Image retrieval method, device and computer-readable storage medium

Abstract

The invention relates to the field of computer vision, and provides an image retrieval method, device and computer-readable storage medium to accurately and efficiently retrieve images with complex backgrounds and / or small ROIs. The method comprises: performing dimensionality reduction operations on the features of each convolutional layer of the image to be retrieved to obtain each dimensionality reduction feature; performing clustering based on each dimensionality reduction feature to obtain multiple clustering features; performing feature extraction on multiple clustering features Fusion to obtain the global feature; based on the global feature, the image to be retrieved is retrieved from the database. In one aspect of the present invention, by performing dimensionality reduction operations on the features of each convolutional layer of the image to be retrieved, the Region Of Interest (ROI) can be changed into an arbitrary shape, reducing the impact of noise on image retrieval results; the other On the one hand, through clustering operations based on each dimensionality reduction feature, multiple clustering area features are obtained, which minimizes the impact of factors such as illumination, angle, and occlusion on image features.

Description

technical field [0001] The invention belongs to the field of computer vision, and in particular relates to an image retrieval method, device and computer-readable storage medium. Background technique [0002] Image retrieval refers to the task of returning an image that is closest to the image to be retrieved by searching the database given an image to be retrieved. Image retrieval is an important problem in computer vision and image analysis. Image retrieval has some important applications in many fields, such as product recommendation, security monitoring, and medical diagnosis. [0003] Although the industry has invested a lot of effort in researching image retrieval, it is a pity that image retrieval is still a complex and difficult problem. The retrieval accuracy and efficiency of image retrieval are affected by many factors. This is because, on the one hand, the complex image background often has serious interference on the region of interest, which affects the accur...

AI Technical Summary

Problems solved by technology

[0003] Although the industry has invested a lot of effort in researching image retrieval, unfortunately, image retrieval is still a complex and difficult problem

The retrieval accuracy and efficiency of image retrieval are affected by many factors. This is because, on the one hand, the complex image background often has serious interference on the region of interest, which affects the accuracy of retrieval; on the other hand, in large-scale In the process of image retrieval, images often reach millions or even larger, and image retrieval has very high requirements for real-time performance, so the algorithm for image retrieval must be very efficient and fast

However, many existing image retrieval algorithms often cannot accurately and efficiently extract effective retrieval schemes for images with complex backgrounds or small Region Of Interest (ROI), and thus cannot extract good features for retrieval.

Images