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

Pinkeye image algorithm

An image algorithm and image technology, applied in image enhancement, image analysis, image data processing and other directions, can solve problems such as high cost, low efficiency, waste, etc., and achieve the effect of limited equipment dependence, convenient installation and fast speed

Pending Publication Date: 2022-01-04
爱诺达智能科技(苏州)有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This screening method: the first is inefficient, once the flow of people is too large, it will cause disorder on the site; the second cost is relatively high, requiring a large number of personnel, equipment, and instruments, resulting in unnecessary waste; third, in the prior art , the demand for hardware equipment is relatively high. In fact, the abnormal recognition based on neural network in the existing technology also has a certain coverage rate, and the process of feature extraction is highly dependent on hardware.

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
  • Pinkeye image algorithm
  • Pinkeye image algorithm
  • Pinkeye image algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] The present invention provides a kind of red-eye image algorithm, comprises the following steps:

[0034] S1: import an image, import the image in RGB format to be detected, and crop the image to an image size of 200*200;

[0035] S2: Image conversion, converting the processed image in RGB format into an image in HVS format, that is, converting red, green and blue into hue, saturation, and brightness;

[0036] S3: parameter setting, parameter setting is performed according to the acquired feature points;

[0037] Among them, the model of HSV (hue, saturation, value) color space corresponds to a conical subset in the cylindrical coordinate system, and the top surface of the cone corresponds to V=1, which contains R=1 and G=1 in the RGB model , B=1 three faces, the color represented is brighter; the color H is given by the rotation angle around the V axis. Red corresponds to an angle of 0°, green corresponds to an angle of 120°, and blue corresponds to an angle of 240°;...

Embodiment 2

[0048] The difference from Example 1 lies in the difference of S1, specifically:

[0049] S1: Import the image, import the image in RGB format to be detected, and crop the image to an image size of 200*200, add a watermark label to the upper left corner of the image, and perform denoising processing on the image;

[0050] The cropping of the image includes:

[0051] Perform histogram normalization on the input image;

[0052] It involves rotating the image so that the line connecting the left and right eyes remains horizontal;

[0053] Scale the image to obtain a normalized image of uniform size;

[0054] Use the face detection class divider to get the face area;

[0055] Locate the effective area of ​​the eye through eye detection and pupil positioning;

[0056] Crop the image to preserve the effective area of ​​the eyes.

[0057]In summary, the present invention has a screening function, which can detect people with red eye symptoms in time, and remind managers to condu...

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 pinkeye image algorithm. The algorithm comprises the following steps: S1, image import: importing a to-be-detected image in an RGB format, and processing a size of the image; S2, image conversion: converting the processed image in the RGB format into an image in an HVS format; S3, parameter setting: performing parameter setting according to feature points needing to be acquired; S4, feature point acquisition: calling the set parameters, and calculating the feature points needing to be acquired; S5, feature point threshold calculation: setting a threshold to discard and retain the calculated feature points; and S6, result output: performing result output on all the feature points meeting parameter requirements and threshold calculation requirements. The algorithm has a screening function, can find people with pinkeye symptoms in time and remind a manager to perform secondary examination and medical treatment, is suitable for school places, exhibition centers and the like, has a limited degree of dependence on hardware equipment, is convenient to install, can be installed on multiple devices, and is high in speed.

Description

technical field [0001] The invention relates to the technical field of eye abnormality screening for special groups of people in specific and designated occasions, and specifically relates to a red-eye image algorithm. Background technique [0002] Currently known eye diseases are mostly manifested as redness or congestion of the eyeballs; there are requirements for the eyes in special scenes, such as: schools, various exhibitions, etc. Some public places or specific areas require necessary screening of special groups of people. At this time, professional staff are required to screen special groups of people one by one with the help of equipment or instruments. This screening method: the first is inefficient, once the flow of people is too large, it will cause disorder on the site; the second cost is relatively high, requiring a large number of personnel, equipment, and instruments, resulting in unnecessary waste; third, in the prior art , the demand for hardware equipment ...

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): G06T7/00G16H50/20
CPCG06T7/0012G16H50/20G06T2207/30041
Inventor 丁辉
Owner 爱诺达智能科技(苏州)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