Unlock instant, AI-driven research and patent intelligence for your innovation.

An Improved Face Detection System

A technology of face detection and face area, applied in the field of face detection, can solve the problems of face detection algorithm not having real-time performance and lack of robustness

Active Publication Date: 2020-03-17
XINJIANG ZHICHEN TIANLIN INFORMATION TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The face detection algorithm for two-dimensional images is not real-time and lacks robustness

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
  • An Improved Face Detection System
  • An Improved Face Detection System
  • An Improved Face Detection System

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] The present invention is further described in conjunction with the following examples.

[0050] see figure 1 , a kind of improved human face detection system of the present embodiment, comprises human face acquisition module 1, human face localization module 2, skin color detection module 3 and human face matching module 4, and described human face acquisition module 1 is used for collecting current For an image containing face information, the data processing module 2 is used for denoising the collected image, and the face positioning module 3 is used for depth information and color information of the face area collected by a depth sensing sensor Determine the radius of the human face, the skin color detection module 4 is used to convert the collected skin color samples into different spaces for comparison, thereby distinguishing whether the pixel points belong to "human face skin color" or "non-human face skin color", and the human face matching Module 5 is used to e...

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

An improved face detection system, comprising a face collection module, a data processing module, a face positioning module, a skin color detection module and a face matching module, the face collection module is used to collect current images containing face information , the data processing module is used to denoise the collected image, the face positioning module is used to determine the radius of the face through the depth information and color information of the face area collected by the depth sensing sensor, and the skin color The detection module is used to transform the collected skin color samples into different spaces for comparison, so as to distinguish whether the pixels belong to "face skin color" or "non-face skin color". The face feature parameters extracted from the face area are matched with the face area feature parameters stored in the database to perform face recognition. The beneficial effect of the invention is: through the construction and connection of each module, face recognition with complex background is realized.

Description

technical field [0001] The invention relates to the technical field of face detection, in particular to an improved face detection system. Background technique [0002] Face detection is an important part of face recognition. Faced with the increasing attention to information security today, face detection has been used in medical care, traffic monitoring, smart home, etc. Due to the inherent defects of the traditional two-dimensional image-related face detection algorithm, it is impossible to make correct detection in complex backgrounds such as uneven illumination and excessive face deflection angles. Most of the existing face technologies are algorithms based on two-dimensional images. [0003] The face detection algorithm for two-dimensional images is not real-time and lacks robustness. When monitoring criminal behavior, the speed of locating facial features will directly affect the safety of people's lives and property. Contents of the invention [0004] In view of...

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 Patents(China)
IPC IPC(8): G06K9/00
CPCG06V40/162G06V40/161G06V40/168
Inventor 不公告发明人
Owner XINJIANG ZHICHEN TIANLIN INFORMATION TECH CO LTD