Color Image Segmentation and Recognition based on Shape and Color Features

摘要: Recent advances in computer technology have made it possible to create databases for large number of images. A major approach directed towards achieving CBIR is the use low-level visual features image data segment, index and retrieve relevant images from database. Segmentation partition a digital into regions simplify representation something that more meaningful easier analyze. Color based segmentation significantly affected by choice color space. In different spaces, L*a*b space better content an image. this paper K- means algorithm used Shape description or important issue both object recognition classification. After focuses on shape descriptor- eccentricity efficient effective retrieval performance. The proposed method applied database containing 2600 fruit