Attribute assisted reranking model for web image search

The Image reranking play important role in the process of web image search. The search engines are mostly based on text and limited to user search by keyword which leads to ambiguity among images. The noisy or irrelevant images may be present in the retrieved results. The purpose of web image search re-ranking is to reorder the retrieved entities to get the optimal rank list. The existing visual reranking schemes improve text-based search results by making the use of visual information. These methods are based on low-level visual features, and do not take into account semantic relationship among images. Here, semantic attribute assisted re-ranking is proposed for web image search, also user search interaction is proposed to get more refined result by using image [url removed, login to view] image is represented by attribute features, using the classifiers for the predefined attributes. The hypergraph is used to model the relationship between images. Ranking is carried out to order the images. The basic belief is that related images should have similar ranking. The performance will be evaluated to verify the effectiveness of the proposed attribute-assisted reranking method

Engineering Imaging Java Machine Learning (ML) MySQL

Project ID: #10082735

About the project