Performance rise in novel content based video retrieval using Vector Quantization
Dipak R. Pardhi, Jitesh Rajendra Neve · 2016
In this recent world, almost everything is getting digitized rapidly. A text based video retrieval system is degrading the performance with respect to user's perception these days. So it's time to move on to the content based retrieval approach to a video. The effective implementation of this system can be done by revision of the content based video retrieval style. Content Based Video Retrieval (CBVR) is the emerging system for any video retrieval application. The Block Truncation Coding (BTC) is one of the color feature extraction technique in the CBVR. With improvements to the BTC, Thepade's Sorted Ternary Block Truncation Coding (TSTBTC) is also the recent color feature extraction technique. One more technique is discussed here about the transform feature extraction of the video. None of the method right now extended for both of the features like color and transform. In other hand Vector Quantization (VQ) is the lossy compression technique. If VQ is used with TSTBTC it can deal with both of the features like color and transform. Because VQ supports hybrid features and VQ is not used before.