A Review on Feature Extraction Techniques for CBIR with different BTC methods
R.Sahaya Jeya Sutha, S. John Peter · Journal of Emerging Technologies and Innovative Research · 2019
Content Based Image Retrieval (CBIR) is one of the fastest growing research areas to search the relevant images from the large image collections by analyzing the content of the user required query image. The retrieval time in CBIR is reduced by extracting the image features from the compressed image instead of the original image. The Block Truncation Coding (BTC) is a very efficient compression technique which requires least computational complexity and it can also effectively employed to index images in database for CBIR applications. Various improved versions of BTC methods are available for compression which is suitable for CBIR. This paper gives the review of feature extraction techniques for CBIR with different BTC methods such as Ordered Dithering BTC(ODBTC), Error Diffusion BTC (EDBTC), Dot Diffusion (DDBTC).