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

A face detection method and device

A face detection, the first face technology, applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve the problem of low detection efficiency, reduce the number of detection, improve detection efficiency, and improve detection accuracy Effect

Active Publication Date: 2019-05-31
SHENZHEN INTELLIFUSION TECHNOLOGIES CO LTD
View PDF15 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, in the case of a large number of faces in the image, the detection efficiency is low

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
  • A face detection method and device
  • A face detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach

[0098] As a possible implementation manner, the face detection device also includes:

[0099] The second acquisition unit 304 is used to acquire training data, the training data includes a set of image segments and a first face category label and a first position label of each image segment in the image segment set, and the first face category label is used to identify whether it is a person An image segment of the face;

[0100] The input unit 305 is used to input the first image segment into the cascaded convolutional neural network to be trained to obtain the second face category label and the second position label, and the first image segment is in the image segment set obtained by the second acquisition unit 304 For any image segment, the second face category label is used to identify the probability that the first image segment is an image segment of a human face;

[0101] Calculation unit 306, for calculating the total loss according to the first face category label ob...

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 embodiment of the invention provides a face detection method and device. The method comprises: acquiring a to-be-detected image; Predicting the size of a human face in the to-be-detected image byusing a human face scale prediction network to obtain a predicted human face size; And positioning a face position in the to-be-detected image by using the predicted face size and the cascaded convolutional neural network, wherein the cascaded convolutional neural network comprises two sub convolutional neural networks. By implementing the embodiment of the invention, the face detection efficiencycan be improved.

Description

technical field [0001] The invention relates to the technical field of target detection, in particular to a face detection method and device. Background technique [0002] In order to improve the accuracy of image detection without affecting the efficiency of image detection, the industry has introduced a cascaded convolutional neural network. In the process of using a cascaded convolutional neural network to detect images, all regions of the image must pass through the first sub-convolutional neural network, and the input image area of ​​​​the subsequent sub-convolutional neural network comes from the output of the previous sub-convolutional neural network. The area considered to be a face. It can be seen that the detection efficiency of the cascaded convolutional neural network is related to the number of faces in the image, and the more faces the lower the detection efficiency. Therefore, when the number of faces in the image is large, the detection efficiency is low. ...

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
Inventor 吴涛吴伟杨龙张兆丰王孝宇田第鸿
Owner SHENZHEN INTELLIFUSION TECHNOLOGIES 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