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

Rotation invariant face detection method based on multi-task progressive registration network

A face detection, rotation invariant technology, applied in the field of image processing, can solve the problems of lack of image rotation change, scale change robustness, etc.

Active Publication Date: 2019-11-15
CHONGQING UNIV OF POSTS & TELECOMM
View PDF11 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

An important shortcoming of the existing typical DCNN face detection network is the lack of robustness to image rotation changes, scale changes, 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
  • Rotation invariant face detection method based on multi-task progressive registration network
  • Rotation invariant face detection method based on multi-task progressive registration network
  • Rotation invariant face detection method based on multi-task progressive registration network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The embodiment of the present invention is realized based on a cascaded multi-layer convolutional neural network. The image to be tested passes through all levels of multi-layer convolutional neural networks at one time, and each level of multi-layer convolutional neural network performs face classification, face candidate frame regression, Face key point detection and angle recognition tasks. Finally, the registration is performed by flipping the image according to the predicted rotation angle, and the registration image is judged as a face image.

[0024] In order to illustrate the technical solutions of the present invention, the following will be described in conjunction with the drawings and specific embodiments.

[0025] figure 1 The implementation process of the rotation-invariant face detection provided by the embodiment of the present invention is shown, and the details are as follows:

[0026] S1. Construct and train a cascaded multi-layer convolutional neur...

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 rotation invariant face detection method based on a multi-task progressive registration network, and belongs to the field of computer vision. The method mainly comprises thefollowing steps: preprocessing an image, and constructing and training a cascaded multilayer convolutional neural network; inputting a test image, generating image sets with different resolutions by using an image pyramid mode, and then sending the image sets into the cascaded multilayer convolutional neural network to start detection; filtering out a part of non-face windows by each level of network, adjusting the position of a candidate frame according to a frame regression result, and predicting the rotation angle of the face at the same time; and then carrying out registration through image overturning operation according to the predicted rotation angle. According to the invention, through a multi-task progressive registration network method, real-time and rotary self-adaptive face detection is realized, and good effects are achieved in precision and speed.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a rotation-invariant face detection method based on a convolutional neural network. Background technique [0002] Images containing human faces are essential for human-computer interaction based on intelligent vision. Face detection provides rich visual information for intelligent analysis of the above targets, which can be used to identify objects of interest in images. At the same time, the research on face detection has also become an unavoidable basic problem in the fields of image processing, computer vision and pattern recognition, and has been widely concerned by researchers. The progress made in face detection has played an important supporting role in many problems in the field of computer vision and pattern recognition, such as face recognition, video tracking, head pose estimation and gender recognition. [0003] The research on face detection of human object...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/165G06V40/172G06N3/045G06F18/241
Inventor 周丽芳谷雨雷帮军李伟生
Owner CHONGQING UNIV OF POSTS & TELECOMM
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com