Title :
Exploration of Image Search Results Quality Assessment
Author :
Xinmei Tian ; Yijuan Lu ; Stender, Nate ; Linjun Yang ; Dacheng Tao
Author_Institution :
Key Lab. of Technol., Univ. of Sci. & Technol. of China, Hefei, China
Abstract :
Image retrieval plays an increasingly important role in our daily lives. There are many factors which affect the quality of image search results, including chosen search algorithms, ranking functions, and indexing features. Applying different settings for these factors generates search result lists with varying levels of quality. However, no setting can always perform optimally for all queries. Therefore, given a set of search result lists generated by different settings, it is crucial to automatically determine which result list is the best in order to present it to users. This paper aims to solve this problem and makes four main innovations. First, a preference learning model is proposed to quantitatively study and formulate the best image search result list identification problem. Second, a set of valuable preference learning related features is proposed by exploring the visual characters of returned images. Third, a query-dependent preference learning model is further designed for building a more precise and query-specific model. Fourth, the proposed approach has been tested on a variety of applications including re-ranking ability assessment, optimal search engine selection, and synonymous query suggestion. Extensive experimental results on three image search datasets demonstrate the effectiveness and promising potential of the proposed method.
Keywords :
database indexing; image retrieval; search engines; image retrieval; image search result list identification problem; image search result quality assessment; indexing features; optimal search engine selection; query-dependent preference learning model; query-specific model; ranking functions; reranking ability assessment; search algorithms; synonymous query suggestion; visual characters; Algorithm design and analysis; Big data; Google; Search engines; Search problems; Training; Visualization; Image retrieval; reranking ability assessment; search results performance comparison;
Journal_Title :
Big Data, IEEE Transactions on
DOI :
10.1109/TBDATA.2015.2497710