SVM Relevance Feedback in HSV Quantization for CBIR

In this research have implemented SVM relevance feedback technique in HSV quantization for CBIR. The proposed technique has two stages. The first stage performs image retrieval process based on results of distance measurement. The distance measurement used is Jeffrey Divergence with threshold 0.15. The second stage is image retrieval process based on SVM RF prediction model. The SVM RF model is formed based on user-provided feedback images. The users’ feedback images are labeled as positive and others are negative. The purpose of this study is to determine the best value of the constant C on the linear kernel and the best value of the constant (C, G) on the RBF kernel. The best value of the constants provided generates the best model of SVM RF in the HSV Quantization method so that improve the performance of the CBIR system. Performance measurements are evaluated based on precision, recall, F-measure, and accuracy values. Based on the results of experiments that conduct on Wang dataset obtained that (C, G) = (22.725, 22.725) is the best value on the RBF kernel. While C = 25.275 is the best value on SVM RF using linear kernel. The best of SVM RF technique is SVM RF using RBF kernel of second feedback. The SVM RF using RBF kernel increases the average precision value by 3.02%, the average recall value increasing amount 171.48%, the average F-Measure value increasing amount 80.34%, while the average accuracy value increasing amount 1.99% compared with the baseline. The SVM RF using RBF kernel obtains the best value on both the average recall value and the average F-Measure value compared to the state-of-the-art.