ICIP 2012: Wireless Networks and Computational Intelligence pp 129-138 | Cite as
Shot-Based Genre Identification in Musicals
Abstract
The phenomenal growth of World Wide Web has caused an easier and faster access to multimedia contents. The volume of available multimedia contents like Hindi movies’ music databases online has been exponentially increased. It results in dire need of automatic music retrieval from such databases. In recent years content-based music retrieval has been viewed as a potential solution to it. The ability of content based music retrieval is to automatically identify different characteristics of music data such as its genre. Unfortunately, the existing genre identifiers that are mostly tested on western music databases, has very low accuracy on Hindi movies’ music databases. Moreover, all the existing approaches of genre identification are based on music audio. In this paper, we propose a framework to automatically identify genre of a Hindi movie song using its video features. We used video shot duration and actor movement to classify the songs in pop, romantic, and tragic classes. We performed our experiments on 105 popular Hindi movies’ songs falling evenly in three proposed genres. An accuracy of 89.5% has been achieved that proves the effect of music video on its genre.
Keywords
Actor Movement Content-Based Video Retrieval Genre Identification Shot Duration Song Genre IdentificationPreview
Unable to display preview. Download preview PDF.
References
- 1.Shen, J., Shepherd, J., Cui, B., Tan, K.L.: A Novel Framework for Efficient Automated Singer Identification in Large Music Databases. ACM Transactions on Information Systems 27(3), 1–31 (2009)CrossRefGoogle Scholar
- 2.Rabiner, L., Juang, B.: Fundamentals of Speech Recognition. Prentice-Hall, N.J. (1993)Google Scholar
- 3.Tao, L., Ogihara, M., Li, Q.: A Comparative Study on Content-Based Music Genre Classification. In: 26th Annual International ACM SIGIR Conference on Research and Development in Informaion Retrieval. ACM, New York (2003)Google Scholar
- 4.Tolonen, T., Karjalainen, M.: A Computationally Efficient Multi Pitch Analysis Model. IEEE Trans. Speech Aud. Process 8(4), 708–716 (2000)CrossRefGoogle Scholar
- 5.Shahram, G., Shyamala, D., Noris, M.N., Sulaiman, M.N., Udzir, N.I.: A Comprehensive Study in Benchmarking Feature Selection and Classification Approaches for Traditional Malay Music Genre Classification. In: DMIN, pp. 71–77 (2008)Google Scholar
- 6.Tzanetakis, G., Cook, P.: Musical Genre Classification of Audio Signals. IEEE Transactions on Speech and Audio Processing 10(5) (July 2002)Google Scholar
- 7.Zhang, H.J., Kankanhalli, A., Smoliar, S.W.: Automatic Partitioning of Full-Motion Video. Multimedia System 1, 10–28 (1993)CrossRefGoogle Scholar
- 8.Zhang, H.J., Low, C.Y., Smoliar, S.W.: Video Parsing and Browsing using Compressed Data. Multimedia Tools and Appl. 1, 89–111 (1995)CrossRefGoogle Scholar
- 9.Anil, J., Aditya, V., Wei, X.: Query by Video Clip. In: International Conference on Pattern Recognition (ICPR 1998), pp. 90–99 (1998)Google Scholar
- 10.Baber, J., Afzulpurkar, N., Dailey, M.N., Bakhtyar, M.: Shot Boundary Detection from Videos Using Entropy and Local Descriptor. In: Proceedings of 17th International Conference Digital Signal Processing, pp. 6–8 (July 2011)Google Scholar
- 11.Chang, C.C., Lin, C.J.: LIBSVM: A Library for Support Vector Machines (2001), http://www.csie.ntu.edu.tw/~cjlin/libsvm