A neural network based CBIR system using STI features and relevance feedback
Intelligent Data Analysis
ROI-based medical image retrieval using human-perception and MPEG-7 visual descriptors
CIVR'06 Proceedings of the 5th international conference on Image and Video Retrieval
| Hi-index | 0.00 |
Abstract: Many intrinsically 2-dimensional visual signals can be effectively encoded in a 1-D form. This simpler representation is well-suited to both pattern recognition and image retrieval tasks. In particular, this paper deals with contour and texture, combined together in order to obtain an effective technique for content-based image indexing. The proposed method, named CONTEXT, represents CONtours and TEXTures by a vector containing the location and energy of the signal maxima. Such a representation has been utilized as the feature extraction engine in an image retrieval system for image databases. The homogeneous treatment reserved to both contour and texture information makes the algorithm elegant and easy to implement and extend. The data used for experimentally assessing CONTEXT were contours and textures from various application do-mains, plus a database of medical images. The experiments reveal a high discriminating power which in turn yields a high perceived quality of the retrieval results.