Multi-angle human face detecting method based on weighting of deformable components

A technology of deformed parts and angled people, applied in the field of pattern recognition and machine intelligence, can solve problems such as false detection, missed detection, simplicity, etc., and achieve the effect of reducing the missed detection rate, solving missed detection and false detection, and reducing the false detection rate

Inactive Publication Date: 2012-08-01
XIDIAN UNIV
View PDF6 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these models treat each component equally, and cannot better play the role of important components in the detection process. Moreover, the multi-model fusion method is too simple to cause a large number of false detections and missed detections.

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
  • Multi-angle human face detecting method based on weighting of deformable components
  • Multi-angle human face detecting method based on weighting of deformable components
  • Multi-angle human face detecting method based on weighting of deformable components

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be described in detail below in conjunction with specific embodiments.

[0033] The meanings of the letters involved in the text are as follows:

[0034] beta m : The parameters of the mth part model obtained by using the mth formal training set subset and its label training;

[0035] The jth part of the mth part model;

[0036] The position of the jth part of the mth part model;

[0037] The weight of the jth component of the mth component model;

[0038] use the kth candidate hypothesis detected by the mth model;

[0039] db m : The threshold after the mth component model is reduced;

[0040] ct: threshold for skin color verification;

[0041] The component position is assumed to be L m The feature vector extracted when

[0042] L m : { l m 0 , . . . , l ...

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 multi-angle human face detecting method based on weighting of deformable components. The method includes a model building process and a human face detecting process. Different weights are set on different components of a human face according to different contributions of the different components to a detection effect, and effects on important components can be sufficiently utilized assuredly. The problem in terms of large-angle human face detection is resolved by a multi-model fusion method, omission ratio is decreased by means of reducing a threshold value in a detection process, and false detecting ratio is decreased by means of a skin color confirming mode in a model result fusion process. The multi-angle human face detecting method effectively resolves problems of omission and false detection in the human face detecting process based on the components, and can be widely applied to the fields of safety detection, identity authentication, intelligent transportation and the like.

Description

technical field [0001] The invention belongs to the field of pattern recognition and machine intelligence technology, and specifically relates to a multi-angle face detection method based on deformable component weighting, which can be used in security detection, identity authentication, intelligent transportation and other fields in complex scenes. Background technique [0002] Face detection is the first step in face analysis, which involves confirming whether there is a face in the input picture or video, and how to locate the position of the face after confirming the face. Due to the rich internal changes of the face and the changes of external conditions, there are many difficulties and challenges in the field of face detection technology, such as different ages, appearances, expressions, etc. All factors seriously interfere with the normal implementation of face detection. [0003] Component-based detection originated in the 1970s (the so-called components, that is, t...

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): G06K9/62G06K9/00
Inventor 赵恒张春晖尹雪聪梁继民
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap