A comprehensive study in novel content based video retrieval using vector quantization over a diversity of color spaces

Now a days there is a fantasy to be digitized rapidly. Where digitization is applicable to every domain; no matter its technical or non-technical. So there is a need of effective retrieval of data. Today people are finding some new retrieval schemes over the traditional query based retrieval systems. So moving towards content based approach is an hour's need. Some betterments are definitely needed to empower the Content Based approach. For content based video retrieval (CBVR) system, Block Truncation Coding (BTC) is one of the techniques to extract color features of a video. One more technique is there with improvements to BTC is Thepade's Sorted Ternary Block Truncation Coding (TSTBTC). Transform feature extraction is one more technique about extraction of the video. Right now only one feature can be targeted in a technique; in other words, there is no method which can be exposed to color as well as transform feature of a video. In other hand, Vector Quantization (VQ) is a popular technique for lossy data compression. If VQ is used with TSTBTC, it can deal with color features as well as transform features of a video. Because VQ is can be operated with hybrid features. This is first time when VQ is seen in CBVR. This paper also describes the efficiency and accuracy of this technique with different Color Spaces.