Medical Image Retrieval Based on Color-Texture Algorithm and GTI Model

With DICOM, information of patient can be stored with the actual images. Content-based access to medical images for supporting clinical decision-making has been proposed to ease the management of clinical data. The paper presents a method of medical image retrieval based on color-texture correlogram and GIT model for endoscopic images. First we define a new image feature called color-texture correlogram which is the extension of color correlogram. The texture image extracted by texture spectrum algorithm is combined with color feature vector , then we calculate the spatial correlation of color-texture feature vector. In order to obviate the expensive computation, we have another way to calculate the pixels´ correlation to reduce its time complexity. Similarity measure is also the key technology during domain of image retrieval, GTI model is used in medical image retrieval for similarity measure, and the technique of relevance feedback is used in the algorithm to enhance the effectiveness of retrieval. Experiment results show that the method discussed in this paper is much more effective.