Contact at or 8097636691/9323040215
Responsive Ads Here

Wednesday, 7 February 2018

An Attribute-Assisted Reranking Model for Web Image Search

An Attribute-Assisted Reranking Model for Web Image Search

The massive growth of digital images over the web, required the best image retrieval techniques that can improve the retrieval accuracy of the images. Hence research focus has been shifted from designing of sophisticated algorithms that can reduce the semantic gap between visual features and the richness of human semantics. Hence many image re-ranking technique has been proposed to enhance the text based image results by taking the advantage of visual information contained in the images. But this earlier techniques are based on the low level visual features. Hence the semantic attributes and low level features are exploited simultaneously by using hypergraph re-ranking method. A hypergraph model the relationship between the images by as per its rele vance score to order the images. Its simple belief is that visually analogous images should have related ranking scores. This modelling connection among more close samples will be able to domain the robustsemantic similarity and thus expedite the great ranking performance.An Attribute-Assisted Reranking Model for Web
Image search re-ranking has been studied for several years and various approaches have been developed recently to boost the performance of text-based image search engine for general queries. This paper serves as an attempt to include the attributes in re-ranking framework. It is observe that semantic attributes are projected to narrow down the semantic gap between low-level visual features and high level semantic meanings. Motivated by that, a novel attribute-assisted retrieval model for re-ranking images is proposed. Based on the classifiers for all the predefined attributes, each image is represented by an attribute feature consisting of the responses from these classifiers. A hypergraph can be the effective approach to model the relationship between images by integrating low-level visual features and semantic attribute features. Hypergraph ranking performed to re -order the images, which is also constructed to model the relationship of all images.

No comments:

Post a Comment