Research On Content-Based Image Retrieval

Due to the steady growth of computer, multimedia and Internet techniques, a huge amount of images are available. Currently, rapid and effective searching for desired images from large-scale image databases becomes an important and challenging research topic. Content-based image retrieval (CBIR) is the set of techniques to address the problem of retrieving relevant images from an image database based on automatically derived image features. In recent years, CBIR has became one of the most active research focuses of implementation of multimedia, and has been applied to many fields.The main contents of this paper are summarized as follows:1. Several key techniques and algorithms of CBIR are analyzed and discussed , such as , the relevance feedback, the low-level feature descriptions including color, shape, and texture, and the similarity measure between images.2. A novel algorithm for image retrieval based on interest points is presented, which utilizes the location information of the interest points, extracts the local color moment feature and shape invariant moment feature. This algorithm is not only robust to translation and rotation, but also avoids the drawbacks of losing the location information in color moment and shape invariant moment. Experimental results show that this algorithm effectively improves the image retrieval accuracy due to combining color and shape features.3. A novel algorithm for image retrieval based on region entropy is proposed, which divides an image into higher and lower entropy regions and extracts the color and shape features with each type of regions. The retrieval procedure consists of two steps: firstly, a simple retrieval algorithm in terms of entropy feature is applied to all the images in the database, and secondly, only the results of the previous retrieval are searched. Experimental results have shown that the proposed method has sound and robust retrieval performance to the images with simple foreground or complex foreground.4. Designed a CBIR system named imSearch, which is an experimental frame system. The development environment is Visual C++6.0.