Block-based shielded face recognition algorithm

A technology of face recognition and block, which is applied in the field of block-based face recognition algorithm with occlusion, and can solve the problems of face recognition algorithm accuracy decline and other problems

Inactive Publication Date: 2018-11-13
FUDAN UNIV
View PDF3 Cites 41 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

As the occlusion ratio of the face area increases, the accuracy of the face recognition algorithm will drop significantly

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
  • Block-based shielded face recognition algorithm
  • Block-based shielded face recognition algorithm
  • Block-based shielded face recognition algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0068] The present invention uses the AR data set to carry out the experiment of occluded face recognition. The AR data set contains a total of 3276 face images of 126 people (including 70 men and 56 women), and each person has 26 face images, including Different facial expressions (normal, smiling, indifferent, angry), different lighting and occlusion situations (sunglasses, scarves). The occluded face images are three pictures of wearing sunglasses and three pictures of scarves under different lighting conditions. Some examples of face images in the AR dataset are as follows: image 3 shown.

[0069] Select 100 people (50 men and 50 women) from the AR face data set, randomly select 8 of the 14 unoccluded face images for each person as the training set, and the other 2 images of wearing sunglasses and 2 images of wearing Images of scarves serve as the test set. The test process is carried out in combination with the trained partial face block occlusion discriminant model. ...

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 image processing, and specifically discloses a block-based shielded face recognition algorithm. The algorithm comprises the following steps of: in an offline training stage, carrying out preprocessing operations such as face detection, geometric face normalization, illumination normalization, extracting four blocks such as a left eye, a right eye, anose and a mouth from a face image on the basis of the preprocessing result, training a network model of each block, extracting corresponding features, training a shielding judgement network of each block to obtain a shielding judgement result, finally fusing the features according to the shielding judgement result of each block, and constructing a K-D tree feature index; and in an online recognition stage, extracting face image features by adoption of a method same as the offline training stage, and carrying out feature query through a K-D tree index manner so as to obtain a recognition result. Experiment results prove that the algorithm has better correctness.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a masked face recognition algorithm based on blocks. Background technique [0002] Face recognition technology plays a very important role in biometric technology. For a long time, researchers have been working on the research of face recognition algorithms. With the passage of time, face recognition algorithms have been continuously proposed, and their accuracy and stability have also been continuously improved. Up to now, face recognition has played a huge role in identity authentication, video surveillance, person tracking and other fields. [0003] The commercialization of face recognition technology indicates that it has a high accuracy rate in a specific environment. The specific environment here means that the collection of face images needs to be based on controlled conditions, such as sufficient lighting, single expression angle, and occlusion. rat...

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): G06K9/00G06K9/62
CPCG06V40/161G06V40/168G06V40/172G06F18/214
Inventor 金城方巧璐吴渊张翌翀冯瑞薛向阳
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