QUERY RECONSTRUCTION IN IMAGE SEARCHING FOR OPTIMUM OUTCOME

Information Technology

Image search engines suffer from a radical variance in retrieval performance over different queries. It is need to identify those difficult queries in order to handle them properly. Query difficulty estimation is an attempt to predict the performance of the search results returned by an image search system. Most existing methods for query difficulty estimation focus on investigating statistical characteristics of the returned images only, while neglecting very important information, the query and its relationship with returned images. To reduce human effects, in this paper, we use image click-through data, which can be viewed as the implicit feedback from users, to overcome the intention gap, and further improve the image search performance. In this we propose a query difficulty estimation method with query reconstruction error with similarity and typicality. This method is proposed based on the semantic gap and the intent gap simultaneously, we propose to integrate multiple visual sense and click-through data with learning image similarity and typicality, and presenting better searching through Reranking approach, named spectral clustering re-ranking We begin query reconstruction through click based multi feature similarity and typicality(RCFST).first we propose multi feature similarity learning algorithm Then based on the learnt click-based image similarity measure, we conduct spectral clustering to group visually and semantically similar images into same clusters, and get the final re-rank list by calculating click-based clusters typicality and within clusters click-based image typicality in descending order.Showing the annotation to the resultant images for better understanding.

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