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

A method and device for establishing a face detection model and face recognition

A face detection and face recognition technology, applied in the field of recognition, can solve the problems of small scope of application and low accuracy of face detection methods, and achieve the effect of adding diversification of functions, avoiding the reduction of detection data accuracy, and expanding the scope of application

Active Publication Date: 2021-10-12
ENC DATA SERVICE CO LTD
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Therefore, the technical problem to be solved by the present invention is that the accuracy of face detection method in the prior art is low and the scope of application is small.

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
  • A method and device for establishing a face detection model and face recognition
  • A method and device for establishing a face detection model and face recognition
  • A method and device for establishing a face detection model and face recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] This embodiment provides a method for establishing a face detection model, which can be used for the establishment of a detection model in the process of face recognition, such as figure 1 shown, including the following steps:

[0030] S11: collect face data as a positive sample, and collect image data that does not contain a face as a negative sample. Here, the face data used for the positive samples may be face data in some historical images, and the face data includes but not limited to face information, lighting scene information, age information and gender information. Accurate face data can obtain a more accurate face detection model. In order to have a clear distinction from positive samples, negative samples should select image data that does not contain human faces to achieve accurate distinction between human faces and non-human faces. In the specific implementation process, the size of positive and negative samples can be unified Transformation, such as uni...

Embodiment 2

[0037] This embodiment provides a face recognition method, which can be used for face recognition in various scenarios, such as figure 2 shown, including the following steps:

[0038] S21: Extract color information of the target image. Here, the target image can be a complete image to be detected, or it can be an image in multiple sliding windows divided from an image, and the color information of the target image can be used as a reference for face recognition, thereby reducing the size of the image. The range of face detection. As a preferred solution, step S21 may include: converting the target image into a YUV color space to obtain YUV data of the target image; extracting U data and V data from the YUV data as color information of the target image. That is, the principle of pink detection is used for skin color discrimination. Skin color detection refers to the process of selecting pixels corresponding to human skin in the target image. Specifically, the target image is...

Embodiment 3

[0048] This embodiment provides a device for establishing a face detection model, which can be used for the establishment of a detection model in the face recognition process, such as image 3 Shown, comprise: acquisition module 31, conversion module 32, the first extraction module 33 and training module 34, each module function is as follows:

[0049] The collection module 31 is configured to collect face data as a positive sample, and collect image data that does not contain a face as a negative sample. For details, refer to the detailed description of step S11 in Embodiment 1.

[0050] The conversion module 32 is configured to convert the positive samples and negative samples into polar coordinate system data. For details, refer to the detailed description of step S12 in Embodiment 1.

[0051] The first extraction module 33 is configured to extract the polar coordinate features of the positive sample and the negative sample from the polar coordinate system data. For details...

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 present invention provides a method and device for establishing a face detection model and face recognition. The method for establishing a model includes: collecting face data as a positive sample, and collecting image data that does not contain a face as a negative sample; The positive sample and the negative sample are converted into polar coordinate system data; the polar coordinate features of the positive sample and the negative sample are respectively extracted from the polar coordinate system data; the classifier is trained by using the polar coordinate feature to obtain Face detection model. In this scheme, as long as the coordinate rotation angle of the image to be detected is determined, the rotated face in the image can be detected, and a rich face detection model can be obtained through simple operations, which not only increases the function diversity of the face detection model but also improves the Detection accuracy, when performing face recognition, using the skin color threshold range to distinguish colors reduces the recognition range, reduces the amount of data calculation, and avoids the problem of lower detection data accuracy caused by image rotation.

Description

technical field [0001] The invention relates to the field of recognition technology, in particular to a method and device for establishing a face detection model and face recognition. Background technique [0002] Face detection means that for any given image, a certain strategy is used to search it to determine whether it contains a human face, and if so, return the position, size and posture of the human face. Face detection is a key link in automatic face recognition system. Today, the application background of face detection has gone far beyond the scope of face recognition system, and has important application value in content-based retrieval, digital video processing, video detection and so on. For example, it is applied to face recognition, face gender recognition, and age classification and other information recognition. At present, many scholars and research institutions at home and abroad have conducted in-depth research on the problem of face detection. Among th...

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
CPCG06V40/172G06V40/168
Inventor 李俊张旺张如高
Owner ENC DATA SERVICE CO LTD
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