Advanced technology has resulted in drastic growth of multimedia data. In day to day life huge amount of multimedia data is generated an uploaded over web. Storing this multimedia data has become a challenging task. Storing the data in video format efficiently and retrieving it accurately has become important. If the data is appropriately classified under different categories and then stored, it can be retrieved faster. In this paper a novel video classification techniques has been proposed to classify the videos. Transform domain has the property of energy compaction that helps to figure out the important data in the video and neglect the least important data. Thus the proposed techniques uses the Fourier transformed video content as the attributes for classification process. Twelve different classification algorithms are used and six fractional portions of transformed content forming the feature vectors of six different sizes are experimented. With the proposed technique highest classification accuracy of 89.16% is obtained.

Content based video classification, Fourier transform, Fractional energy, data mining classifiers

[1] Ambika Ashirvad Mohanty, Bipul Vaibhav, “A Frame-based Decision Pooling Method for Video Classification “, Annual IEEE India Conference (INDICON), 2013
[2] Mahmood Karimian, Mostafa Tavassolipour, “Exploiting Multiview Properties In Semi-Supervised Video Classification”, 6'th International Symposium on Telecommunications (IST'2012)
[3] Dr. Sudeep D. Thepade, Rik Das,” Performance Comparison of Feature Vector Extraction Techniques in RGB Color Space using Block Truncation Coding for Content Based Image Classification with Discrete classifiers” INDICON 2014.
[4] Dr. Sudeep D. Thepade, Madhura M. Kalbhor, Video Classification using Sine, Cosine, and Walsh Transform with Bayes, Function, Lazy, Rule and Tree Data Mining Classifier. International Journal of Computer Applications (0975 –8887) Volume 110 –No. 3, January 2015.
[5] Dr. Sudeep D. Thepade, Madhura M. Kalbhor,Video classification with fractional energy of Haar, Hartley, Slant and Kekre transforms using Function , Bayes, Tree, Lazy and Rule classifiers. A-Blaze, Nodia, 2015
[6] J. L. Walsh, “A Closed Set of Orthogonal Functions,” American Journal of Mathematics, vol. 45, pp. 5-24, 1923 .
[7] J. Han and M. Kamber, (2000) “Data Mining: Concepts and Techniques,” Morgan Kaufmann.
[8] Mizianty, M. ; Kurgan, L. ; Ogiela, M.,” Comparative Analysis of the Impact of Discretization on the Classification with Naïve Bayes and Semi-Naïve Bayes Classifiers”. Seventh International Conference Machine Learning and Applications, ICMLA 2008.
[9] Ian H.Witten and Elbe Frank, (2005) "Datamining Practical Machine Learning Tools and Techniques," Second Edition, Morgan Kaufmann, San Fransisco.