5.1 結論
本研究提出一個針對投影片切換時的動態效果，將其偵測並分類的完整流程，
能夠將教學影片中自動擷取出動態換頁效果所在位置，並進行分類，最終將所有 的動態換頁效果分為三種類別。
本研究流程共分為兩個主要階段：第一階段是動態換頁效果偵測，由計算每 兩張鄰近影像間的差距，找出含有換頁特效的連續變動畫面所在；第二階段是動 態換頁效果的分類，依照第一階段中偵測的結果，將各段連續變動畫面進行判斷 處理，將其分類到適當的類別。
由實驗結果，可得到以下結論：
(1) 無論投影片為單純或複雜背景，皆能有效偵測並分類出換頁特效。
(2) 採用簡易的特效偵測及分類演算法，卻仍有良好的成效。
(3) 無法正確處理環境光源變化及攝影機振動等環境因素所造成的錯誤。
(4) 使用大量點對點相減演算法，部份錯誤情況無法完全避免。
本研究仍存在許多限制：
(1) 設下大量的門檻值，需多次調整出適當的門檻值。
(2) 無法處理人物在畫面中走動的情況。
本研究主要貢獻有兩點：
(1) 將動態規劃最佳演算法(DPAO)導入教學影片中進行比對。
(2) 有別於一般教學影片中投影片的靜態切換偵測，本研究針對動態換頁效 果的投影片，提出一個完整的偵測及分類流程，並定義出 SCT、DCT、
MCT 三種不同的動態效果類別，並依照不同類別特性來進行不同的演算 法處理。
5.2 未來研究
為了讓本研究能夠更加準確的偵測及分類動態效果，以及能適用於實際的上 課教學影片，以下則提出幾點未來可以加以改進的地方：
(1) 由於本研究針對於動態效果，因此不能略過任何一張影像資訊，必需處 理極為大量的影像，因此考慮到執行速率，所以採用計算較為簡易的演 算法，但相對的正確率有所下降，因此如果能找出更為迅速或正確的演 算法，將有助於本研究的計算耗時及正確率。
(2) 本研究是由不同的演算法模組所進行處理分類，因此能夠針對個別的分 類演算法(DPAO、GLPD、BM)進行替換或改進，以求更為加強本研究分類 的正確性。
(3) 本研究針對於換頁時的特效，而不包含同一張投影片中的個體特效(如文 字飛入)，因此如果能針對此個體特效建立出另一套偵測流程，將更能適 用於生動的教學投影片。
(4) 本研究不考慮於錄製影片時，發生同學及老師進出畫面的情況，因此如 果能加入此類額外處理判斷，將更能適用於實際的上課影片。
參考文獻
[1] Open Source Computer Vision Library (OpenCV) http://www.opencv.org.
[2] Y. Abdeljaoued, T. Ebrahimi, C. Christopoulos and I.M. Ivars, ―A New Algorithm For Shot Boundary Detection‖, Proceedings of the 10th European Signal Processing Conference, Tampere, Finland, September 2000.
[3] J. C. Bezdek, and N.R. Pal, ―Some New Indexes of Cluster Validity‖, IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, Vol. 28, No.
3, pp.301-315, Jun 1998.
[4] P. Browne, A. F. Smeaton, N. Murphy, N. O'Connor, S. Marlow and C. Berrut,
― Evaluating and Combining Digital Video Shot Boundary Detection Algorithms‖, Proceedings of Irish Machine Vision and Image Processing Conference, 2000.
[5] H.S. Chang, S. Sull and S.U. Lee, ―Efficient Video Indexing Scheme for Content-Based Retrieval‖, IEEE Transactions On Circuits And Systems For Video Technology, Vol. 9, No. 8, pp. 1269-1279, December 1999.
[6] 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.
[7] U. Gargi, R. Kasturi and S.H. Strayer, ―Performance Characterization of Video-shot-change Detection Methods‖, IEEE Transactions on Circuits and Systems for Video Technology, Vol. 10, No. 1, pp. 1-13, February 2000.
[8] B. Gatos and N. Papamarkos, ―Applying Fast Segmentation Techniques at a Binary Image Represented by a Set of Non-Overlapping Blocks‖, Proceedings of the Sixth International Conference on Document Analysis and Recognition, pp.
1147-1151, 2001.
