Content-Based Image Retrieval Using Hierarchical Color and Texture Similarity Calculation

With the evolution of multimedia technology, the usage of large image database has rapidly increased. Content-based image retrieval has come up as an effective method for image retrieval and management. The use of a single image feature for image retrieval gives unsatisfactory results, therefore the usage of multiple image features is more often preferred. This paper introduces a novel method that combines both color and texture features of an image for image retrieval in a hierarchical manner and shows its advantage. This paper also introduces an effective method of image segmentation for feature extraction. The proposed hierarchical approach was applied to the standard INRIA dataset. A significant improvement in the recall and precision is achieved and is shown in the result section.