Convolution theorem based face verification accelerating method

Abstract

The invention relates to a convolution theorem based face verification accelerating method, and belongs to the field of face verification in computer vision. For a face verification system adopting a CNN (Convolutional Neural Network) technology, a convolution theorem method is adopted to replace the conventional convolution computation method to perform convolution computation on a convolution layer meeting an acceleration condition on the basis of using a GPU parallel computation platform. The convolution theorem shows that convolution in the space domain is equivalent to product in the frequency domain. Through transforming time-consuming convolution computation into product computation in the frequency domain, the computation amount can be significantly reduced, and the computation speed of a CNN is accelerated. In allusion to problems of great computational burden and slow operation speed of the face verification system, the method enables the operation speed of the face verification system to be obviously improved, and the processing capacity for mass data can be improved.

Description

Technical field [0001] The invention belongs to the field of face verification in computer vision, and relates to an acceleration method for face verification, in particular to a face verification acceleration method based on the convolution theorem. Background technique [0002] With the development of society, people’s requirements for security and convenience are increasing. Face verification technology has made great progress in recent decades. It has the advantages of directness, friendliness, and convenience. It can be used in login verification and identity verification. Recognition and many other scenes have received extensive attention and research. The goal of face verification is to determine whether the faces in two face pictures are the same person, which is mainly composed of three parts: face image preprocessing, feature extraction, and feature measurement. After deep learning was proposed, especially after the application of convolutional neural networks (CNN) in...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problems of large computational burden and slow running speed of the face verification system, the purpose of the present invention is to provide an implementation scheme for face verification acceleration based on the convolution theorem

Images