[9] Y. Gong, ―An Accurate and Robust Method for Detecting Video Shot Boundaries‖, Proceedings of IEEE International Conference on Multimedia Computing and Systems, Vol. 1, pp. 850-854, July 1999.
[10] B. Gunsel, A. M. Ferman and A. Murat Tekalp, ―Temporal Video
Segmentation Using Unsupervised Clustering and Semantic Object Tracking‖, Journal of Electronic Imaging, Vol. 7, No. 3, pp. 592-604, July 1998.
[11] S. Ji and H.W. Park, ―Region-based Video Segmentation using DCT Coefficients‖, Proceedings of IEEE International Conference on Image Processing, Vol. 2, pp.150-154, 1999.
[12] S. Khedekar, V. Ramanaprasad, S. Setlur and V. Govindaraju, "Text - Image Separation in Devanagari Documents‖, Proceedings of the 6th International Conference on Document Analysis and Recognition, Washington, DC, USA, Vol.
2, pp. 1265-1269, 2003.
[13] C Lin, M Sheu, H Chiang, C Liaw and C Tsai, ―An Efficient Video De-interlacing with Scene Change Detection‖, Proceedings of the 5th
International Conference on Information, Communications and Signal Processing, pp. 36-40, December 2005.
[14] Z. Lei, W. Chou, J. Zhong and C.H. Lee, ―Video Segmentation Using Spatial and Temporal Statistical Analysis Method‖, Proceedings of IEEE International Conference on Multimedia and Expo, New York, Vol. 3, pp.
1527-1530, July 2000.
[15] M. Lin, J.F. Nunamaker, M. Chau and H. Chen, ―Segmentation ofLecture Videos Based on Text: A Method Combining Multiple Linguistic Features‖, Proceedings of the 37th Hawaii International Conference on System Sciences, 2004, Big Island, Hawaii, pp. 3-11, 2004.
[16] H. Lu, Y.P. Tan, X. Xue and L. Wu, ―Shot Boundary 'Detection using Unsupervised Clustering and Hypothesis Testing‖, Proceedings of IEEE International Conference on Communications, Circuits and Systems, Vol. 2, pp.932-936, June 2004.
[17] J. Nang, S. Hong and Y. Ihm, ―An Efficient Video Segmentation Scheme for MPEG Video Stream using Macroblock Information‖, Proceedings of the 7th ACM international conference on Multimedia, Orlando, Florida, United States, pp.
23-26, 1999.
[18] M.R. Naphade, R. Mehrotra, A.M. Ferman, J. Warnick, T.S. Huang and A.M.
Tekalp, ―A High-performance Shot Boundary Detection Algorithm using Multiple Cues‖, Proceedings of IEEE International Conference on Image Processing, Vol.
1, pp. 884-887, October 1998.
[19] C. O’Toole1, A. Smeaton, N. Murphy and S. Marlow, ―Evaluation of Automatic Shot Boundary Detection on A Large Video Test Suite‖, Proceedings of The Challenge of Image Retrieval, Newcastle, UK, pp. 25-26 February, 1999.
[20] N. Otsu, ―A threshold selection method from gray-level histograms‖, IEEE Transactions on Systems, Man and Cybernetics, pp. 62–66, 1979.
[21] S.C. Pei and Y.Z. Chou, ―Efficient MPEG Compressed Video Analysis using Macroblock Type Information‖, IEEE Transactions On Multimedia, Vol. 1, No. 4, pp. 321-333, December 1999.
[22] T.M. Rath and R. Manmatha, ―Word Image Matching Using Dynamic Time Warping‖, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 2, pp. 521-527, June 2003.
[23] S. Repp and C. Meinel, ―Semantic Indexing for Recorded Educational Lecture Videos‖, Proceedings of the 4th Annual IEEE Int. Conference on Pervasive Computing and Communications Workshops, pp. 240-245, March 2006.
[24] R. J. Rodrigues and A. C. G. Thomé, ―Cursive Character Recognition - A Character Segmentation Method using Projection Profile-based Technique‖, Proceedings of The 4th World Multi-conference on Systemics, Cybernetics and Informatics SCI 2000 and The 6th International Conference on Information Systems, Analysis and Synthesis ISAS 2000 - Orlando, USA - August 2000.
