Human face key point positioning method and device

A face key point and positioning method technology, which is applied in the field of face key point positioning method and positioning device, can solve the problem that the SDM algorithm is difficult to achieve real-time calculation, and achieve the effect of fast speed and high precision

Inactive Publication Date: 2018-03-06
BEIJING SOHU NEW MEDIA INFORMATION TECH
View PDF9 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, the speed of the SDM algorithm is relatively difficult to meet the needs of real-time computing on the mobile terminal, and the actual test requires more than 90ms on a general mobile phone.

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
  • Human face key point positioning method and device
  • Human face key point positioning method and device
  • Human face key point positioning method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0044] Such as figure 1 As shown, it is a flow chart of Embodiment 1 of a method for locating key points of a human face disclosed by the present invention, including:

[0045] S101. Perform face detection on the target image to obtain a face image;

[0046] A more general face detection algorithm is used, including the face detection algorithm that comes with OpenCV (Open Source Computer Vision Library, open source computer vision library) or the algorithm 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 discloses a human face key point positioning method. The human face key point positioning method comprises the following steps: carrying out human face detection on an objective image toobtain a human face image; shrinking the human face image into a shrunk image with preset definition; extracting a first-stage key point from the shrunk image by a supervision descending regressor; mapping the first-stage key point to the human face image so as to judge a three-dimensional posture of the human face image; and selecting the corresponding combined random tree regressor to extract asecond-stage key point from the human face image on the basis of the three-dimensional posture. By a mode of combination of a supervision descending method and a combined random tree algorithm, the human face key points in the image are positioned, and meanwhile, high precision and high speed are ensured.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a face key point positioning method and a positioning device. Background technique [0002] Face key point location is mainly to predict the key points of the face through the image features of the face. The current main technical solutions include cascading regression and regressing the coordinates of key points through convolutional neural networks. Although the convolutional neural network regression scheme has high precision, it has a large amount of calculation and is difficult to optimize for real-time applications. Considering the limitation of the amount of calculation, the scheme of cascading regression is mostly used on the mobile terminal. [0003] The processing flow of cascade regression is to approach the final goal of regression, that is, the two-dimensional coordinates of key points, through cascading regressors step by step. In order to reduce...

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): G06K9/00
CPCG06V40/161G06V40/168
Inventor 肖锋赵壁原
Owner BEIJING SOHU NEW MEDIA INFORMATION TECH
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