Methods and devices for obtaining frontal human face images

A face image, frontal image technology, applied in the field of face recognition, to achieve the effect of strong executable, improved efficiency, simple and effective method

Inactive Publication Date: 2016-03-16
SHENZHEN YIHUA COMP +2
View PDF2 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the embodiments of the present invention is to propose a method and device for obtaining a frontal image of a human face, aiming at solving the problem of how to improve the efficiency of human face recognition

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
  • Methods and devices for obtaining frontal human face images
  • Methods and devices for obtaining frontal human face images
  • Methods and devices for obtaining frontal human face images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] refer to figure 1 , figure 1 is a schematic flow chart of the first embodiment of the method for acquiring a frontal image of a human face according to the embodiment of the present invention.

[0048] In Embodiment 1, the method for obtaining a frontal image of a human face includes:

[0049] Step 101, according to the face image to be processed and the image of the feature part of the face collected in pre-training, the image of the feature part of the face in the face image to be processed is acquired;

[0050] Preferably, said acquiring images of facial features in said to-be-processed facial images includes:

[0051] Acquiring images of facial feature parts of ears, eyes and / or nose in the human face image to be processed.

[0052] Preferably, according to the face image to be processed and the image of the feature part of the face collected in pre-training, the image of the feature part of the face in the face image to be processed is obtained, including:

[0...

Embodiment 2

[0066] refer to figure 2 , figure 2 is a schematic flowchart of the second embodiment of the method for acquiring a frontal image of a human face according to the embodiment of the present invention.

[0067] On the basis of Embodiment 1, before obtaining the image of the feature part of the face in the face image to be processed according to the face image to be processed and the image of the feature part of the face collected in advance training, further includes :

[0068] Step 104, training and collecting images of facial features;

[0069] Described training gathers the image of face feature part, comprises:

[0070] Collect the ear image of the frontal face, collect the ear image and non-ear image when the face is deflected, and use the adaboost algorithm to train the collected ear image and non-ear image to obtain the ear classifier file.

[0071] Specifically, the present invention trains and obtains the ear classifier file. Collect the ear images when the face ...

Embodiment 3

[0073] refer to image 3 , image 3 It is a schematic diagram of the functional modules of the device for acquiring a frontal image of a human face according to an embodiment of the present invention.

[0074] In the third embodiment, the device for obtaining a frontal image of a human face includes:

[0075] The first acquiring module 301 is used to acquire the image of the feature part of the face in the face image to be processed according to the face image to be processed and the image of the feature part of the face collected in pre-training;

[0076] Preferably, the first acquisition module 301 is configured to:

[0077] Acquiring images of facial feature parts of ears, eyes and / or nose in the human face image to be processed.

[0078] Preferably, refer to Figure 4 , Figure 4 It is a schematic diagram of the functional modules of the first acquisition module 301 according to the embodiment of the present invention. The first obtaining module 301 includes:

[007...

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

Embodiments of the invention disclose methods and devices for obtaining frontal human face images. According to a to-be-processed human face image and a pre-training acquired image of a human face characteristic part, the image of the human face characteristic part in the to-be-processed human face image is obtained; according to the image of the human face characteristic part, a deviation angle of a human face in the to-be-processed human face image is obtained; according to the deviation angle, the to-be-processed human face image is processed so that a frontal human face image is output; and, through a method for detecting whether the characteristic part can be detected in the human face image at the same time, whether a human face pose is a frontal human face pose is judged. The method is simple and effective, and performability is high; the frontal human face pose eliminates influences of changes of the human face pose and the like on a human face identification algorithm, a frontal human face is directly detected, human face pose correction, human face alignment and other processes are not needed, and human face identification efficiency is improved.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of face recognition, and in particular to a method and device for acquiring a frontal image of a face. Background technique [0002] After long-term development, the face detection method has achieved remarkable results and formed a variety of method categories supported by different theories. Among them, the face detection method based on statistics is widely used. Among many methods, PaulViola et al. People proposed a detection method based on integral images, which has a high performance in terms of accuracy and real-time performance. This face detection method greatly improves the speed of face detection while retaining the robustness of the statistical learning method, which has attracted widespread attention in this field. Of course, there are still many difficulties in face detection. Face lighting, occlusion, and multiple poses continue to pose challenges to traditional frontal...

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
CPCG06V40/171
Inventor 翟云龙
Owner SHENZHEN YIHUA COMP
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