Content Matching – Detection of Duplicate and Near Duplicate Videos

Aqsa Zahid, Rehana Sharif

Abstract


At present, multimedia content is one of the fastest growing data type on internet. As, there are many duplicates on web so while searching users need to spend a lot of time by watching the same clip over and over again. So in order to remove the redundant content from the web and to increase the efficiency and performance of web search there is a straight forward need for the detection of similar and nearly similar videos. Different approaches have been developed in the past and intensive research is still being carried out, at present. Furthermore, there is a straightforward need for the detection of duplicate content.

This paper proposes detection of similar and nearly similar videos using texture descriptor. Note that in existing approaches this parameter (Frame rate) is not handled. A local alignment method in bioinformatics is used for the detection of similar regions between sequences. The strength of our approach is that it detects duplicates and nearly duplicate videos having accurate results for similar videos and ~92% accuracy rate for transformed videos.


Keywords


bio-informatics, DNA matching, Texture matching, Frame rate, Video matching

References


. Shen, H. T., Ooi, B. C., Zhou, X. and Z. Huang. (2007). UQLIPS:” A Real-time Near-duplicate Video Clip Detection System”. In SIGMOD Conference, (pp: 23-28). Vienna, Austria.

. Wu, X., Hauptmann, A. G. and Ngo, C. W. (2007, September). “ Practical Elimination of Near-Duplicates “ from Web Video Search(pp. 23-28). Augsburg, Bavaria, Germany.

. Wu, Z., Huang, Q. and Jiang, S. (2009). Robust Copy Detection By Mining Temporal Self-Similarities. Retrieved fromzpwu, qmhuang, sqjiang@jdl.ac.cn.

. Yang, X., Zhu,Q., Cheng, K., (October 23, 2009) “ Near-Duplicate Detection for Images and Videos” , Beijing, China.

. Tuceryan, M., Jain A. K., (1998) The Handbook of Pattern Recognition and Computer Vision (2nd Edition), pp. 207-248, World Scientific Publishing Co., 1998.

. Wu, Z., Jiang, S., Huang, Q.,” Near-Duplicate Video Matching with Transformation Recognition “ (October 19–24, 2009) , Key Lab of Intell. Info. Process., Inst. of Comput. Tech., Chinese Academy of Sciences, Beijing, China.

. Kim, H., Chang, H., Liu, H., Lee, J., Lee, D., BIM: “ Image Matching Using Biological Gene Sequence “ Alignment (2009) IEEE International Conference On Image Processing, Cairo, Egypt. ISSN: 1522-4880.

. Kim, H., Chang, H., Lee, J., Lee, D., BASIL: “ Effective Near-Duplicate Image Detection using Gene Sequence Alignment,” College of Information Sciences and Technology, Penn State University, USA.

. Tuceryan, M., Jain, K, A.,chapter 2.1 Texture Analysis, The Handbook of Pattern Recognition and Computer Vision (2nd Edition), by C. H. Chen, L. F. Pau, P. S. P. Wang (eds.), pp. 207-248, World Scientific Publishing Co., 1998.

. Achanta, R., Estrada, F., Wils, P., Süsstrunk, S., “Salient Region Detection and Segmentation”. Proc. of International Conference on Computer Vision Systems, May 2008.

. Maillard, P., “Comparing Texture Analysis Methods through Classification”,

. Eleyan, A., , Dem˙irel, H., “Co-occurrence matrix and its statistical features as a new approach for face recognition” Turk J Elec Eng & Comp Sci, Vol.19, No.1, 2011


Full Text: PDF

Refbacks

  • There are currently no refbacks.




 


All Rights Reserved © 2012 IJARCSEE


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 Unported License.