Face recognition device and method

A face recognition and face image technology, applied in the field of face recognition, can solve the problems of identification errors, unequal quality of face image data, and low recognition accuracy, and achieve accurate image feature extraction, improve image quality, and improve recognition. The effect of precision

Inactive Publication Date: 2019-08-30
HUNAN CITY UNIV
View PDF11 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a face recognition device and method to solve the problem of unequal quality of face image data due to different collection equipments proposed in the above background technology, inability to accurately perform image matching and similar faces due to certain common features, prone to misidentification, leading to low recognition accuracy

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 recognition device and method
  • Face recognition device and method
  • Face recognition device and method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] On the one hand, the present invention provides a face recognition device, such as figure 1 and figure 2 As shown, it includes a face acquisition device for collecting face images and an image processing system for processing the collected face images. The image processing system includes an image acquisition module, a sample training module and a face recognition module. The collection module is used to collect images of faces, the sample training module is used to process the collected face images and extract characteristic information, the face recognition module is used to match the collected face images with extracted feature information, and Complete face recognition.

[0047] In this embodiment, the face acquisition device is designed based on the image sensor CCD. The image sensor CCD is also called a charge coupling element, which is a semiconductor device that can convert optical images into digital signals, and convert the acquired user image signals into ...

Embodiment 2

[0051] As the second embodiment of the present invention, in order to facilitate the collection of images of human faces, the inventors improved the image collection module, as a preferred embodiment, such as Figure 3-Figure 4 As shown, the image acquisition module includes an image import module, a geometric processing module, a geometric normalization module, a grayscale processing module, a histogram equalization module, a weighted value filtering module and a feature extraction module. The image import module is used to convert the collected The face image is imported into the image processing system, the geometry processing module is used to locate the imported face image, and the geometry normalization module is used to rotate and cut the positioned face image to form a unified standard and grayscale The processing module is used to convert the color image into a grayscale image to speed up the processing. The histogram equalization module is used to adjust the grayscale...

Embodiment 3

[0073] As the third embodiment of the present invention, in order to facilitate the processing of the collected face images and extract the characteristic information, the inventors improved the image acquisition module, as a preferred embodiment, such as Figure 5-Figure 6 As shown, the sample training module includes a sample collection module, a sample description file module, a vec file creation module, and a training image module. The sample collection module uses the harr feature of the sample for classifier training to obtain a cascaded boosted classifier, and establishes a sample The description file module is used to create a pos.txt file, and note the number of times and names of pictures. The vec file module uses the opencv_createsamples.exe built-in program to create a vec file. The training image module is used to use opencv_haartraining.exe for image training and collection. The sample module includes a positive sample collection module and a negative sample colle...

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 relates to the technical field of face recognition, in particular to a face recognition device and method. The face recognition device comprises a face collection device which is used for collecting face images, and an image processing system which is used for processing the collected face images. In the face recognition device and method, an image acquisition module is set to acquire face images; a color image is converted into a gray level image through a graying processing module, so as to accelerate the processing speed; the gray level distribution of the image is adjusted through a histogram equalization module, so as to improve graphics quality; interference noise in the image is removed through a weighted value filtering module, so that image feature extraction is accurate, and recognition precision is improved; collected face images are matched with extracted feature information through a face recognition module; and a threshold judgment module is set to determinewhether the face images to be recognized are the collected face images or not, thus reducing the judgment error probability, and improving recognition accuracy.

Description

technical field [0001] The invention relates to the technical field of face recognition, in particular to a face recognition device and method. Background technique [0002] As the most intuitive identification method in biometric identification technology, face recognition has the irreplaceable advantages of other biometric identification technologies, such as user-friendly, concealed operation, easy to use, accurate positioning, economic benefits and good system scalability. [0003] Due to the different collection equipments of existing face recognition devices, the quality of face image data is not equal, and image matching cannot be performed accurately. At the same time, due to the existence of certain common features, similar faces are prone to identification errors, resulting in low recognition accuracy. . In view of this, we propose a face recognition device and method. Contents of the invention [0004] The purpose of the present invention is to provide a face ...

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
CPCG06V40/166G06V40/172G06V40/168
Inventor 付媛媛
Owner HUNAN CITY UNIV
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