Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Low-Resolution Face Recognition Method Based on Sparse Representation of Subparts and Compressed Dictionary

A technology of sparse representation and compressed dictionary, applied in the field of low-resolution face recognition, which can solve problems such as limited posture judgment methods

Active Publication Date: 2020-08-18
NANJING UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, using dictionaries of different poses for the test set of different poses improves the computational efficiency, but is limited by the pose judgment method

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
  • Low-Resolution Face Recognition Method Based on Sparse Representation of Subparts and Compressed Dictionary
  • Low-Resolution Face Recognition Method Based on Sparse Representation of Subparts and Compressed Dictionary
  • Low-Resolution Face Recognition Method Based on Sparse Representation of Subparts and Compressed Dictionary

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0100] The present invention is verified on the COX database. The COX data set is a relatively large-scale face recognition data set. It has 3000 sections of video of 1000 people and one high-definition face image for each person, and three sections of video for each person. Shot by three different cameras, the three videos form a set of experiments with each other. People move in different routes in front of the camera. In addition to the movement of the person itself, there are changes in posture, expression, illumination, and occlusion within and between the three videos. In addition, the video itself is low-resolution, which adds difficulties to recognition. The data set divides 300 people as the training set and 700 people as the test set for the experimenters. Such as figure 2 Shown is a schematic diagram of the division method. The sparse representation method used in the present invention has no training process shown, so 700 people are directly used for testing. ...

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 discloses a low-resolution face recognition method based on component and compressed dictionary sparse representation, and belongs to the fields of signal processing, mode recognition, machine learning and computer vision. When the dictionary is constructed, images capable of sparsely representing all video frames in the video are selected as representative frames, and then the HOG features of the representative frames and the mirror images of the representative frames are used for constructing the part dictionary. During testing, the dictionary is used for representing each frame of a tested video in a linear mode, a feedback mechanism is added to correct an abnormal recognition result, and finally voting is carried out to obtain a video classification result. According to the method, the sparse representation is applied to video face recognition, the robustness of the sparse representation to shielding and noise is kept, other steps are added to improve the effect and efficiency of the method in large-scale low-resolution video face recognition, and the defects of the method under the conditions of illumination change and the like are overcome.

Description

technical field [0001] The invention belongs to the fields of signal processing, pattern recognition, machine learning and computer vision, and in particular relates to a low-resolution face recognition method based on sub-components and sparse representation of compressed dictionaries. Background technique [0002] Since the late 20th century, hardware has developed rapidly, and digital images have become an important information carrier in contemporary society. With the continuous development of computer vision technology, more and more technologies have become practical products. Face recognition is a biometric technology for identification based on human facial feature information. It has the advantages of non-intrusive, convenient, and non-contact. Face recognition technology is developing very rapidly, especially with the advent of deep neural networks, which makes robot face recognition similar to or even surpass the recognition ability of human eyes. However, altho...

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
Inventor 肖琼琳杨若瑜李俊
Owner NANJING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products