With the development of computer and internet, collections of images are more common and are increasingly becoming larger. Hence, there is a need for tools to efficiently manage, organize and navigate through them. This makes the content-based image retrieval (CBIR) a very important and challenge research area. In recent years, CBIR is a very active research direction and has been applied to many fields. In this paper, the exploratory research work has been done around the low-level feature extraction, which includes color space, visual features and so on. The main contributions of this paper are summarized as follows: (1)Several key techniques and algorithms of CBIR are deeply analyzed and discussed, such as color space, the low-level features, the similarity measure between the features and the evaluation methods of image retrieval algorithms. (2)A new image retrieval method based on color histogram and spatial information is proposed. Firstly, the HSV space is quantized into nine subsets. Then, the spatial information of each subset is calculated. Finally, both the histogram and spatial information are used to retrieval image. (3) An image management and retrieval platform based on MPEG-7 is implemented. The main functions of this platform include image management, auto feature extraction, indexing and clustering and so on.
修改评论