Optimized web image search using meta annotation re-ranking technique
An image retrieval system is a computer system for browsing, searching and retrieving images from a large database of digital images. Given a textual query in Traditional text Based Image Retrieval (TBIR),relevant images are to be reranked using visual features after the initial text based image search. In this paper, a new meta annotation based re-ranking framework for large scale TBIR has been proposed. This problem has been computed on basis of Multiple
Instance Learning and Generalized Multiple Instance (GMI) learning method. To address the ambiguities on the instance labels in the positive and negative bags GMI settings have been proposed. Also the user log performs the operation of individual user interaction with the system which improves the performance of image retrieval.
Keywords: Multiple Instance, Generalized Multiple Instance, Image Re- ranking , Text Based Image Retrieva
Citation: *, ( 2017), Optimized web image search using meta annotation re-ranking technique. Scientific Transactions in Environment and Technovation Journal(STET), 10(3): 146-150
Received: 07/01/2015; Accepted: 01/04/2017;