Content-Based Image Retrieval Using Error Diffusion Block Truncation Coding Features - 2015

PROJECT TITLE:

Content-Based Image Retrieval Using Error Diffusion Block Truncation Coding Features - 2015

ABSTRACT:

This paper presents a replacement approach to index color pictures using the options extracted from the error diffusion block truncation coding (EDBTC). The EDBTC produces 2 color quantizers and a bitmap image, that are any processed using vector quantization (VQ) to get the image feature descriptor. Herein 2 features are introduced, particularly, color histogram feature (CHF) and bit pattern histogram feature (BHF), to live the similarity between a query image and the target image in database. The CHF and BHF are computed from the VQ-indexed color quantizer and VQ-indexed bitmap image, respectively. The distance computed from CHF and BHF will be used to live the similarity between two images. As documented within the experimental result, the proposed indexing method outperforms the previous block truncation coding based image indexing and the other existing image retrieval schemes with natural and textural information sets. Therefore, the proposed EDBTC isn't only examined with good capability for image compression but additionally offers an efficient manner to index pictures for the content-based image retrieval system.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here