Chest DR Image Classification Based on Support Vector Machine

For increasing the classification accuracy of chest DR images between normal and lesion images, and improving the deficiencies of poor generalization ability of traditional statistical theory, a kind of medical image classification method adapting small samples was proposed. In order to get the decision-making function, SVM classifier was applied to study on training set of chest DR images. The test samples were divided into two categories, normal and lesion images. The experimental results show this approach simple and effective, and get good results in the case of small samples. In the medical conditions of limited clinical cases, this method can be used as a tool for early diagnosis and help doctors improving the recognition accuracy rate. The method has a good application value.