The key requirement in medical imaging systems is to be able to display images relating to a particular disease, there is increasing interest in the use of Image Retrieval techniques to aid diagnosis by identifying the region of abnormalities from bio-medical images. Bio-medical images, such as pathology slides, usually have higher resolution than general-purpose pictures. In this paper an evolutionary computing based technique for classification of biomedical images on the basis of combined feature vector, which combines color and texture feature into a single feature vector, is presented. The system uses concept based on pixel descriptors, which combines the human perception of color and texture into a single vector, with the extraction of region of interest. The region extracted using the feature vectors represented in the form of pixel descriptor are fed as input to a neural network, which is trained for classification of images using genetic algorithm. The technique has been implemented on the database of biomedical images. Some of the experimental results are reported in the paper. The medical community can be assisted with this technique in diagnosing the disease.
展开▼
