Light field face recognition method based on deep belief network

A deep belief network and face recognition technology, which is applied in character and pattern recognition, image data processing, instruments, etc., can solve the problems of backward progress in 3D face recognition, and achieve the effect of broad application prospects

Active Publication Date: 2017-02-15
SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current progress in 3D face recognition is relatively backward.

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
  • Light field face recognition method based on deep belief network
  • Light field face recognition method based on deep belief network
  • Light field face recognition method based on deep belief network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] Embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. It should be emphasized that the following description is only exemplary and not intended to limit the scope of the invention and its application.

[0034] According to an embodiment of the present invention, such as figure 1 As shown, the DBN-based light field face recognition method can include four parts: light field camera image acquisition, 4D light field reconstruction, image preprocessing, and DBN classifier processing.

[0035] 1. Light field camera image acquisition

[0036] This part uses a light field camera to collect face data. It can collect photos of people's front face, side face, and glasses occluded under strong light conditions, and can also collect front face, side faces, and glasses occluded photos under dark light conditions. , to build a face image database. The light field camera can be a known Lytro camera.

[0037] 2. 4D lig...

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

Provided is a light field face recognition method based on a depth belief network. The method comprises the steps that a 4D light field sub-hole image array needed in face recognition is reconstructed based on a face image collected by a light field camera to obtain a training set; b, face image collection is carried out on an object to be recognized through the light field camera, and the 4D light field sub-hole image array is reconstructed based on a face image of the object to be recognized to obtain a testing set; c, the training set is input into a DBN classifier to train the DBN classifier; d, the testing set is input into the trained DBN classifier, and the DBN classifier determines and outputs a recognition result. By applying the method to face recognition, an excellent effect can be obtained. The method has the advantage that 2D face images can be easily collected and operated, thereby having broad application prospect.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a light field face recognition method based on Deep Belief Networks (DBN for short). Background technique [0002] Many modern face recognition methods are based on image features such as local binary features and SIFT features. Instead of trying to find new image features, it is better to apply machine learning related methods to automatically learn related features. In recent years, the research of deep learning on two-dimensional face recognition has achieved certain results. However, the current progress in 3D face recognition is relatively backward. Contents of the invention [0003] The main purpose of the present invention is to provide a light field face recognition method based on a deep belief network for the deficiencies of the prior art. [0004] To achieve the above object, the present invention adopts the following technical solutions: [0005]...

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): G06K9/00G06T7/00
Inventor 袁春顾兵
Owner SHENZHEN GRADUATE SCHOOL TSINGHUA 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