AbstractsMedical & Health Science

With the availability of easy and inexpensive methods to create and newlinestore images in digital formats the visual information preserved and shared newlineelectronically has grown dramatically Efficient image searching, browsing newlineand retrieval tools are required by users from various domains including newlineremote sensing, crime prevention publishing medical forensic etc For this newlinepurpose many general purpose image retrieval systems have been developed newlineText based image retrieval are based on language but variations in annotation newlinewill pose challenges to image retrieval Content based image retrieval relies newlineon the characterization of primitive features such as color shape and texture newlinethat can be automatically extracted from the images themselves The main newlineargument leveled against these Content Based Image Retrieval systems newlineconcerns their lack of robustness to rotation and occlusion newlineAlso most of the conventional image retrieval systems lack the newlinecapability to utilize human intuition and emotion appropriately in the process newlineof image retrieval It is difficult to retrieve a satisfactory result when the user newlinewants an image that cannot be explicitly specified The difference between the newlineusers information and the image representation is called the semantic gap in newlineContent Based Image Retrieval systems The limited retrieval accuracy of newlineimage centric retrieval systems is basically due to the inherent semantic gap newline newline%%%reference p146-160p.