HOG feature and FAST algorithm-based eyes positioning method

A positioning method and algorithm technology, applied in computing, computer parts, character and pattern recognition, etc., can solve problems such as high false alarm rate, large impact on iris recognition accuracy, low robustness and accuracy false alarm rate, etc. , to achieve the effect of low false alarm rate, improved robustness and accuracy, and high robustness and accuracy

Active Publication Date: 2017-09-08
杭州岱石科技有限公司
View PDF7 Cites 5 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 r

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
  • HOG feature and FAST algorithm-based eyes positioning method
  • HOG feature and FAST algorithm-based eyes positioning method
  • HOG feature and FAST algorithm-based eyes positioning method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

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

[0067] refer to figure 1 and figure 2 , a binocular positioning method based on HOG feature and FAST algorithm, comprising the following steps:

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

[0069] 2) Obtain the i-th frame image srcImage to be positioned, and copy the image midImage, where i is a positive integer;

[0070] 3) Preprocessing the image midImage, the specific process is as follows:

[0071] 3.1) Carry out grayscale transformation to the image midImage, and convert the image into a grayscale image;

[0072] 3.2) Gaussian smoothing is performed on the image midImage, and noisy points are filtered;

[0073] 3.3) Perform an expansion operation on the image midImage to enlarge the light spot.

[0074] 4) Use the FAST algorithm for spot detection on the image midImage to obtain the coordinate vector points of the center point of the candidate area. The sp...

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 an FOG feature and FAST algorithm-based eyes positioning method. The method comprises the following steps of: loading a trained SVM model file; obtaining the ith frame image to be positioned, and copying an image midImage; preprocessing the image midImage; carrying out facula detection by using a FAST algorithm, and obtaining a candidate area center point coordinate vector points; sequentially judging whether a candidate area is an eye area or not, and obtaining eye area center point vector pointsTru; screening points in the vector pointsTru so as to obtain an eye area center point vector, the final return vector of which is 2 for the most; if only one eye is detected, carrying out repair; and returning an eye area center point vector pointsFnl, traversing the vector pointsFnl, and intercepting a rectangular area which takes the pointsFnl as center to serve as an eye area. The method is capable of stably adapting to the environment change, and is relatively high in environment robustness and correctness and relatively low in false alarm rate.

Description

technical field [0001] The invention relates to the technical fields of computer vision, image processing, pattern recognition, etc., and is a method for quickly positioning eyes in face images collected by an infrared single-camera device. The method can be used in schools, banks, prisons, factories, etc. Occasionally, it is also suitable for the access control and surrounding areas of private houses. Background technique [0002] Biometric identification technology is a technology that uses automated technology to detect personal physiological characteristics or personal behavior characteristics for identity verification. It has been widely used in the fields of business, military, and criminal investigation. Among many biological characteristics, iris recognition has important academic research value and broad application prospects due to its uniqueness, stability, collectability, and non-invasiveness. It has developed rapidly in recent decades. In China, it has been wid...

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): G06K9/00
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 Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap