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

A face detection method and device based on convolutional neural network

A convolutional neural network and face detection technology, applied in the field of face detection based on convolutional neural network, to achieve the effect of powerful feature extraction ability, guarantee accuracy and improve detection speed

Active Publication Date: 2018-09-11
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method avoids the time consumption caused by the sliding window, and is conducive to solving many face application problems that require high real-time performance.

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 face detection method and device based on convolutional neural network
  • A face detection method and device based on convolutional neural network
  • A face detection method and device based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0045]In order to describe the specific implementation method of the present invention in detail, the method of the present invention will be further described by taking a face detection database as an example. The database contains 3500 photos, including different scenes, such as day, night, indoor, outdoor, etc. When using the present invention to carry out face detection, proceed according to the following steps:

[0046] Step S1, all the photos in the database are scaled into grayscale images of the same size, and the label information of the pictures is divided into two categories according to whether each pixel of the picture belongs to a face, such as figure 2 shown.

[0047] Step S2, establishing a convolutional neural network with 5 convolutional layers and 3 fully connected layers, wherein the last fully connected layer has the same dimension as the input image, and all weights of the network are randomly initialized. The activation functions of the convolutional ...

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 face detection method and device based on a convolutional neural network. The method includes scaling all the pictures in the training set into a grayscale image of a predetermined size, and assigning label information to each pixel in each of the pictures, and the label information is used to indicate whether the corresponding pixel is a person face; set up a convolutional neural network, wherein each layer of the convolutional neural network is an input layer, a plurality of convolutional layers, a plurality of fully connected layers and an output layer; use gradient descent method and backpropagation algorithm to train the described Convolutional neural network; input the photo to be detected into the trained convolutional neural network to obtain the output feature value of the last layer; compare the output feature value of the last layer with a predetermined threshold to determine the Describe whether each pixel in the photo to be tested is a face area; use the minimum closure method to detect the position of the face according to each pixel determined to be a face area.

Description

technical field [0001] The invention relates to the technical fields of pattern recognition and computer vision, in particular to a face detection method and device based on a convolutional neural network. Background technique [0002] Face detection is a very important problem in computer vision. With the growth of application requirements such as face recognition, age estimation, gender estimation and expression recognition, face detection, as the first step to complete these tasks, has gained more and more attention. The more people pay attention. Some traditional methods use sliding windows to detect faces, then judge each obtained window, and finally detect the position of the face. However, these methods use sliding window technology, which will take a lot of time in this link, and are not particularly suitable for some applications with high real-time requirements. Contents of the invention [0003] In order to solve the problems in the prior art, the object of 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
CPCG06V40/161
Inventor 王亮黄永祯张凯皓
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
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