Abstract: In order to improve the detection performance of mass, which lies on the similar appearance between masses and density tissues in the breast, an support vector machine classifier based on typical features is designed to classify the ROIs. Furthermore, the relevance feedback is introduced to improve the performance of support vector machine. Then a new mass detection scheme based on support vector machine and Relevance Feedback is proposed. Simulation experiments on mammograms illustrate that the support vector machine classifier based on typical features can improve the detection performance of the featureless support vector machine classifier by 5%, while the introduction of relevance feedback can further improve the detection performance to about 90%.

Key words: support vector machine, relevance feedback, mass detection, feature extraction