REDUCTION OF SEMANTIC GAP USING LOW LEVEL VISUAL FEATURES

Digital image libraries and other multimedia databases have been dramatically expanded in recent years. In order to effectively and precisely retrieve the desired images from a large image database, the development of a content-based image retrieval (CBIR) system has become an important research issue. Most of the existing approaches lack the capability to effectively incorporate human intuition and emotion into retrieving images. In order to reduce the semantic gap the proposed approaches emphasize on finding the best representation for dif erent image features. Furthermore, very few of the representative works will consider the user's subjectivity and preferences in the retrieval process. In this project, a user-oriented mechanism for CBIR method based on low level visual features like color texture, histogram and correlation are used. Color attributes like the mean value, the standard deviation were used. The entropy based on the gray level co-occurrence matrix of an image is considered as the texture feature. Further the histogram values are used for effective image retrieval process; finally the images are compared using correlation values at both the ends. The efficiency of proposed technique is evaluated and the experimental result indicates that it outperforms other existing systems. In this project based on reduction of I have used corel datasets is used which consist of 1000 images of varying 10 semantic contents, out of which 100 images were used.