on Signal Processing Systems, pp. 295-300, 2007.
[10]Yin-Fu Huang and Chia-Ming Wang, “Self-adaptive harmony search algorithm for optimization,” Expert Systems with Applications, Vol. 37, No. 4, pp. 2826-2837, 2010.
[11]S. K. Jain and R. S. Jadon, “Movies genres classifier using neural network,” Proc. the 24th International Symposium on Computer and Information Sciences, pp. 575-580, 2009.
[12]X. Jin and R. Bie, “Random forest and PCA for self-organizing maps based automatic music genre discrimination,” Proc. the International Conference on Data Mining, pp. 414-417, 2006.
[13]P. L. Lanzi, “Fast feature selection with genetic algorithms: a filter approach,” Proc. the International Conference on Evolutionary Computation, pp. 537-540, 1997.
[14]N. Levinson, “The Wiener RMS error criterion in filter design and prediction,” J. Math. Phys., Vol. 25, pp. 261-278, 1947.
[15]R. Lienhart, “Comparison of automatic shot boundary detection algorithms,” Proc. Storage and Retrieval for Image and Video Databases VII, SPIE, Vol. 3656, pp. 1-12, 1998.
[16]J. M. Martinez, R. Koenen, and F. Pereira, “MPEG-7: the generic multimedia content description standard, part 1,” IEEE Multimedia, Vol. 9, No. 2, pp. 78-87, 2002.
[17]J. M. Martinez, “MPEG-7 overview (version 10),” ISO/IEC JTC1/SC29/WG11 N6828, 2004.
[18]D. McEnnis, C. McKay, I. Fujinaga, and P. Depalle, “jAudio: a feature extraction library,” Proc. the 6th International Conference on Music Information Retrieval, pp. 600-603, 2005.
[19]Y. Panagakis and C. Kotropoulos, “Music genre classification via topology preserving non-negative tensor factorization and sparse representations,” Proc. the 35th IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 249-252, 2010.
[20]Y. Panagakis, C. Kotropoulos, and G. R. Arce, “Non-negative multilinear principal component analysis of auditory temporal modulations for music genre classification,” IEEE Transactions on Audio, Speech, and Language Processing, Vol. 18, No. 3, pp. 576-588, 2010.
[21]Z. Rasheed, Y. Sheikn, and M. Shah, “On the use of computable features for film classification,” IEEE Transactions on Circuits and System for Video Technology, Vol. 15, No. 1, pp. 52-64, 2005.
[22]G. Silviu, Information Theory with Applications, McGraw-Hill, 1977.
[23]H. D. Wactlar, “The challenges of continuous capture, contemporaneous analysis, and customized summarization of video content,” Proc. the Workshop on Defining a Motion Imagery Research and Development Program, pp. 1-9, 2001.
[24]R. Weber, H. J. Schek, and S. Blott, “A quantitative analysis and performance study for similarity-search methods in high-dimensional spaces,” Proc. the 24th International Conference on Very Large Data Bases, pp. 194-205, 1998.
[25]Apple iTunes Movie Trailers Website at http://trailers.apple.com/trailers/.
[26]Internet Movie Database (IMDb) at http://www.imdb.com/.
[27]The Compact Edition of the Oxford English Dictionary II, Oxford University Press, p. 2537, 1971.