Medical Image Retrieval and Classification Based on Morphological Shape Feature

摘要

Medical Image Retrieval and Classification is very important in Computer-Aided Diagnosis. Feature extraction is one of the most important techniques in content based image retrieval and classification. How to extract low-level features which reflect high-level semantics of an image is crucial for medical image retrieval and classification. In allusion to this issue, there proposed a method using edge density histogram to extract shape feature of medical images in this paper. Then Euclidean distance and Support Vector Machine (SVM) are used for medical image retrieval and classification. Results of experimentation showed that the proposed algorithm has been applied to medical image retrieval with promising effect.