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

Face recognition method and system based on self-adaption and color normalization

A face recognition and self-adaptive technology, applied in the field of face recognition, can solve problems such as large interference, achieve the effect of improving accuracy and reducing redundancy

Active Publication Date: 2020-10-02
ZHEJIANG PONSHINE INFORMATION TECH CO LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the above-mentioned patents can recognize human faces, they are aimed at full-face detection during detection, and are greatly interfered by light, shadows, etc., and face recognition cannot be performed accurately.

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 method and system based on self-adaption and color normalization
  • Face recognition method and system based on self-adaption and color normalization
  • Face recognition method and system based on self-adaption and color normalization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] This embodiment provides a face recognition method based on self-adaptation and color normalization, such as figure 1 shown, including steps:

[0047] S1. Create a face image dataset;

[0048] S2. Perform adaptive scale selection processing on the images in the face data set based on the face detection network to obtain a new face image;

[0049] S3. Perform face positioning on the new output face image, and perform color normalization processing on the eye area of ​​the positioned face to obtain a processed face image;

[0050] S4. Input the processed face image into the face recognition network, and calculate the Euclidean distance between the vector of the processed face image and the prestored face image, and judge whether the Euclidean distance is less than the first preset threshold, if so, Then obtain the training samples, and input the training samples into the face recognition network for training to obtain the final face recognition network model;

[0051] ...

Embodiment 2

[0101] A face recognition method based on self-adaptation and color normalization provided in this embodiment is different from Embodiment 1 in that:

[0102] This embodiment uses the ASIA-FaceV5 Asian face data set, in which 2000 images are used as a training set and 500 images are used as a test set. The method in Example 1 is used for processing, as shown in Table 1, the speed and accuracy comparison effect of using this method and not using this method.

[0103]

[0104] Table 1

[0105] According to Table 1, it can be obtained that the speed of detection is improved through the adaptive mechanism, and the color normalization of the eye area improves the accuracy of face recognition.

Embodiment 3

[0107] This embodiment provides a face recognition system based on self-adaptation and color normalization, such as Image 6 shown, including:

[0108] Creation module 11, is used for creating face image data set;

[0109] The first processing module 12 is used to perform adaptive scale selection processing on the images in the face data set based on the face detection network to obtain new face images;

[0110] The second processing module 13 is used to perform face positioning on the new output face image, and perform color normalization processing on the eye area of ​​the face after positioning to obtain a processed face image;

[0111] The training module 14 is used to input the processed human face image into the face recognition network, and calculate the Euclidean distance between the vector of the processed human face image and the prestored human face image, and judge whether the Euclidean distance is less than the first preset Threshold, if so, then obtain 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

The invention discloses a face recognition method based on self-adaption and color normalization. The face recognition method comprises the following steps: S1, creating a face image data set; S2, performing adaptive scale selection processing on the images in the face data set based on a face detection network to obtain new face images; S3, carrying out face positioning on the output new face image, carrying out color normalization processing on the eye periphery area of the positioned face, and obtaining a processed face image; S4, inputting the processed face image into a face recognition network, calculating the Euclidean distance between the vector of the processed face image and a pre-stored face image, judging whether the Euclidean distance is smaller than a first preset threshold value or not, if so, obtaining a training sample, and inputting the training sample into a face recognition network for training to obtain a final face recognition network model; and S5, inputting an image to be recognized into the face recognition network model for face recognition to obtain a final recognition result.

Description

technical field [0001] The invention relates to the technical field of face recognition, in particular to a face recognition method and system based on self-adaptation and color normalization. Background technique [0002] When training the face detection network, due to the different angles and focal lengths, the size of the face in the sample image is not fixed. In order to accurately locate all possible faces in the image, we usually enlarge / reduce the original image to form an image pyramid. It means to choose as many zoom ratios as possible to form images with different resolutions, when the zoom-in / down ratios are very close, it will cause detection frame redundancy. [0003] For example, the patent with the publication number CN109684931A discloses a face recognition method based on color sub-channels, including the following steps: S1: training of face recognition models and normalization of frequency of different color channels; S2: selecting people to be recognized...

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
IPC IPC(8): G06K9/00
CPCG06V40/172G06V40/161
Inventor 陈晓莉丁一帆徐菁杨世宏徐云华林建洪
Owner ZHEJIANG PONSHINE INFORMATION 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