Large-scale face recognition method based on depth convolution neural network model

A neural network model and deep convolution technology, applied in the fields of artificial intelligence and computer vision, can solve problems such as large-scale face recognition difficulties, and achieve the effect of solving complex model construction, excellent results, and simple model structure.

Active Publication Date: 2017-06-20
FUDAN UNIV
View PDF5 Cites 43 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The purpose of the present invention is to provide a large-scale face recognition method based on a deep convolutional neural network model to improve the accuracy of face recognition and solve the problem of difficulty in large-scale face recognition in current practical application scenarios

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
  • Large-scale face recognition method based on depth convolution neural network model
  • Large-scale face recognition method based on depth convolution neural network model
  • Large-scale face recognition method based on depth convolution neural network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The specific implementation of the present invention, the deep convolutional neural network model based on residual learning in the million-level face recognition task is explained below in conjunction with the accompanying drawings, and the specific operation steps of the realization are as attached figure 1 shown.

[0051] 1. Preprocess the image

[0052] First use the image processing tool MTCNN [19] Detect the face in the picture, then use MTCNN to detect 5 key points in the face (two eyes, nose tip, corners of mouth on both sides), and then face alignment method [20] Face alignment is performed, and finally the size of the processed image is normalized to 112×96.

[0053] 2. Build the deep convolutional neural network model based on residual learning proposed by the present invention

[0054] Using the deep learning framework Caffe, build the deep convolutional neural network model based on residual learning proposed by the present invention, as shown in the att...

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

The invention belongs to the technical field of computer vision and artificial intelligence, and particularly relates to a large-scale face recognition method based on a depth convolution neural network model. The method comprises steps of putting forward a residual error learning depth network model facing large-scale face recognition, wherein the residual error learning depth network model is formed by a convolution layer, a residual error layer and a full connection layer, and the residual error layer is formed by adding one path of multiple convolution layer cascade data and one path of original data to calculate the sum; and carrying out normalization operation in batch after each convolution layer in the model. According to the invention, by use of the characteristics of strong learning ability and good residual error learning convergence of the depth convolution neural network, layers of the model are increased in the aspect of the layer number of the network model; and in the aspect of residual error layer structure, the invention provides a highly efficient residual error layer structure. In the field facing the large-scale face recognition, the accuracy of the provided method is greatly improved compared with a base line model, and the accuracy of face retrieval in a million-class face recognition database can reach 74.25%.

Description

technical field [0001] The invention belongs to the technical fields of computer vision and artificial intelligence, and in particular relates to a large-scale face recognition method. Background technique [0002] With the rapid improvement of machine learning technology and computer hardware performance, breakthroughs have been made in recent years in computer vision, natural language processing and speech recognition and other application fields. Face recognition is a basic task in the field of computer vision, and its accuracy has also been greatly improved. [0003] In the past few years, many large technology companies and famous research institutions have proposed many efficient face recognition methods, and the accuracy rate on the industry's most famous face evaluation set LFW exceeds 99%. Such remarkable results are mainly attributed to two aspects: deep learning and massive data. Deep learning solves the problem of feature expression in face recognition. Compare...

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 Applications(China)
IPC IPC(8): G06K9/00G06N3/08
CPCG06N3/08G06N3/084G06V40/171G06V40/172
Inventor 王展雄邵蔚元冯瑞
Owner FUDAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap