A Multiple Feature Fusion Based Image Retrieval Algorithm

Abstract

With the rapid development of information technology, how to quickly retrieve the target image from massive image data has become a research hotspot in the field of image processing. In this paper, we propose an image retrieval algorithm based on multiple feature fusion. Our idea is to improve existing image retrieval algorithms that are only done with a single feature extraction. First, we combine the global features and local features of the image by setting different weights, and then further retrieve based on the adaptive coefficients of the fusion features. Experimental results show that our retrieval speed and accuracy of the algorithm is better than single feature extraction, which improves the query efficiency. It has a good P-R curve and has good application value in the field of image retrieval.