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

Method for constructing image quality evaluation and face recognition efficiency relation model

A technology for image quality evaluation and face recognition, which is applied in the field of image processing to achieve the effect of avoiding waste and saving expenses

Inactive Publication Date: 2015-07-15
NANJING UNIV OF POSTS & TELECOMM
View PDF3 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is to propose a method for constructing a relationship model between image quality evaluation and face recognition efficiency in view of the problems involved in the background 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
  • Method for constructing image quality evaluation and face recognition efficiency relation model
  • Method for constructing image quality evaluation and face recognition efficiency relation model
  • Method for constructing image quality evaluation and face recognition efficiency relation model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] Below in conjunction with accompanying drawing, technical scheme of the present invention is described in further detail:

[0038] Such as figure 1 As shown, the present invention discloses a method for constructing a relationship model between image quality evaluation and face recognition efficiency, comprising the following steps:

[0039] Step A: Collect image frames containing faces from high-definition, standard-definition, and normal-definition cameras to obtain input images at three image quality levels.

[0040] Step B: Convert the input image at each image quality level into a grayscale image, input the QAC image quality evaluation algorithm, and obtain the score based on the image quality of each image (full score is 100 points), in each level of image, the The obtained scores are sorted from small to large, and the scores located at the first 20% and the last 20% of the sequence are eliminated. Level, take the maximum and minimum values ​​of the remaining s...

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 method for constructing an image quality evaluation and face recognition efficiency relation model. The method comprises the following steps: collecting image video frames of three image quality levels of low definition, standard definition and high definition, carrying out quality evaluation for the image video frames, and obtaining corresponding image quality taking value intervals; carrying out face detection for the image video frames, and recording three levels of face detection power; grouping the face images with the three image quality levels according to different faces, and equally dividing each group into two parts, wherein one part includes training images, and the other part includes images to be identified; according to the training images, training a face dictionary; according to the face dictionary, carrying out face identification for the images to be identified, and recording the face identification success rate; finally, associating the face recognition efficiency with the corresponding image quality evaluation level. The method can be applied to the related fields such as video monitoring and guides different application fields to realize reasonable selection for the image collection equipment level, and the hardware input cost of application system construction is optimized.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for constructing a relationship model between image quality evaluation and face recognition efficiency. Background technique [0002] Image quality evaluation is one of the key technologies of image processing systems. The methods and indicators of image quality evaluation can provide useful guidance on how to improve image quality and select corresponding image processing methods in application fields such as image processing systems. Since the success rate of face recognition largely depends on the quality of the input image, the misjudgment rate caused by using poor-quality images for recognition is often high, and the computing resources required for recognition are wasted. [0003] The relationship model between image quality and face recognition rate has important research significance in both theoretical research and practical application. At the applica...

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): G06K9/00G06K9/66
Inventor 吴蔚杰刘佶鑫李艺
Owner NANJING UNIV OF POSTS & TELECOMM
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