An Interactive Approach for Filtering Out Junk Images From Keyword-Based Google Search Results

• Published in: IEEE transactions on circuits and systems for video technology Vol. 19; no. 12; pp. 1851 - 1865
• Main Authors: Yuli Gao, Jinye Peng, Hangzai Luo, Keim, D.A., Jianping Fan
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.12.2009; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Access methods and protocols, osi model; Applied sciences; Clustering algorithms; Detection, estimation, filtering, equalization, prediction; Displays; Exact sciences and technology; Filtering; Filters; Filtration; Hyperbolic image visualization; Image processing; incremental kernel learning; Indexing; Information theory; Information, signal and communications theory; Interactive; junk image filtering; Kernel; Large-scale systems; mixture-of-kernels; Queries; Search engines; Search problems; Searching; Signal and communications theory; Signal processing; Signal, noise; Studies; Telecommunications; Telecommunications and information theory; Teleprocessing networks. Isdn; Texts; user-system interaction; Visualization; Visualization; Automatic classification; Query; Similarity; Image processing; Semantic analysis; Updating; Multiple image; Aggregation; Learning; Outlier; Hyperbolic image visualization; incremental kernel learning; Learning algorithm; Filtering; Keyword; Image retrieval; Search engine; Information retrieval; On-line systems; mixture-of-kernels; user-system interaction; HTTP; Signal classification; Kernel method; Interactive system; junk image filtering; Indexing
• ISSN: 1051-8215; 1558-2205
• DOI: 10.1109/TCSVT.2009.2026968

The keyword-based Google images search engine is now becoming very popular for online image search. Unfortunately, only the text terms that are explicitly or implicitly linked with the images are used for image indexing but the associated text terms may not have exact correspondence with the underlying image semantics, thus the keyword-based Google images search engine may return large amounts of junk images which are irrelevant to the given keyword-based queries. Based on this observation, we have developed an interactive approach to filter out the junk images from keyword-based Google images search results and our approach consists of the following major components. a) A kernel-based image clustering technique is developed to partition the returned images into multiple clusters and outliers. b) Hyperbolic visualization is incorporated to display large amounts of returned images according to their nonlinear visual similarity contexts, so that users can assess the relevance between the returned images and their real query intentions interactively and select one or multiple images to express their query intentions and personal preferences precisely. c) An incremental kernel learning algorithm is developed to translate the users' query intentions and personal preferences for updating the mixture-of-kernels and generating better hypotheses to achieve more accurate clustering of the returned images and filter out the junk images more effectively. Experiments on diverse keyword-based queries from Google images search engine have obtained very positive results. Our junk image filtering system is released for public evaluation at: http://www.cs.uncc.edu/~jfan/google-demo/.