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

Yolo-based face detection and face alignment method

A technology of face alignment and face detection, which is applied in the field of face recognition, can solve the problems of slow face detection and alignment efficiency and inability to perform joint tasks, so as to improve generalization ability, prevent over-fitting problems, and improve efficiency Effect

Active Publication Date: 2017-11-17
上海荷福人工智能科技(集团)有限公司
View PDF6 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] In order to solve the above technical problems, the present invention provides a yolo-based face detection and face alignment method to solve the problem that MTCNN face recognition adopts a staged method for face detection and alignment, which is slow in efficiency and cannot perform joint tasks

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
  • Yolo-based face detection and face alignment method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In order to make the purpose, technical solutions and advantages of the application clearer, the application will be further described in detail in conjunction with the accompanying drawings and specific embodiments below. The schematic embodiments of the application and their descriptions are used to explain the application and do not constitute Undue limitation of this application.

[0031] like figure 1 As shown, a yolo-based face detection and face alignment method includes the following steps:

[0032] S1. Perform network training, which specifically includes the following steps:

[0033] S1-1. Create a face data set, randomly select face images with illumination changes, scale changes and scene changes on the LFW database, and divide 80% of these face images into training sets and 10% into test sets , the remaining 10% is classified as a verification set; the training set is used to build a pre-training model, the test set is used to test the generalization abil...

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 belonging to the field of face recognition discloses a yolo-based face detection and face alignment method. The method comprises steps of network training and network verification. At the step of network training, a face data set is established; an image in the face data set is marked; and a face detection and alignment database is reconstructed. Therefore, problems that the efficiency is low and joint tasks can not be carried out because face detection and alignment are carried out by means of stage division during MTCNN face recognition are solved; the robustness of face recognition and the generalization ability of the network are improved; and a problem of over fitting caused by a few of samples is solved.

Description

technical field [0001] The invention belongs to the field of face recognition and specifically designs a yolo-based face detection and face alignment method. Background technique [0002] Face recognition technology is based on human facial features to judge the input face image or video stream. First judge whether there is a human face, and if so, further give the position and size of the human face. And based on these information, the feature information of the face is further extracted, and finally it is compared with the known face to identify the identity of each face. Generally speaking, face recognition is divided into two steps. One is face recognition. The second is face alignment. In terms of face detection, the current face detection adopts the frame detection method, that is, the image is divided into several frames by network learning, the face is captured from several frames, and the face is extracted. The key point is confidence, and face alignment is to com...

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
IPC IPC(8): G06K9/00
CPCG06V40/172G06V40/161
Inventor 王兵杨燕平刘威鑫
Owner 上海荷福人工智能科技(集团)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

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