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

CNN (Convolutional Neural Network) based face image quality evaluation method and device

A technology of convolutional neural network and face image, which is applied in the field of evaluating the quality of face image based on convolutional neural network, which can solve the problems of the influence of recognition results and the lack of technology in face image.

Inactive Publication Date: 2018-07-10
武汉众智数字技术有限公司
View PDF3 Cites 40 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In practical applications, after the staff locks the suspect, it is necessary to determine the identity information of the suspect through static recognition or deploy and control through dynamic recognition to facilitate the arrest. However, the angle, rotation, illumination, and resolution of the face in the image to be recognized Rate, noise, occlusion and other factors will have a significant impact on the recognition results
At present, how to select a face image that meets the requirements from a large number of face images has not yet been realized by technology.

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
  • CNN (Convolutional Neural Network) based face image quality evaluation method and device
  • CNN (Convolutional Neural Network) based face image quality evaluation method and device
  • CNN (Convolutional Neural Network) based face image quality evaluation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] figure 1 The method for evaluating the quality of human face images based on a convolutional neural network provided by an embodiment of the present invention is shown, and the method includes:

[0049] Step 101: Collect multiple face images in the surveillance video, and calculate the preliminary quality value corresponding to each face image;

[0050] Step 102: Calculate the image data of each face image, and generate a training sample set according to each image data and preliminary quality value, wherein the image data includes key point binary images, grayscale images and edge intensity images;

[0051] Step 103: Train the training sample set based on the convolutional neural network to obtain a quality evaluation model;

[0052] Step 104: Generate image data from the face image to be recognized, and perform face quality evaluation on the image data through a quality evaluation model to obtain a quality value of the face image to be recognized.

[0053] This solu...

Embodiment 2

[0089] see Figure 5 , the embodiment of the present invention provides a kind of device based on convolutional neural network to evaluate the face image quality, and described device comprises:

[0090] Acquisition unit 501, used for collecting multiple face images in the monitoring video;

[0091] The calculation unit 502 is connected to the acquisition unit 501, and is used to calculate the preliminary quality value corresponding to each face image, and calculate the image data of each face image, according to each image data and the image data corresponding to the The initial quality value generates a training sample set, and the image data includes a key point binary image, a grayscale image and an edge intensity image;

[0092] The training unit 503 is connected to the calculation unit 502, and trains the training sample set based on the convolutional neural network to obtain a quality evaluation model;

[0093] The evaluation unit 504 is connected to the training unit...

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 provides a CNN based face image quality evaluation method and device. The method comprises that face images in a monitoring video are collected to form a face data set, and the face dataset comprises an initial quality value corresponding to each face image; image data of each face image is calculated, a training sample set is generated according to the image data and initial quality value of each image, and the image data includes a binary key point image, a grayscale map and an edge intensity graph; the training sample set is trained on the basis of the CNN, and a quality evaluation model is obtained; and a to-be-identified face image generates image data, the face quality of the image data is evaluated by the quality evaluation model, and a quality value of the to-be-identified face image is obtained. Via the schemes, a frame with the highest face image quality in the video can be used for subsequent face analysis and identification. The quality evaluation and filtering effect can be optimized, and the case solving efficiency can be improved greatly.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a method and device for evaluating the quality of human face images based on a convolutional neural network. Background technique [0002] With the rapid development of science and technology, intelligent video surveillance technology is widely used in public security criminal investigation business. It has become an important means of criminal investigation technology to find and lock suspect targets from video surveillance. [0003] In practical applications, after the staff locks the suspect, it is necessary to determine the identity information of the suspect through static recognition or deploy and control through dynamic recognition to facilitate the arrest. However, the angle, rotation, illumination, and resolution of the face in the image to be recognized Rate, noise, occlusion and other factors will have a significant impact on the recognition results. How to ...

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): G06T7/00
CPCG06T7/0002G06T2207/20081G06T2207/20084G06T2207/30168G06T2207/30201
Inventor 向少雄贺波涛吴迪
Owner 武汉众智数字技术有限公司
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