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

Face feature point detection method based on ASM

A face feature and point detection technology, which is applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve the problems of failure to extract face feature points, affect the accuracy of face feature points, and local optimum, and achieve the best results Good, easy-to-implement effect that keeps things simple

Active Publication Date: 2017-07-25
SHENZHEN LAUNCH DIGITAL TECH
View PDF6 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when localizing feature points, local texture features are usually used for search and matching, and local texture features only contain part of the neighborhood information of the current feature point, which can easily cause local optimal problems in the matching process, resulting in the failure of face feature point extraction. Failed, affecting the accuracy of face feature point detection

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 feature point detection method based on ASM
  • Face feature point detection method based on ASM
  • Face feature point detection method based on ASM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0019] A face feature point detection method based on ASM, which includes a model building part and a model matching part, wherein the model building part is carried out according to the following steps, and the flow chart of the model building part is as follows figure 1 The left part shows:

[0020] (1) Mark training samples: use N face images as training samples, and mark n ordered feature points in each face image, then all feature points of the i-th image can be expressed as a feature vector:

[0021] x i =(x i1 ,y i1 ,x i2 ,y i2 ,...,x in ,y in ) T ,

[0022] Where (xia, yia) is the coordinate of the a-th feature point in the i-th image, and T represents the transpose of the matrix.

[0023] (2) Set the weight of feature points: Since the stability of each feature point in all feature points of the face is different (such as the feature points on the contours of the nose, chin, cheeks, etc., the range of changes with facial expressions is small, so the feature p...

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 relates to the technical field of image processing and mode recognition, and discloses a face feature point detection method based on ASM. The method also describes extra features of face feature points on the basis of traditional ASM algorithm. Specifically, the method describes HOG information of neighborhood in addition to local texture features, combines a HOG feature vector with a texture feature vector to form a feature descriptor which can provide higher resolution. Therefore, the method can fast and accurately select candidate feature points, and effectively increase the speed and precision of face feature point detection.

Description

technical field [0001] The invention relates to the technical fields of image processing and pattern recognition, in particular to an ASM-based face feature point detection method. Background technique [0002] With the urgent need for fast and efficient automatic identity verification technology in today's society, face recognition technology has become a current research hotspot due to its advantages of non-contact and simple acquisition equipment. Face recognition technology can be divided into three stages: face detection, feature extraction, and classification recognition. Among them, face detection and feature extraction are the basis of face recognition algorithms. The accuracy of facial positioning and the richness of feature information extraction in the process of face detection It directly determines the final effect of face recognition. [0003] Face detection can be roughly detected using a Haar feature based face detector. Haar feature (Haar-like feature) is ...

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): G06K9/00G06K9/62
CPCG06V40/168G06V40/172G06F18/253
Inventor 彭志远李星明段晶晶
Owner SHENZHEN LAUNCH DIGITAL TECH
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