Single-image human face posture estimation method based on depth value

A face pose, single image technology, applied in computing, computer parts, instruments, etc., can solve the ill-conditioned pose estimation process, the lack of depth information of face features, and the inability to distinguish between interior and exterior points. question

Active Publication Date: 2017-04-19
SANMING UNIV
View PDF1 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Based on the following points: (1) Multi-pose two-dimensional face image recognition is still the mainstream; (2) The geometric relationship method of facial feature points has the advantages of simplicity, short time consumption, and high efficiency; (3) Most of the existing pos

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
  • Single-image human face posture estimation method based on depth value
  • Single-image human face posture estimation method based on depth value
  • Single-image human face posture estimation method based on depth value

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0103] The present invention will be further described below in conjunction with the drawings and embodiments.

[0104] Please refer to figure 1 , The present invention provides a single image face pose estimation method based on depth value, which is characterized in that it comprises the following steps:

[0105] Step S1: Obtain a face image of the pose to be estimated;

[0106] Step S2: preprocessing, converting the face image to be estimated into a grayscale image, normalizing the grayscale value to [0,1], and performing denoising and normalization processing, and converting the processed grayscale image The size is unified to 64×64;

[0107] Step S3: For the preprocessed grayscale image, the affine transformation invariance initialization principle (ATIIA) is introduced to establish an initial model, the traditional active shape model (ASM) method is improved, and the two-dimensional values ​​of ten facial feature points are extracted. The ten facial feature points are the lef...

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 a single-image human face posture estimation method based on a depth value, and the method comprises the following steps: obtaining a human face with a to-be-estimated posture; converting the human face with a to-be-estimated posture into a gray scale image, and carrying out the noise reduction and standardization processing; introducing an affine transformation invariance initialization principle to build an initial model, improving a conventional active shape model method, and extracting the two-dimensional values of ten human face feature points; solving the depth values of ten human face feature points through the perspective imaging principle through employing an iteration algorithm; estimating a human face posture estimation target function; carrying out the primary estimation of the human face posture through four human face feature points, enabling the primary estimation value to serve as the input value for the least square optimization calculation of a target function, and outputting a human face posture result of secondary estimation; carrying out the further optimization of a least square optimization calculation result through employing an M-estimation algorithm, and outputting a final estimation result. The invention overcomes a pathological problem of posture estimation, and is good in posture estimation precision and robustness.

Description

technical field [0001] The invention relates to a single image human face attitude estimation method based on depth value. Background technique [0002] In recent years, although the development of depth camera technology and the advent of Microsoft Kinect have broken the situation of high prices of depth cameras in the past, and two new depth image databases, ETH Face Pose and Biwi Kinect, have appeared in the field of face pose estimation. In practical applications such as customs, airports, exhibition halls and other public places and public security systems for chasing criminals, it still takes time to collect and update the two-dimensional database to the three-dimensional database. Therefore, at present, multi-pose recognition for a single two-dimensional face image is still the mainstream . At present, the frontal face recognition system has achieved good recognition results, but the effective recognition of multi-pose face images is still not good. According to sta...

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
CPCG06V40/171
Inventor 邱丽梅吴龙邱思杰
Owner SANMING 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