Web Based Medical Image Retrieval System Using Fuzzy Connectedness Image Segmentation and Geometric Moments

Medical image database is growing day by day. There are various categories of medical images such as CT scan, X- Ray, Ultrasound, Pathology, MRI, Microscopy, etc [1]. Physicians compare previous and current medical images associated with patients to provide right treatment. Medical Imaging is playing a leading role in modern diagnosis. Efficient image retrieval tools are needed to retrieve the intended images from large growing medical image databases. Such tools must provide more precise retrieval results with less computational complexity. This paper proposed fuzzy connectedness image segmentation for medical image retrieval in Oracle using digital imaging and communications in medicine (DICOM) format. Paper includes the comparison of image retrieval techniques with the proposed fuzzy connectedness image segmentation combined with geometric moment. Paper also gives the implementation details of proposed algorithm in Oracle. For the analysis purpose we have implemented feature extraction methods for color, texture and shape based feature extraction. These methods are compared with the proposed algorithm.