Paper Details

This technology presents a technique for content-based image retrieval (CBIR) by misusing the benefit oflow complexity ordered dither block truncation coding (ODBTC) for the generation of image content descriptor. In theencoding step, ODBTC packs a picture hinder into relating quantizers and bitmap picture. Two picture elements areproposed to list a picture, in particular, color co-occurrence feature (CCF) and bit pattern features (BPF), which arecreated specifically from the ODBTC encoded information streams without performing the disentangling procedure. TheCCF and BPF of a picture are essentially gotten from the two ODBTC quantizers and bitmap, individually, by includingthe visual codebook. Experimental results show that the proposed method is superior to the block truncation codingimage retrieval systems and the other earlier methods, and thus prove that the ODBTC arrangement is not simply suitedfor picture weight, because of its ease, also offers a direct and fruitful descriptor to rundown pictures in CBIR system.

Anjali B. Pandhare, Krishnakant Gupta, Sagar Gurav, Ajinkya Khangal, “Content-Based Image Retrieval Using Features Extracted From HalftoningBased Block Truncation Coding”, International Journal of Advance Engineering and Research Development (IJAERD), Vol. 3, Issue 5, pp. 823-827, May 2016.