Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Face identification method under shielding condition based on deep learning

A face recognition and deep learning technology, applied in the field of face recognition, can solve problems such as difficulty in implementation and increase in complexity of face recognition technology, and achieve the effect of improving effectiveness

Inactive Publication Date: 2018-02-09
HARBIN MAX TELEGENT SCI & TECH DEV CO LTD
View PDF8 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the real environment, the face image information collected in real time will be interfered by various factors such as human hair, masks, hats, sunglasses and other frequently worn objects, which greatly increases the complexity of face recognition technology. very difficult

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 identification method under shielding condition based on deep learning
  • Face identification method under shielding condition based on deep learning
  • Face identification method under shielding condition based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0020] A face recognition method under occlusion conditions based on deep learning, the method includes the following steps: (1) face detection and feature point detection for a given face image with partial occlusion; (2) according to the detected (3) Based on the ubuntu16.04 operating system, under the GPU1080, build the CAFFE deep learning framework to obtain the face recognition model.

Embodiment 2

[0022] According to the face recognition method under the occlusion condition based on deep learning described in embodiment 1, the specific process of performing face detection and feature point detection on a given face image with partial occlusion is as follows:

[0023] (1) For the given face image data with partial occlusion, after three layers of convolutional layers, the obtained feature maps are respectively input into the first group of face classification layer, frame regression layer and facial feature point positioning layer to obtain Face candidate box and bounding box regression vector;

[0024] (2) Use the candidate frame as the input to continue the convolution operation, and then after three layers of convolution, the obtained feature map is input into the fully connected layer, and then input into the second group of face classification layer, border regression layer and facial feature point positioning layer to further improve the accuracy of the frame;

[...

Embodiment 3

[0027] According to the face recognition method under occlusion conditions based on deep learning described in Embodiment 1, the specific process of performing facial features partial map interception according to the positions of the detected feature points on the human face is as follows: according to the detected human face The location of the feature points, the original image is cut into three partial images including eyes, nose, and mouth, which are used for subsequent training.

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

A face identification method under a shielding condition based on deep learning is disclosed. In reality, face image information collected in real time is interfered by a plurality factors of shielding of body hairs, a gauze mask, a hat, sunglasses and other frequent-wearing objects and other factors so that complexity of a face identification technology is greatly increased and realization difficulty is large. The method comprises the following steps of (1) carrying out face detection and characteristic point detection on a given partially-shielded face image; (2) according to detected positions of characteristic points on a face, carrying out partial five-sense-organ image capture; and (3) based on a ubuntu16.04 operation system, under GPU1080, constructing a CAFFE deep learning framework and acquiring a face identification model. The invention discloses the face identification method under the shielding condition based on the deep learning.

Description

Technical field: [0001] The invention relates to the field of face recognition, in particular to a face recognition method under occlusion conditions based on deep learning. Background technique: [0002] Face recognition technology is an intelligent recognition technology that combines pattern recognition technology and computer vision technology, and has a wide range of applications. Security monitoring in schools, companies, and residential quarters, and even attendance systems can be completed through automatic face recognition technology; face recognition technology can also be used to improve the efficiency of solving crimes in tasks such as finding lost children and the elderly, and tracking fugitives. and many more. In the real environment, the face image information collected in real time will be interfered by various factors such as human hair, masks, hats, sunglasses and other frequently worn objects, which greatly increases the complexity of face recognition tec...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06V40/165G06V40/172G06V40/171G06N3/045G06F18/24G06F18/214
Inventor 姚一鸣
Owner HARBIN MAX TELEGENT SCI & TECH DEV CO LTD
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
Eureka Blog
Learn More
PatSnap group products