[25] E. Saez, J.I. Benavides and N. Guil, ―Reliable Real Time Scene Change Detection in MPEG Compressed Video‖, Proceedings of IEEE International Conference on Multimedia & Expo, Vol. 1, pp. 567-570, June 2004.
[26] M. Sawaki and N. Hagita, ―Text-Line Extraction and Character Recognition of Document Headlines With Graphical Designs Using Complementary Similarity Measure‖, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.
20, No. 10, pp. 1103-1109, October 1998.
[27] B. Shahraray, ‖Scene Change Detection and Content-Based Sampling of Video Sequences‖, in Digital Video Compression: Algorithms and Technologies, Arturo Rodriguez, Robert Safranek, Edward Delp, Editors, Proc. SPIE 2419, pp.
2-13, February 1995.
[28] T. Shin, J.G. Kim, H. Lee and J. Kim, ―Hierarchical Scene Change Detection in An MPEG-2 Compressed Video Sequence‖, Proceedings of IEEE International Symposium on Circuits and Systems, Vol. 4, pp. 253-256, June 1998.
[29] A. Stegner and R. Klette, ―Evaluation of mpeg motion compensation algorithms‖, Tech. Rep., The University of Auckland, October 1997.
[30] K.W. Sze, K.M. Lam and G. Qiu, ―A New Key Frame Representation for Video Segment Retrieval‖, IEEE Transactions on Circuits and Systems for Video Technology, Vol. 15, No. 9, pp. 1148-1155, September 2005.
[31] K.W. Sze, K.M. Lam and G. Qiu, ―An Optimal Key Frame Representation for Video Shot Retrieval‖, Proceedings of IEEE International Symposium on Intelligent Multimedia, Video and Speech Processing, pp. 270-273, October 2004.
[32] W. Tian and Y. Qiao, ―Off-line Chinese Signature Verification based on Optimal Matching of Projection Profiles‖, Proceedings of the 6th World Congress on Intelligent Control and Automation, Dalian, China, Vol. 2, pp. 10240-10244, June 2006.
[33] V.V. Vinod and H. Murase, ―Object Location Using Complementary Color Features: Histogram and DCT‖, Proceedings of the 13th International Conference on Pattern Recognition, Vol. 1, pp. 554-559, August 1996.
[34] Z. Wang, G. Liu and L. Liu, ―A Fast And Accurate Video Object Detection And Segmentation Nethod In The Compressed Domain‖, Proceedings of IEEE International Conference Neural Networks & Signal Processing, Nanjing, China, Vol. 2, pp. 1209-1212, December 2003.
[35] T. Yokoi and H. Fujiyoshi, ―Generating A Time Shrunk Lecture Video by Event Detection―, Proceedings of IEEE International Conference on Multimedia
& Expo, Toronto, Ontario, Canada, pp. 873-876, July 2001.
[36] H.J. Zhang, A. Kankanhalli and S.W. Smoliar, ―Automatic Partitioning of Full-motion Video‖, Multimedia Systems, Vol. 1, No. 1, pp. 10-28, 1993.
[37] D. Zhang, W. Qi and H.J. Zhang, ―A New Shot Boundary Detection Algorithm‖, Proceedings of the Second Pacific Rim Conference on Multimedia:
Advances in Multimedia Information Processing, pp. 63-70, 2001.
[38] L. Zhao, W. Qi, S. Z. Li, S.Q. Yang and H.J. Zhang, ―Content-based Retrieval of Video Shot Using The-improved Nearest Feature Line Method‖, Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol. 3, pp. 1625-1628, 2001.
[39] J. Zhou and X.P. Zhang, ―A Web-Enabled Video Indexing System‖, Proceedings of the 6th ACM SIGMM international workshop on Multimedia information retrieval, New York, USA, pp. 307-314, 2004.
[40] Y. Zhu, T. Tan and Y. Wang, ―Font Recognition Based on Global Texture Analysis‖, IEEE Transactions Pattern Analysis and Machine Intelligence, Vol. 23 No.10, pp.1192-1200, October 2001.
[41] Y. Zhuangt, Y. Rui, T. S. Huang and S. Mehrotra, ―Adaptive Key Frame Extraction using Unsupervised Clustering‖, Proceedings of IEEE International Conference on Image Processing, Vol.1, pp. 866-870, October 1998.