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

Binocular positioning method based on hog feature and fast algorithm

A positioning method and algorithm technology, applied in the fields of image processing, computer vision, and pattern recognition, can solve the problems of high false positive rate, large impact on iris recognition accuracy, low robustness and accuracy false positive rate, etc. The effect of low reporting rate, improving robustness and accuracy, and high robustness and accuracy

Active Publication Date: 2020-11-17
杭州岱石科技有限公司
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the shortcomings of the existing binocular positioning method that cannot stably adapt to changes in the environment, that complex backgrounds have a greater impact on the accuracy of iris recognition, and that the false alarm rate is high, the present invention provides an A binocular positioning method based on HOG features and FAST algorithm with high stickiness, high accuracy and low false alarm rate

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
  • Binocular positioning method based on hog feature and fast algorithm
  • Binocular positioning method based on hog feature and fast algorithm
  • Binocular positioning method based on hog feature and fast algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0066] The present invention will be further described below with reference to the accompanying drawings.

[0067] Refer figure 1 and figure 2 , A two-eye positioning method based on HOG feature and FAST algorithm, including the steps of:

[0068] 1) Load the well-trained SVM model file;

[0069] 2) Get the i-shaped frame image SRCIMAGE to be positioned, and copy the image MIDIMAGE, i is an integer;

[0070] 3) Prepare the image MIDIMAGE, the specific process is as follows:

[0071] 3.1) Gray transformation of image MIDIMAGE, convert the image to grayscale;

[0072] 3.2) Gaussian smooth processing is performed on the image MIDIMAGE, and the noisy point is filtered;

[0073] 3.3) Inflate the image MIDIMAGE, enlarge the spot.

[0074] 4) Use the FAST algorithm to use the FAST algorithm to obtain spot detection, get the candidate area center point coordinate vector Points, the specific process is as follows:

[0075] 4.1) Set the threshold T for comparing the gradation difference bet...

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

A binocular positioning method based on HOG feature and FAST algorithm, load the trained SVM model file; obtain the i-th frame image to be positioned, and copy the image midImage; preprocess the image midImage; use the FAST algorithm to perform spot Detect, obtain the coordinate vector points of the center point of the candidate area; judge whether the candidate area is the eye area in turn, and obtain the center point vector pointsTru of the eye area; filter the points in the vector pointsTru, and obtain the eye area whose final return vector size is at most 2 Center point vector; if only one eye is detected, repair it; return the center point vector pointsFnl of the eye area, traverse the vector pointsFnl, and intercept the rectangular area centered on pointsFnl as the eye area. The invention stably adapts to changes in the environment, has high robustness and accuracy to the environment, and has low false alarm rate.

Description

Technical field [0001] The present invention relates to the field of computer vision, image processing, pattern recognition, a method of eye quickly locate achieved for a face image of infrared light of a single camera apparatus acquired, the method can be used in schools, banks, prisons, factories and other public occasions, access to a private residence and surrounding area are equally applicable. Background technique [0002] Biometrics is an automated technique to detect individual physiological characteristics or personal behavioral characteristics using the technology authentication, in terms of business, the military field, the fields of criminal investigation have been widely used. Among the many biological characteristics, iris recognition for its uniqueness, stability can be collected, non-invasive, etc., have important academic research value and broad application prospects, has been rapid development in recent decades in China it had been widely used in many important...

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): G06K9/00
CPCG06V40/19G06V40/193
Inventor 张永良陈骁陈小柱周涤心钱笑笑
Owner 杭州岱石科技有限公司
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