Unlock instant, AI-driven research and patent intelligence for your innovation.

A Face Verification Acceleration Method Based on Convolution Theorem

A convolution theorem and face verification technology, which is applied in the field of face verification in computer vision, can solve problems such as slow running speed and large computational burden of the face verification system

Active Publication Date: 2019-01-29
深圳市小枫科技有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Face Verification Acceleration Method Based on Convolution Theorem
  • A Face Verification Acceleration Method Based on Convolution Theorem
  • A Face Verification Acceleration Method Based on Convolution Theorem

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. In the present invention, GPU is used as the computing platform, CUDA is used as the GPU parallel computing framework, and Caffe is selected as the CNN framework.

[0055] The specific implementation steps are as follows:

[0056] Step 1: Judging whether the acceleration condition is satisfied by the input parameters of the convolutional layer.

[0057] When both K and L are greater than 100 or P is greater than 5, this method can achieve an acceleration effect.

[0058] Step 2: Input image and convolution kernel size expansion.

[0059] Use CUDA_KERNEL_LOOP parallel loop to create N threads, each thread handles the expansion operation of a pixel in the image, and N threads perform the expansion operation in parallel.

[0060] Expanding the size of the input image and convolution kernel requires additional cache space. The parameters of each...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

A face verification acceleration method based on convolution theorem belongs to the field of face verification in computer vision. For the face verification system using CNN technology, on the basis of using the GPU parallel computing platform, for the convolution layer that meets the acceleration conditions, the convolution theorem method is used to replace the conventional convolution calculation method for convolution calculation. The convolution theorem states that convolution in the spatial domain is equivalent to product in the frequency domain. By converting the time-consuming convolution calculation into the product calculation in the frequency domain, the calculation amount can be significantly reduced and the calculation speed of CNN can be accelerated. Aiming at the problems of heavy calculation burden and slow operation speed of the face verification system, the present invention significantly improves the operation speed of the face verification system and improves the processing ability of massive data.

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 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 applied to login verification, identity Recognition and many other scenarios have received extensive attention and research. The goal of face verification is to judge whether the faces in two face pictures are the same person. It mainly consists of three parts: face image preprocessing, feature extraction, and feature measurement. After the introduction of deep learning, especially after the great success of the application of convolutional neural networks ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00
CPCG06V40/16
Inventor 刘波郭申
Owner 深圳市小枫科技有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com