| Hi-index | 0.00 |
Image retrieval is an active research area in image processing, pattern recognition, and computer vision. Relevance feedback has been widely accepted in the field of content-based image retrieval (CBIR) as a method to boost the retrieval performance. In recent literature, many researchers have employed the conventional support vector machine (SVM) for relevance feedback. This dissertation presents a novel fuzzy support vector machine (FSVM) that solves the four major problems encountered by the conventional SVMs: small size of samples, biased hyperplane, over-fitting, and real-time. To improve the performance, a new dominant color descriptor (DCD) is also proposed. Experimental results based on two groups of Corel images show that the proposed system performs much better than the previous methods. It achieves high accuracy and reduces the processing time greatly.