Content Based Image Retrieval Method Based on SIFT Feature
Tao He, Yong Qi Wei, Zhijun Liu, Guorong Qing, Defen Zhang · 2018
To find images we require in the large scale image database, in this paper, we proposed a SIFT feature based content based image retrieval method. In the proposed image retrieval system, SIFT feature vectors are extracted from each original image, and then feature vectors are constructed. When a query image is given, SIFT feature vector is established for the query image, and then we search for the feature vector library to obtain visual similarly images. Afterwards, visual similarly images are returned to the user according to visual similarity computing results. The main innovation of this paper lies in that we introduce SIFT descriptor to represent visual content of images, and then utilize the distance ratio as the threshold to control the number of matched feature points. Experimental results demonstrate that the proposed method can retrieve visually similar images with high accuracy.