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

A face detection method and device

A technology of face detection and face, which is applied in character and pattern recognition, instruments, computer components, etc., can solve problems such as unsuitable for occasions with high real-time requirements, time-consuming classification process, single characteristic parameters, etc., to achieve classification The process takes a short time, reduces the amount of calculation, and the effect of low calculation amount

Active Publication Date: 2017-04-26
SHENZHEN SENSETIME TECH CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Referring to the existing patented technologies, most of them have some common problems, such as single feature parameters and low accuracy; the extraction and classification process takes a long time, and is not suitable for occasions with high real-time requirements, etc.

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 Construction

[0021] Attached below figure 1 The present disclosure will be described in detail with Examples and Examples.

[0022] Provide a kind of face detection method in a basic method embodiment, described method comprises the following steps:

[0023] S100. Calculate the number of pyramid feature layers and the scaling ratio: calculate the number of pyramid feature layers n_scales and the scaling ratio S according to the size of the image to be recognized and the scaling minimum width and height parameters obtained based on face model training, and the scaling ratio needs to ensure that the scaling area Maximize the area;

[0024] S200. Extract the feature data based on the face classification of the pyramid feature layer: divide the pyramid feature layer into a complete extraction layer and an approximate extraction layer, perform complete extraction and approximate extraction respectively, and obtain the face classification basis of each layer feature data;

[0025] The complet...

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 disclosure discloses a face detection method and device. The method calculates the number of pyramid feature layers and scaling coefficients, extracts pyramid feature data, classifies and extracts data, and obtains a face detection result. The disclosed method performs classification on the basis of rapid multi-scale pyramid feature data extraction, which can effectively reduce the amount of calculation under the premise of ensuring the detection accuracy; does not limit the characteristic parameters, and combines the results on the basis of multi-layer classification to obtain the final The result of face recognition can improve the accuracy; due to the low amount of calculation, the classification process takes a short time and is suitable for occasions with high real-time requirements. The device realized based on the method is convenient and effective to use, and is especially suitable for embedded applications.

Description

technical field [0001] The present disclosure relates to the technical field of image pattern recognition, in particular to a face detection method and device. Background technique [0002] Face detection technology belongs to the category of biometric technology, and has become an effective means of biometric authentication, and has achieved certain application results in payment, attendance, security and other fields. According to public documents, the existing automatic face detection products can be roughly divided into two categories, one is a general software and hardware platform based on PC+OS (WIN or Linux); the other is developed around DSP, FPGA or ARM Embedded products. Due to problems in cost, stability, and maintainability, it is difficult to promote general-purpose platforms. Embedded systems are application-centric, based on tailorable software and hardware computer technology, and are suitable for areas with strict requirements on functionality, reliabilit...

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
CPCG06V40/168G06V40/172
Inventor 刘文志李嘉斌毛宁元
Owner SHENZHEN SENSETIME TECH 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