Backlight face image processing method, face recognition method

A face image and processing method technology, which is applied in the field of image processing, can solve the problems of reduced recognition accuracy, information loss, and accuracy improvement of the same type of image, so as to improve the brightness of the collected face image, improve the success rate, and improve the similarity. degree of effect

Active Publication Date: 2021-02-05
芯算一体(深圳)科技有限公司
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Although the above image processing method can improve the visual brightness of the picture, it will cause information loss
Therefore, in face recognition, it does not bring about a good improvement in accuracy. In the case of a large amount of information loss, it may even cause a reduction in recognition accuracy or the matching degree of the same type of image.

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
  • Backlight face image processing method, face recognition method
  • Backlight face image processing method, face recognition method
  • Backlight face image processing method, face recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0054] A method for processing a backlit human face image according to an embodiment of the present invention. figure 1 It is a schematic flow chart of the method for backlighting human face image in one embodiment, as figure 1 Shown, the processing method of this backlight face image comprises step 102 to step 108:

[0055] Step 102: Obtain and collect face images.

[0056] Specifically, a camera is used to collect a face image, and then the collected face image is obtained; if applied to an access control system, the collected face image may be a visitor's face image.

[0057] Step 104: Conver...

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 a method for processing a backlit face image, a face recognition method, and an access control system based on face recognition. The method includes the following steps: calculating and collecting the value of each pixel of the face image in the V channel and the value in the V channel Average value; obtain the average value of each face image in the input library in the V channel, as the average value of the V channel of the library image, obtain the maximum value of the face image in the input library in the V channel, and use it as the maximum value of the V channel of the library image; if the collection The average value of the face image in the V channel is lower than the preset value of the V channel, and it is determined to be a backlit face image, and the value of each pixel in the V channel of the collected face image is adjusted. The adjusted value of each pixel in the V channel includes The product of the brightness sum and the value of the pixel point of the collected face image in the V channel, the brightness sum includes the sum of the difference between the average value of the V channel of the library image minus the brightness ratio and 1, and the brightness ratio is the sum of the collected face image in The ratio of the average value of the V channel to the maximum value of the V channel of the library image.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a backlight face image processing method, a face recognition method, and an access control system based on face recognition. Background technique [0002] In face recognition, scenes with backlit faces are usually encountered, which often leads to problems such as low similarity between the backlit face image and the target face image, and misidentification. For example, if a face image of a visitor with a dark face is collected, the similarity between the visitor and the library is only 0.4. If the similarity threshold is set to 0.5, it will cause wrong recognition results and reduce the success rate of face recognition. . The current backlight image processing usually uses histogram equalization or uses different image processing libraries to process the image. [0003] Histogram equalization is often used to increase the global contrast of an image, especially when ...

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): G06K9/00G06K9/46G06T7/90
CPCG06T7/90G06T2207/10004G06T2207/30201G06V40/166G06V40/168G06V10/56
Inventor 申啸尘乔国坤周有喜
Owner 芯算一体(深圳)科技有限公司
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