Graded Retrieval Method Research for Medical Images

Fast, nicely retrieving similar image case from medical image database is very helpful for doctor to detect and make decision in difficulty case. This paper presents a new policy for medical images retrieval based on graded retrieving method. First, the four classical texture features, including texture energy, texture entropy, texture inertial moment and local texture calmness, are calculated by the co-occurrence matrix of the image, and utilized to accomplish the elementary retrieval. Second, the method makes use of the projection vector of the object outline using Canny edge operator to breed out the false alarms of the elementary retrieval and accomplish high-grade retrieval. Experiment results show that the method can achieve fairly high precision and recall.