REGION-BASED IMAGE RETRIEVAL WITH RELEVANCE FEEDBACK | ||||
JES. Journal of Engineering Sciences | ||||
Article 12, Volume 40, No 3, May and June 2012, Page 819-832 PDF (502.22 K) | ||||
Document Type: Research Paper | ||||
DOI: 10.21608/jesaun.2012.114412 | ||||
View on SCiNiTO | ||||
Author | ||||
A. Hamdy | ||||
Department of Communications, and Computers Engineering Faculty of Engineering, Helwan University Cairo, Egypt | ||||
Abstract | ||||
Region-based image retrieval (RBIR), a special type of content based image retrieval (CBIR), is an important research. This paper presents integration of RBIR with relevance feedback (RF) to enhance the performance of CBIR. Watershed algorithm is used to extract regions but not all regions are with the same importance. So, a region-weighting scheme reflecting the process of human visual perception is proposed. By using relevance feedback method, the matching process could improve retrieval performance interactively and allow progressive refinement of query results according to the user's feedback action. | ||||
Keywords | ||||
Relevance feedback; Region-based image retrieval; Content-based image retrieval; Attention center; Integrated region matching; Watershed segmentation; Feature extraction | ||||
Statistics Article View: 66 PDF Download: 136 |
||||