Visual Search Optimization using Concept Related Re-Ranking

Visual search re-ranking defined as re-ordering visual documents like image, videos etc. based on the initial search. Ranking the multimedia content like images, videos are a challenging research topic in the noisy visual environment. Now days, leading search engines are fully depends on the description, title, surrounding information of an image which produce irrelevant image which are not equal to visual content. In this paper, a new approach proposed to improve the visual search precision level. First, the initial ranking occurred based on the textual information like tag, description relevancy which didn’t produce relevant images. Second, by using visual query examples in the search engine to filter the images based on feature. The visual equivalence between the images calculated to increase the relevance results. Mainly the Equivalence Reranking approach focused on the relationship between the concepts of documents considered to reorder the initial search result with higher resolution images for optimizing the list of images. And by avoiding and removing irrelevant image along with the low resolution images by re-ranking approach, will increase the performance of search engine.

[1]  Chuan-Ju Wang,et al.  Rank Refinement for Social Images by a Random Walk Model , 2011 .

[2]  Mingjing Li,et al.  Statistical correlation analysis in image retrieval , 2002, Pattern Recognit..

[3]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Van Rijsbergen,et al.  A theoretical basis for the use of co-occurence data in information retrieval , 1977 .

[5]  W. Bruce Croft,et al.  Query expansion using local and global document analysis , 1996, SIGIR '96.

[6]  Edward A. Fox,et al.  Support Vector Machines to Weight Voters in a Voting System of Entity Extractors , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[7]  Hui Hui Wang,et al.  Image Retrieval: Techniques, Challenge, and Trend , 2009 .

[8]  Dong Wang,et al.  Video search in concept subspace: a text-like paradigm , 2007, CIVR '07.

[9]  Shih-Fu Chang,et al.  A reranking approach for context-based concept fusion in video indexing and retrieval , 2007, CIVR '07.

[10]  Markus A. Stricker,et al.  Similarity of color images , 1995, Electronic Imaging.

[11]  Pietro Perona,et al.  Learning object categories from Google's image search , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[12]  Nicu Sebe,et al.  Content-based multimedia information retrieval: State of the art and challenges , 2006, TOMCCAP.

[13]  Mario Fernando Montenegro Campos,et al.  An image retrieval method based on factor analysis , 2003, 16th Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI 2003).

[14]  Shih-Fu Chang,et al.  Video search reranking through random walk over document-level context graph , 2007, ACM Multimedia.

[15]  Marcel Worring,et al.  Are Concept Detector Lexicons Effective for Video Search? , 2007, 2007 IEEE International Conference on Multimedia and Expo.

[16]  Tao Mei,et al.  Optimizing video search reranking via minimum incremental information loss , 2008, MIR '08.

[17]  Jin Zhao,et al.  Video Retrieval Using High Level Features: Exploiting Query Matching and Confidence-Based Weighting , 2006, CIVR.

[18]  Dong Wang,et al.  The importance of query-concept-mapping for automatic video retrieval , 2007, ACM Multimedia.

[19]  Tao Mei,et al.  CrowdReranking: exploring multiple search engines for visual search reranking , 2009, SIGIR.