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

Face detection and recognition method and device based on face key point correction

A face key point and face detection technology, applied in the field of computer vision, can solve the problems of low face recognition accuracy and slow recognition speed, and achieve the effect of improving recognition speed, recognition speed and accuracy.

Inactive Publication Date: 2019-05-24
北京英索科技发展有限公司
View PDF9 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the above problems, the present invention proposes a face detection and recognition model training method and device based on face key point correction and a face detection and recognition method and device based on face key point correction. The basic idea involves detection and recognition technology, In order to solve the problems of low accuracy and slow recognition speed of face recognition, it expands the scope of use of the face detection and recognition system

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 detection and recognition method and device based on face key point correction
  • Face detection and recognition method and device based on face key point correction
  • Face detection and recognition method and device based on face key point correction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] Embodiments of the present invention are described below with reference to the drawings. It can be understood that the specific implementation manners described here are only used to explain relevant content, rather than to limit the present invention. In addition, it should be noted that, for the convenience of description, only the parts related to the present invention are shown in the drawings. At the same time, it should be noted that, in the case of no conflict, the implementation modes and features in the implementation modes of the present invention can be combined with each other.

[0043] Such as figure 1 As shown, a kind of face recognition detection model training method based on face key point correction of the present invention comprises the following steps:

[0044]Step S11, firstly carry out the training of the first-level convolutional neural network, and for the multiple face images collected, manually mark or use traditional face key point detectors...

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 face detection and recognition method based on face key point correction. The method comprises a face detection and recognition model training method and a face detection andrecognition model using method. According to the face detection recognition model training method, a training data set is sent to a two-stage convolutional neural network for training, the first stage is a detection correction network, and detection part model training is completed; And the second level is an identification network to obtain an identification part model. The invention discloses aface detection recognition model using method. and inputting an image to be detected into the trained detection correction network to obtain a human face key point position coordinate, cutting and correcting the image to be detected according to the human face key point position, and inputting the corrected image into the trained recognition network to obtain human face identity recognition information.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a face detection and recognition method and device based on face key point correction. Background technique [0002] With the development of deep learning technology and the rapid improvement of computer computing power, the fields of artificial intelligence, computer vision and image processing are developing rapidly. Among them, face recognition, as a classic topic in the field of computer vision, has great research and application value, and has a high demand for it. The main problem solved by face recognition is that for an input image containing a human face, the algorithm can automatically extract the facial features on the image, and recognize the facial image according to the features, and give the recognition result. [0003] At present, face recognition related technologies have made great progress, and some successful applications have appeared. Traditional face recogn...

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
Inventor 张红武舒剑军
Owner 北京英索科技发展有限公司
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