Paper Title
Performance Appraise of Data Mining Classifiers from Bayes, Function, Lazy, Rule and Tree Family for Video Classification Using Linde Buzo Gray Vector Quantization Codebooks

Abstract
In today’s era multimedia is playing a vital role. The Number of videos are generated in huge amount which implies the need to build the classification system based on contents of videos. The paper proposes video classification approach with data mining classifiers applied on Linde Buzo Gray Vector Quantization Codebooks of the video frames. Total 68 variations of proposed classification method with 17 assorted classifiers and 4 different codebook size are tested here on a database having 300 videos. Classification accuracy is used to compare the performance of the variations of proposed video classification method. The best performance is observed by Random Forest classifier of Tree family with 64 codebook size of Linde Buzo Gray Vector Quantization. Keywords - Video Classification; Linde Buzo Gray Vector Quantization; Bayes, Function, Lazy, Rule, Tree Data mining classifiers.