Increasing the performance of text base image search engine using Attribute assisted Reranking Model

Image Processing

The large growth of digital images on the web, will required the best image retrieving methods that can be improve the retrieval accuracy of images. Therefore research focus has been shifted from designing of generated algorithms that reduce the gap between visual features and richness of human semantics. Therefore many image re-ranking techniques has been developed to enhance the text based image results by taking the advantage of visual information contained in the images. But the previous techniques are based on low level visual features. Hence in this paper the semantic attributes and low level features are exploited simultaneously by using hypergraph re-ranking method. Based on classifiers for all the predefined attributes, each image is represented by an attribute feature containing of the results from these classifiers. A hyper graph model is the association between the images and its relevance score to order the images. Its simple based on that visually similar images should have related ranking scores. Proposed a Profile based classification technique on the top of attribute assisted re-ranking approach, to provide more accurate results specific to the user profession. This modeling link among more close samples and will be able to domain the robust semantic similarity, hence expedite the great ranking performance in profile based classification. The experimental results show the success of this method on attribute assisted as well as profile based image re-ranking.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.