Content based image retrieval (CBIR) contains a set of techniques to process the visual features of a query image, in order to retrieve images semantically similar to it, in a database. To improve the performance of image retrieval systems, relevance feedback tool can b
More
Content based image retrieval (CBIR) contains a set of techniques to process the visual features of a query image, in order to retrieve images semantically similar to it, in a database. To improve the performance of image retrieval systems, relevance feedback tool can be used. In this research, to increase the effectiveness of the image retrieval systems, the fusion of two (multiple) short term learning methods based on relevance feedback is proposed. In the proposed method, fusion is performed in three levels: fusion in ranks, fusion in retrieved images, and fusion in similarities. To evaluate the performance of the proposed method, a CBIR system with 10000 images of 82 different semantic groups is employed. The experimental results confirm the superior of suggested method in terms of retrieval precision.
Manuscript profile
