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

Multi-scale face detection method based on angular point skin color detection

A face detection, multi-scale technology, applied to instruments, character and pattern recognition, computer components, etc., can solve problems such as large amount of calculation and difficult real-time detection

Inactive Publication Date: 2020-04-03
HUNAN UNIV
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These methods for face detection have achieved the goal of face detection to a certain extent, but the amount of calculation is huge, and it is difficult for real-time 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
  • Multi-scale face detection method based on angular point skin color detection
  • Multi-scale face detection method based on angular point skin color detection
  • Multi-scale face detection method based on angular point skin color detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The invention is a multi-scale human face detection method based on corner point skin color detection. It mainly includes the following five steps:

[0037] (1) Calculate the edge points of the image

[0038] (2) Select corner points from edge points

[0039] (3) Determine whether the corner pixel is a skin color corner

[0040] (4) Density clustering of skin color corner points

[0041] (5) Select the skin color corner points that meet the conditions to form the face area

[0042] The development language is python, the development environment is win10, the input of the method is an image, and the output is an image containing the face area mark. Specific steps are as follows:

[0043] The first step: calculate the edge points of the image

[0044] First grayscale the image, then perform Gaussian blur on the grayscale image with two different blur radii to obtain two Gaussian blurred images, and finally subtract the two images to obtain a result containing edge 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 provides a multi-scale face detection method based on angular point skin color detection. The method mainly comprises the following steps: (1) an image angular point extraction method based on Gaussian difference and edge gradient filtering; (2) a skin color corner filtering method; (3) a multi-scale face detection method based on density clustering. The center and the contour edge of the human face are determined by detecting the positions of the skin color angular points in the human face, and therefore, human face detection is achieved.

Description

technical field [0001] The invention relates to the field of artificial intelligence, and relates to a multi-scale human face detection method based on corner point skin color detection. Background technique [0002] Face detection refers to using the human face as the subject of target detection, determining whether there is a face in a given image, and estimating the position and size of the detected face. In recent years, the technology used for face detection has developed rapidly. It is the basis of face AI technologies such as face recognition, expression recognition, and face changing, and plays an important role. Face detection is a very simple task for humans, but it is not easy for computers, including the accuracy of detection and the efficiency of performance. Especially in different images, the image size of the face part is inconsistent, that is, geometry, such as pose, facial expression, occlusion, etc., and the influence of luminosity changes, which brings c...

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
CPCG06V40/161G06V40/168G06V40/172G06F18/23
Inventor 张吉昕秦拯胡娟廖鑫张汗灵黄小凤翟亚静
Owner HUNAN UNIV
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