A New Method of Semantic Feature Extraction for Medical Images Data

0 IntroductionCurrently al most all medical i mage analysis systems usequantified color , shape and texture-based features orcombination of thosefeatures . We call thosefeatures as quan-tified features , which have several disadvantages :to extractlocal quantifiedfeatures needs the basic operation such as i m-age segmentation or edge extraction (for example,shape fea-ture) ; some features are based on the ground of one traitwithout consideration of other traits (For example,gray sta-tistic fea…

A new method of semantic feature extraction for medical images data

In order to overcome the disadvantages of color, shape and texture-based features definition for medical images, this paper defines a new kind of semantic feature and its extraction algorithm. We firstly use kernel density estimation statistical model to describe the complicated medical image data, secondly, define some typical representative pixels of images as feature and finally, take hill-climbing strategy of Artificial Intelligence to extract those semantic features. Results of a content-based medial image retrieve system show that our semantic features have better distinguishing ability than those color, shape and texture-based features and can improve the ratios of recall and precision of this system smartly.