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

Image processing method based on near-infrared imaging and terminal

A near-infrared imaging and image processing technology, which is applied in the field of image processing, can solve the problems of ignoring blood vessel depth information, poor quality of blood vessel extraction, and excessive noise at the edge of blood vessels, so as to achieve good human eye recognition, good extraction quality, and retain relative depth information Effect

Pending Publication Date: 2020-04-03
SHENZHEN YUANHUA MEDICAL EQUIP TECH CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This traditional binarization algorithm is represented by 0 below a certain threshold, and 255 above a certain threshold, ignoring the depth information of blood vessels.
And the disadvantage of this algorithm is that there are a lot of noise on the edges of blood vessels, the blood vessels and non-vessels are too stiff, the quality of blood vessel extraction is poor, and the relative depth information of blood vessels cannot be preserved.

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
  • Image processing method based on near-infrared imaging and terminal
  • Image processing method based on near-infrared imaging and terminal
  • Image processing method based on near-infrared imaging and terminal

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] Please refer to Figure 1 to Figure 6 , Embodiment 1 of the present invention is:

[0063] An image processing method based on near-infrared imaging, comprising the steps of:

[0064] S1. Obtain convolution kernels in different directions respectively, where the dimension of the convolution kernel is n and the number of directions is m. The convolution kernel is a matrix of n rows and n columns. The larger n is, the finer the convolution algorithm is, and the better the quality of the preprocessed image is. Stream lag. Therefore, in order to obtain perfect results in both image quality and processing time, preferably, the value range of n is [27,39]. The convolution kernels in different directions are different. The more the number of directions m is, the more the number of convolution kernels will be, and the convolution algorithm will be more refined, but it will lead to increased computation and longer processing time. Preferably, the value range of m is [6,12]. T...

Embodiment 2

[0077] Please refer to Figure 7 , the second embodiment of the present invention is:

[0078] An image processing terminal 100 based on near-infrared imaging, corresponding to the method in Embodiment 1, includes a memory 1 and a processor 2, wherein a computer program is stored in the memory 1, and when the processor 2 executes the computer program Implement the following steps:

[0079] Obtain convolution kernels in different directions respectively, the dimension of the convolution kernel is n, and the number of directions is m;

[0080] Obtaining a matrix of interest from the original grayscale image by traversal, where the dimension of the matrix of interest is n;

[0081] performing convolution operations on the matrix of interest with convolution kernels in different directions to obtain m new element matrices;

[0082] Taking the maximum value of the new element values ​​of the same coordinates in the m new element matrices to obtain a preprocessed image matrix;

...

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 image processing method based on near-infrared imaging and a terminal. The image processing method comprises the steps: respectively obtaining convolution kernels in different directions, the dimension of each convolution kernel being n, and the number of directions being m; obtaining an interested matrix from the original grayscale image in a traversal mode, wherein thedimension of the interested matrix is n; performing convolution operation on the interested matrix and convolution kernels in different directions to obtain m new element matrixes; taking the maximumvalue of the new element values with the same coordinates in the m new element matrixes to obtain a preprocessed image matrix; and performing color assignment on the preprocessed image matrix to obtain a final image. The image processing method performs convolution operation on the original grayscale image and a convolution kernel to obtain a pre-processed image with enhanced blood vessels ratherthan inhibited blood vessels, wherein the pre-processed image still well reserves relative depth information of the blood vessels; and the image processing method performs color assignment on the preprocessed image so that the preprocessed image is enabled to have better human eye identification degree.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an image processing method and terminal based on near-infrared imaging. Background technique [0002] At present, there are near-infrared projection vascular imaging devices on the market for image processing. In order to distinguish blood vessels from non-vascular imaging devices, most of them use binarization algorithms, that is, blood vessels and non-vascular imaging devices only have two values ​​after binarization. (For example, blood vessels are represented by 0, and non-blood vessels are represented by 255). This traditional binarization algorithm is represented by 0 below a certain threshold, and 255 above a certain threshold, ignoring the depth information of blood vessels. And the disadvantage of this algorithm is that there are a lot of noise on the edges of blood vessels, the blood vessels and non-vessels are too stiff, the quality of blood vessel ex...

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): G06T5/00G06T11/40
CPCG06T11/40G06T2207/10048G06T2207/20104G06T2207/30101G06T5/94Y02D10/00
Inventor 周俊波陈健敏
Owner SHENZHEN YUANHUA MEDICAL EQUIP TECH 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