Analysis Of Reranking Techniques For Web Image Search With Attribute –Assisted

Kiranmai Madireddi, P.Lakshmana Rao, Sayeed Yasin

Abstract


Many commercial search engines such as Google, Yahoo and Bing have been adopted this strategy. The search engines are mostly based on text and constrained due to user search by keyword which results into ambiguity among images. The noisy or irrelevant images may be present in the retrieved results. The purpose of web image search re-ranking is to reorder retrieved elements to get optimal rank list. The existing visual reranking schemes improve text-based search results by making the use of visual information. These methods are based on low-level visual features, and do not take into account the semantic relationship among images. Semantic attribute assisted re-ranking is proposed for web image search. Using the classifiers for predefined attributes, each image is represented by attribute features. The hypergraph is used to model the relationship between images. Hypergraph ranking is carried out to order the images. The basic principle is that similar images should have similar ranking. This paper presents a detail review of different image retrieval and reranking approaches. The purpose of the survey is to provide an overview and analysis of the functionality, merits, and demerits of the existing image reranking systems, which can be useful for researchers for developing effective system with more accuracy.


References


Xiaoou Tang, Fellow, IEEE, Ke Liu, Jingyu Cui, Student Member, IEEE, Fang Wen, Member, IEEE, and Xiaogang Wang, Member, “IntentSearch: Capturing User Intention for One-Click Internet Image Search†IEEE IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 34, NO. 7, JULY 2012 [2]N. Ben-Haim, B. Babenko, and S. Belongie, “ Improving Web- Based Image Search via Content Based Clustering,†Proc. Int’lWorkshop Semantic Learning Applications in Multimedia, 2006. [3]Josip krapac,Moray Allan Jakob Verbeek,Frederic Jurie /’Improving Web Image Search results using query relative classifiers†IEEE 978¬4244-6985- 7/10/2010 IEEE.

Chen Cao1, Shifeng Chen1, Yuhong Li1, Jianzhuang Liu,†Online - Non feedback image Reranking via dominant data selectionâ€, MM’12, October 29-November 2, 2012, Nara, Japan.Copyright 2012 ACM 978-1-4503-1089-5/12/10

Jia Deng, Alexander C. Berg , Li Fei -Fei ,†Hierarchical Semantics Indexing for Large Scale Image Retrieval â€.

F. Jing, C. Wang, Y. Yao, K. Deng, L. Zhang, and W. Ma, “Igroup: Web Image Search Results Clustering,†Proc. 14th Ann. ACM Int"l Conf. Multimedia, 2006.

J. Cui, F. Wen, and X. Tang, “Real Time Google and Live Image Search Re-Ranking,†Proc. 16th ACM Int"l Conf. Multimedia, 2008.

K. Jarvelin and J. Kelkalainen. IR evaluation methods for retrieving highly relevant documents. In Proceedings of ACM SIGIR conference on Research and Development in Information Retrieval, 2000.

W. H. Hsu, L. S. Kennedy and S.-F. Chang. Video search reranking via information bottle principle. In Proceedings of ACM Conference on Multimedia, 2006.


Full Text: PDF [Full Text]

Refbacks

  • There are currently no refbacks.


Copyright © 2013, All rights reserved.| ijseat.com

Creative Commons License
International Journal of Science Engineering and Advance Technology is licensed under a Creative Commons Attribution 3.0 Unported License.Based on a work at IJSEat , Permissions beyond the scope of this license may be available at http://creativecommons.org/licenses/by/3.0/deed.en_GB.

Â