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

Face recognition device, image processing method, feature extraction model and storage medium

An image processing and face feature technology, applied in the field of face recognition, can solve the problem of low robustness of face features, and achieve the effect of improving accuracy and robust feature expression

Active Publication Date: 2019-09-17
SHENZHEN TCL NEW-TECH CO LTD
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, deep neural networks are currently used to extract facial features, and the extracted facial features are not robust to changes in lighting, expression, etc.

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
  • Face recognition device, image processing method, feature extraction model and storage medium
  • Face recognition device, image processing method, feature extraction model and storage medium
  • Face recognition device, image processing method, feature extraction model and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0045] The main solution of the embodiment of the present invention is: obtain target human face image; Adopt Gabor filter to carry out Gabor filtering process on described target human face image, obtain the first characteristic image, adopt the preset module in deep convolutional neural network to pair The target face image is subjected to convolution and pooling processing to obtain a second feature image; according to the first feature image and the second feature image, a face feature image corresponding to the target face image is generated.

[0046] Because the face features extracted by the deep convolutional neural network in the prior art are not robust to changes in illumination and expression.

[0047] The invention provides an image processing method, which can improve the accuracy of human face feature e...

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 an image processing method. The image processing method comprises the following steps: obtaining a target face image; carrying out Gabor filtering processing on the target face image by adopting a Gabor filter to obtain a first feature image, and carrying out convolution and pooling processing on the target face image by adopting a preset module in a deep convolutional neural network to obtain a second feature image; and generating a face feature image corresponding to the target face image according to the first feature image and the second feature image. The invention also discloses a face feature extraction model, a face recognition device and a readable storage medium. The invention aims to improve the accuracy of face feature extraction, so that the extracted face features have more robust feature expression.

Description

technical field [0001] The invention relates to the technical field of face recognition, in particular to an image processing method, a face feature extraction model, a face recognition device and a readable storage medium. Background technique [0002] How to extract face description features in face recognition is a key step. The information of the face image is mainly composed of two parts. One is the characteristics of the identity of the face, such as glasses, nose, mouth, etc., which belong to the essential attributes of the face; the other is caused by external factors, such as the light when taking pictures. , shooting angle, etc. The ideal face description features should only reflect the essential attributes of the face, and not be sensitive to external face features such as illumination and posture. However, deep neural networks are currently used to extract facial features, and the extracted facial features are not robust to changes in illumination and expressi...

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): G06K9/00G06N3/04
CPCG06V40/171G06V40/172G06N3/045Y02D10/00
Inventor 赖长明徐永泽薛凯文
Owner SHENZHEN TCL NEW-TECH CO LTD