Face detection method and face detection device

A face detection and face technology, applied in the field of face detection, can solve the problems of poor anti-interference ability and low robustness, and achieve the effect of ensuring the effect and speed, and the effect is good.

Active Publication Date: 2016-08-31
SHENZHEN INST OF ADVANCED TECH
View PDF4 Cites 81 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the embodiment of the present invention provides a face detection method and device to solve the problem of poor anti-interference ability and low robustness of the existing technology to the influencing factors in face data

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
  • Face detection method and face detection device
  • Face detection method and face detection device
  • Face detection method and face detection device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present invention. It will be apparent, however, to one skilled in the art that the invention may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

[0024] The embodiment of the present invention is realized based on a cascaded multi-layer convolutional neural network. The images to be tested pass through the multi-layer convolutional neural networks at various levels in turn, and each level of multi-layer convolutional neural network is eliminated. Non-face images are eliminated. The image does not need to enter the next-level multi-layer con...

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 is suitable for the technical field of face identification and provides a face detection method and a face detection device. The method comprises steps that a cascaded multi-level convolution nerve network is constructed and trained; an image is inputted to the cascaded multi-level convolution nerve network and sequentially passes through each level of the cascaded multi-level convolution nerve network; if the image is eliminated by one level of the cascaded multi-level convolution nerve network, the image is determined to be a non-face image; if the image is outputted from the last level of the cascaded multi-level convolution nerve network, the image is determined to be a face image. According to the method, multiple types of monitoring information are utilized, characteristics with stronger robustness can be learned and utilized, the face detection effect is better compared with a traditional detector, and the cascaded multi-level convolution nerve network can be utilized to guarantee the face detection effect and the face detection speed.

Description

technical field [0001] The invention belongs to the technical field of face recognition, in particular to a face detection method and device. Background technique [0002] In the field of face recognition applications, face detection and face key point positioning are the basis of follow-up work, and they need to have strong robustness to ensure the normal and efficient execution of follow-up work. In practical application scenarios, face data has various influencing factors, such as illumination, occlusion, posture changes, etc. These uncontrollable factors will have a great impact on the effect of face recognition. [0003] At present, face detection technology is mainly realized by features based on manual design, such as Haar features, HOG features, etc. These methods are less robust in complex environments and when facial poses and expressions change greatly. The anti-interference ability is poor, so sometimes the detection effect can only be guaranteed by sacrificing ...

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
CPCG06V40/161G06V40/172
Inventor 乔宇张凯鹏李志锋
Owner SHENZHEN INST OF ADVANCED 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