Title :
Learning Pathological Characteristics from User´s Relevance Feedback for Content-Based Mammogram Retrieval
Author :
Wei, Chia-Hung ; Li, Chang-Tsun
Author_Institution :
Dept. of Comput. Sci., Warwick Univ., Coventry
Abstract :
Content-based image retrieval (CBIR) has been proposed to address the problem of image retrieval from medical image databases. Relevance feedback, explaining the user´s query concept, can be used to bridge the semantic gap and improve the performance of CBIR systems. This paper proposes a learning method for relevance feedback, which utilizes probabilistic model to generalize the 2-class problem and provide an estimate of probability of class membership. To build the probabilistic model, support vector machine (SVM) is applied to classify the mammograms, and then scale them to the probability of class membership. Experimental results show that the proposed learning method can effectively improve the average precision rate from 40% to 62% through five iterations of relevance feedback rounds
Keywords :
content-based retrieval; mammography; medical image processing; probability; relevance feedback; support vector machines; visual databases; CBIR; SVM; content-based image retrieval; mammogram retrieval; medical image databases; pathological characteristics; probabilistic model; relevance feedback; support vector machine; Biomedical imaging; Content based retrieval; Feedback; Image databases; Image retrieval; Information retrieval; Learning systems; Pathology; Support vector machine classification; Support vector machines;
Conference_Titel :
Multimedia, 2006. ISM'06. Eighth IEEE International Symposium on
Conference_Location :
San Diego, CA
Print_ISBN :
0-7695-2746-9
DOI :
10.1109/ISM.2006.101