ABSTRACT
For more than a decade query-by-one-example (QBE) has been a popular query system for content-based image retrieval (CBIR). However, recent research has shown that a single image is not sufficient to form its semantics or concept of the intended query. Searching concept "car," for instance, one might need many examples of car images in various colors. The color feature is then understood as a non-factor in the distance metric. In our approach, users can query by using groups of query images. There are three possible groups: relevant (positive), irrelevant (negative) or neutral groups. We define the range for each feature within these groups of query images, and use them to adjust the weights of the features. As a result, some features may be cancelled out from the similarity computation. The measure then becomes a dynamic metric for image retrieval. Our approach achieves a higher degree of precision and recall and, at the same time, significantly reduces the time complexity of matching. The proposed approach is tested against the ImageGrouper method. The results show that this approach is an effective and efficient technique for QBE.
- Munehiro Nakazato and Thomas S. Huang, "Extending Image Retrieval with Group-Oriented Interface," In Proceedings of IEEE ICME2002, 2002.Google Scholar
- Thomas E. Bjoerge and Edward Y. Chang, "Why one example is not enough for an image query," In Proceedings of IEEE ICME 2004, 2004.Google Scholar
- http://www.ifp.uiuc.edu/~nakazato/grouper/Google Scholar
- Smith, J. R. and Chang S-F. Transform features for texture classification and discrimination in large image databases. In Proceedings of IEEE Intl. Conf. on Image Processing. 1994.Google Scholar
- Smith J. R. and Chang S-F. "Quad-Tree Segmentation for Texture-based Image Query." In Proceedings of ACM 2nd International Conference on Multimedia, 1994. Google ScholarDigital Library
- Strang, G. and Nguyen, T., "Wavelet and Filter Banks," Wellesley-Cambridge Press, 1997.Google Scholar
- Zhou, X. S. and Huang, T. S., "Edge-based structural feature for content-base image retrieval," Pattern Recognition Letters, Special issue on Image and Video Indexing, 2000. Google ScholarDigital Library
- Gonzales, R. C. and Woods, R. E., "Digital Image Processing," Addison-Wesley, 1992. Google ScholarDigital Library
- A.W.M. Smeulders et al, Content-based image retrieval at the end of the early years. IEEE Trans. On PAMI, 22(12): 1349--1380, 2000. Google ScholarDigital Library
- Ying Dai and Dawei Cai, "Imagery - based digital collection retrieval using eigen SGLD matrices," In Proceedings of IEEE ICME 2004, 2004.Google Scholar
- Joo-Hwee Lim and Jesse S. Jin, "Image retrieval using spatial icons," In Proceedings of IEEE ICME 2004, 2004.Google Scholar
- S. Berretti, G. D. Amico and A. Del Bimbo, "Shape representation by spatial partitioning for content based retrieval applications," In Proceedings of IEEE ICME 2004, 2004.Google Scholar
- B. Ko, H. S. Lee, and H. Byun, "Region-based image retrieval system using efficient feature description," In Proceedings of IEEE Int. Conf. on Pattern Recognition, Barcelona, Spain, 2000, pp. 283--286. Google ScholarDigital Library
- F, Liu, X. Xiong, and K. L. Chan, "Natural image retrieval based on features of homogeneous color regions," In Proceedings of IEEE on Image Analysis and Interpretation, Austin, Texas, Apr. 2000, pp. 73--77. Google ScholarDigital Library
- Xiangyu Jin and James C. French, "Content-based image retrieval for multimedia databases: Improving image retrieval effectiveness via multiple queries," Proceedings of the first ACM international workshop on Multimedia databases, Nov. 2003, pp. 86--93. Google ScholarDigital Library
Recommendations
An adaptive technique for content-based image retrieval
We discuss an adaptive approach towards Content-Based Image Retrieval. It is based on the Ostensive Model of developing information needs--a special kind of relevance feedback model that learns from implicit user feedback and adds a temporal notion to ...
Image retrieval based on bag of images
ICIP'09: Proceedings of the 16th IEEE international conference on Image processingConventional relevance feedback schemes may not be suitable to all practical applications of content-based image retrieval (CBIR), since most ordinary users would like to complete their search in a single interaction, especially on the web search. In ...
A Comparison of Content Based Image Retrieval Systems
CSE '14: Proceedings of the 2014 IEEE 17th International Conference on Computational Science and EngineeringContent-based image retrieval (CBIR) is the application of computer vision techniques to the image retrieval problem. There are two main content-based image retrieval paradigms: one based on visual queries, referred to as query-by-visual-example (QBVE), ...
Comments