An Image Retrieval Algorithm Based on Region Segmentation

Abstract

Visual image, as a kind of rich content and performance of multimedia information, has been tremendously popular for a long time. Image retrieval technology is complicated than text retrieval, due to text-based image retrieval is often need manual annotation, so very laborious and individual subjective factors are there. In order to solve these problems, this paper puts forward a kind of image retrieval algorithm based on improved region segmentation. First, use of image segmentation technology, dividing the image into several regions, then to match each region and the being tested image, and obtained retrieval results in the end. It can be seen through experiment, the user only needs to submit a retrieval image, so it can greatly reduce the user's retrieval burden, and improve the efficiency of retrieval.