Assessment of similarity measurement criteria in Thepade's Sorted Ternary Block Truncation Coding (TSTBTC) for Content Based Video Retrieval

Abstract

Rapid growth in Information technology and Communication networking, have increased the inclination of professionals in storage and archival of multimedia-video data. Efficient and accurate retrieval of archived video data is essential need of many professional groups like researchers, analyst, journalist and historians. Textual metadata based video retrieval is intuitive and subject to human perception. Thus researchers are exploiting the opportunity of extracting the features based on content of video and retrieve the video accordingly. There rises a new horizon of Content Based Video Retrieval. Color content based video retrieval has been attempted using Block Truncation Coding and variations of it. Thepade's Sorted Ternary Block Truncation Coding level 2 (TSTBTC-2) has been attempted for Color Content Based Video Retrieval in this paper. The paper attempts detailed performance comparison of sixteen similarity measures alias Euclidean Distance, City Block Metric, Chebychev Distance, Mean Square Error, Hamming Distance, Minkowski Distance, Soergel Distance, Sorensen Distance, Canberra Distance, Kulczynski Distance, Wave Hedges Distance, Harmonic Mean Distance, Cosine Similarity, Jaccard Distance, Fidelity Distance and Squared Chord Distance across five families L p Minkowski family, L 1 family, Intersection family, Inner Product Family and Fidelity family. TSTBTC-2 based video retrieval experimentation is done on test bed of 500 videos with 500 queries and the average accuracy is computed. After experimentation it has been found that L p Minkowski family performs better and fidelity family's similarity measures are not suitable for applications like Color Content Based Video Retrieval. Among all similarity measures considered Sorensen Distance shows best performance followed by City Block Metric measure.