The week's pick
Reseach Article
Content based Video Retrieval using Text Annotation and Low Level Features Technique
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 145 - Number 14 |
| Year of Publication: 2016 |
| Authors: Aniket Sugandhi, Deepshikha Sharma |
10.5120/ijca2016910842
|
Aniket Sugandhi, Deepshikha Sharma . Content based Video Retrieval using Text Annotation and Low Level Features Technique. International Journal of Computer Applications. 145, 14 ( Jul 2016), 11-16. DOI=10.5120/ijca2016910842
Abstract
The information retrieval processes are playing essential role in the computer based database exploration or finding the essential contents from the databases. Now in these days a number of search techniques and retrieval models are exist by using which the users can find the data. According to the different data formats the information retrieval processes are also varying therefore different data format based retrieval process are works in different manner. In this presented work the content based video retrieval model is presented. In the content based video retrieval model the work is initiated from the segmentation of the videos into the set of frames. The segmentation of video is performed using the FFMPEG media library that works on the basis of two parameters first the video clip and second the time slot duration by which the frames are extracted. After segmentation to enable the text based query the text annotation concept is used and the individual frames of video is tagged with the user defined text. On the other hand to enable the query by example the low level features of individual frames are also computed. To compute the low level descriptors shape, color and texture analysis is performed. Thus the canny edge detection, local binary pattern and the color movement analysis techniques are used. Finally for classifying the relevant videos according to the user query the KNN classifier is implemented. That classifier accepts the user text query or the example query for classifying the similar video objects from the database. The implementation of the presented methodology is performed using JAVA technology. Additionally for finding the performance precision, recall, and f-measures are computed, according to the computed values the example based techniques provides more accurate outcomes as compared to text based query. In addition of that the resource consumption of the proposed technique is also computed in terms of time and space, according to the results the example based query processing consumes additional resources as compared to text based methods. Thus the proposed work is accomplished with the satisfactory performance.
References
- Zhengyu Deng, Jitao Sang, and Changsheng Xu, “Personalized Celebrity Video Search Based on Cross-Space Mining”, PCM 2012, LNCS 7674, pp. 455–463, 2012. c Springer-Verlag Berlin Heidelberg 2012.
- Norbert Fuhr, “An Information Retrieval View of Environmental Information Systems”, Technische Hochschule Darmstadt, Fachbereich Informatik Karolinenplatz 5, W-6100 Darmstadt Germany.
- A. Scherp and R. Jain, “Towards an ecosystem for semantics”, In Proceedings of Workshop on Many faces of Multimedia Semantics, at ACM Multimedia 2007, pp. 3-12.
- B V Patel and B B Meshram, “Content based Video Retrieval Systems”, International Journal of UbiComp (IJU), Vol.3, No.2, April 2012.
- Yu-Gang Jiang, Jun Yang, Chong-Wah Ngo, Alexander G. Hauptmann, “Representations of Key point-Based Semantic Concept Detection: A Comprehensive Study”, IEEE, 2008.
- Masoud Nosrati, Ronak Karimi, Mehdi Hariri, “Detecting Circular Shapes From Areal Images Using Median Filter and CHT”, World Applied Programming, Vol (2), Issue (1), . 49-54, January 2012.
- Zhenhua Guo, Lei Zhang, David Zhang, “A Completed Modeling of Local Binary Pattern Operator for Texture Classification”, IEEE transaction on image processing, 2010.
- Mohammad Jafari, Neda Abdollahi, Ali Amiri, Mahmood Fathy, “Generalization of Determinant Kernels for Non-Square Matrix and its Application in Video Retrieval”, International Journal of Scientific Research in Computer Science and Engineering, Volume-3, Issue-4.
- Dan Albertson, Melissa P. Johnston, “Connecting with Educators: Science Teachers and Interactive Video Retrieval”, iConference 2015 Proceedings.
- Haojin Yang and Christoph Meinel, “Content Based Lecture Video Retrieval Using Speech and Video Text Information”, IEEE Transactions on Learning Technologies, vol. 7, no. 2, April-June 2014.
- Jiajun Liu, Zi Huang, Hongyun Cai, Heng Tao Shen, Chong Wah Ngo, Wei Wang, “Near-Duplicate Video Retrieval: Current Research and Future Trends”, ACM Computing Surveys, Vol. 45, No. 4, Article 44, Publication date: August 2013.
- Luca Rossetto, Ivan Giangreco, HeikoSchuldt, St´ephaneDupont, Omar Seddati, MetinSezgin, and Yusuf Sahillio˘glu, “IMOTION — A Content-Based Video Retrieval Engine”, (Eds.): MMM 2015, Part II, LNCS 8936, pp. 255–260, 2015. c Springer International Publishing Switzerland 2015.
- Ling Shao, Simon Jones, and Xuelong Li, “Efficient Search and Localization of Human Actions in Video Databases”, IEEE Transactions on Circuits and Systems for Video Technology, Vol 24, No 3, March 2014.
Index Terms
Keywords