An Effective Method for Mammograph Image Retrieval
Junding Sun, Zhaosheng Zhang · 2008
A novel retrieval method for mammograph images was proposed in this paper. The texture structure of mammograph image was firstly extracted by the maximum and minimum of local intensity. Then, a new texture feature, distortion constraint, was introduced based on the speciality of the region of interest. Combined with the weighted moments, the new descriptor was given as an index for mammograph image retrieval. By comparing with the existing methods, experiment results show that the new method has higher performance and efficiency in retrieval and classification of mammograph images.