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

Face image glass removal method based on mobile shape model and weighted interpolation method

An active shape model and glasses removal technology, applied in the field of computer vision, can solve problems such as noise and recognition rate decline, and achieve the effect of improving efficiency and effect, saving training time, and effectively removing glasses in real time

Inactive Publication Date: 2014-11-19
PCI TECH GRP CO LTD
View PDF5 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method uses the face image without glasses to train the feature space, and the effect is better for the input image similar to the training image, but it is easy to introduce a lot of noise and even cause the recognition rate to drop for the input image that is quite different from the training image, and it takes a certain amount of time and effort. A certain number of pictures for training

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 image glass removal method based on mobile shape model and weighted interpolation method
  • Face image glass removal method based on mobile shape model and weighted interpolation method
  • Face image glass removal method based on mobile shape model and weighted interpolation method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0017] (1) To grayscale the input image, use the Adaboost classifier based on Haar features to detect faces;

[0018] (2) Attachment figure 1 , Use the active shape model to extract 68 feature points in the face to locate the area between the eyebrows and the mouth, and then exclude the nose area in this area to locate the initial search area of ​​the glasses;

[0019] (3) Attachment figure 2 , Obtain the face skin texture feature based on the gray-level co-occurrence matrix, and find the position in the initial search area that matches with the face skin texture feature less than 80% as the secondary search area;

[0020] (4) Perform independent target extraction on the secondary search area through the connected domain method based on gray value. When the independent target area is greater than or equal to 50 pixels, the target is determined as the glasses area; otherwise, it is determined as the non-glasses area;

[0021] (5) Perform a distance-based weighted interpolation method w...

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 face image glass removal method based on a mobile shape model and a weighted interpolation method, and the application of the face image glass removal method in face identification. According to the method, glass removal processing is performed on face data detected through the face detection technology, the processed data is used for face identification, and the accurate glass removal method can effectively improve the face identification accuracy. The mobile shape model is utilized by an algorithm for positioning a glass area, and the glass area is removed through the weighted-interpolation-based method, so that the glass removal effect is ensured. With adoption of the method, the problem that the recognition rate is reduced greatly because the deep color thick-frame glasses shield faces during the face identification process is effectively solved, therefore, the face identification performance is improved.

Description

Technical field [0001] The invention relates to the field of computer vision, and in particular to a method for removing glasses of a face image. Background technique [0002] Face recognition is an important research field in recent years. Although great progress has been made, in some practical applications, many factors such as light, posture, glasses, etc. affect the recognition effect to varying degrees. Among them, glasses are more common. A distracter. [0003] At this stage, the most commonly used face image glasses removal method is principal component analysis. This method uses the non-glasses face image training feature space, which is better for input images that are similar to the training image. However, for input images that are larger and different from the training image, it is easy to introduce a lot of noise and even cause the recognition rate to decrease, and it takes a certain time and A certain number of pictures for training. Summary of the invention [000...

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
Inventor 冯琰一张少文丁保剑
Owner PCI TECH GRP 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