Proceedings. 17th IEEE Symposium on Computer-Based Medical Systems (2004)
June 24, 2004 to June 25, 2004
Agma J. M. Traina , University of S?o Paulo at S?o Carlos - Brazil
Andr? G. R. Balan , University of S?o Paulo at S?o Carlos - Brazil
Luis M. Bortolotti , University of S?o Paulo at S?o Carlos - Brazil
Caetano Traina Jr. , University of S?o Paulo at S?o Carlos - Brazil
This paper presents a new approach to retrieve images by content using a composition of relevant features regarding texture, shape and brightness distribution. The first step of the method is a segmentation process based on Markov Random Fields, which can be done automatically, having as parameter the number of desired classes. The regions obtained in the segmentation guide the extraction of measures from the original image producing a 30-dimensional feature vector used in the image retrieval. The experiments showed that the feature vector has high discrimination power and the time for retrieval operations are only fractions of seconds.
A. G. Balan, A. J. Traina, L. M. Bortolotti and C. Traina Jr., "Content-based Image Retrieval Using Approximate Shape of Objects," Proceedings. 17th IEEE Symposium on Computer-Based Medical Systems(CBMS), Bethesda, Maryland, 2004, pp. 91.