Combining Color, Texture and Region with Objects of User's Interest for Content-Based Image Retrieval

Content-based image retrieval (CBIR) systems normally return the retrieval results according to the similarity between features extracted from the query image and candidate images. In certain circumstance, however, users concern more about objects of their interest and only wish to retrieve images containing relevant objects, while ignoring irrelevant image areas (such as the background). Previous work on retrieval of objects of user's interest (OUT) normally requires complicated segmentation of the object from the background. In this paper, we propose a method that utilize color, texture and shape features of a user specified window containing the OUI to retrieve relevant images, whereas complicated image segmentation is avoided. We use color moments and subband statistics of wavelet decomposition as color and texture features respectively. The similarity is first calculated using these features. Then shape features, generated by mathematical morphology operators, are further employed to produce the final retrieval results. We use a wide range of color images for the experiments and evaluate the performance of the proposed method in different color spaces, including RGB, HSV, YCbCr. Although simple, the method has produced promising results.