Face matching method, device, equipment and storage medium

Abstract

The invention discloses a face matching method, device, equipment and a computer-readable storage medium. A target face region image and at least two face organ region images of a target face image are acquired through a candidate region network model, and then through cascading A convolutional neural network model, obtaining at least two target face feature points and corresponding feature vectors, combining the target face feature points to obtain a feature combination, according to the features of the target face feature points in the feature combination vector and the pre-established feature retrieval library, iteratively matching each combination to obtain an image set matching all feature combinations, and performing similarity calculation on the feature vector of the target face feature point and the image set to obtain the human Face matching results, the present invention can reduce the retrieval range, increase the retrieval speed, and improve the user experience.

Description

technical field [0001] The present invention relates to the field of computer image processing, in particular to a face matching method, device, equipment and computer-readable storage medium. Background technique [0002] Face image matching is an important branch in the field of image matching. With the advent of the automated information age, face image matching has more and more applications in real life. Because face information is unique, difficult to forge and easy to collect, it is widely used in access control systems, video surveillance and identity verification technologies. [0003] The existing face image feature matching process is to extract the face image features in the database, search according to the similarity with the target face image features, and sort according to the similarity, so as to realize the process of face verification. The current face retrieval method is to locate the key points of the face, and then according to the geometric attribute...

AI Technical Summary

Problems solved by technology

[0004] However, in the process of realizing the present invention, the inventors found that this traditional face feature matching process has the defect of poor robustness, and the cumbersome search mode of traversal type leads to slow search speed, low work efficiency, and the memory and CPU occupy Larger, does not meet the retrieval requirements of current real-time face recognition

Images