Content based video classification using fuzzy rule base for edge detection

Multimedia sharing has become a recent trend over the Internet among which videos are an integral part. In order to handle such large amount of video data, classification techniques are necessary. This paper provides a video classification technique which uses a Fuzzy rule base to calculate a fuzzy measure `Edginess´ for each pixel. Differences in pixel intensity are calculated and compared with a fuzzy rule base to calculate edginess. This edginess measure is used to decide whether a pixel belongs to an edge or not. Features extracted from training videos train the Naive Bayesian Classifier which is then used for testing videos. Features are pre-processed using techniques such as Discretize, Fuzzy Logic, Numeric to Binary, PKI Discretize and Normalize. Then, they are filtered using Correlation Feature Selection before training the classifier. Experimental Results show that a high accuracy of classification can be achieved with Fuzzy edge detection technique.