An Optimized Neural Network for Content Based Image Retrieval in Medical Applications

The Content-Based Image Retrieval (CBIR) is a widely used approach for finding and retrieving related pictures. It is useful in medical applications for detecting disorders like cancer in the individuals. A lot of previous strategies for increasing the performance of the CBIR were described. CBIR's retrieval time and accuracy, however, can yet be improved. In CBIR, an optimum classifier will be employed to address this problem. In this work, the PSO-ANN is a classifier to detect the events. In addition, visual properties are extracted and these retrieved features will be grouped using the k-means clustering algorithm to enhance the classification process. The suggested classifier is used to recover the similar images of the query image are from clustered features. The simulation results shows that this framework have high accuracy and minimum time with previous approaches.