Ranking of Image Search by Click-Based Uniformity and Typicality

Abstract

Abstract

According to the image search re-ranking, apart from the semantic gap and intent gap, which is the gap between the representation of user’s query and the real objective of the users, is forming a major issue in restricting the evolution of image retrieval. In order to reduce human effects, the method use image click-through data, which can be viewed as the implicative feedback from users, to help overcome the intention gap, and further to improve the performance of image search. The proposed method presents a novel re-ranking approach, named spectral clustering re-ranking with click-based similarity and typicality.

Keywords: Image search, search re-ranking, click-through data, multifeature similarity, image typicality

Cite this Article

Ashwath M, Balapradeep KN, Savitha CK et al. Re-Ranking Of Image Search by Click-Based Uniformity and Typicality. Journal of Image Processing & Pattern Recognition Progress. 2016; 3(3): 39–46p.