Supercharge Your Innovation With Domain-Expert AI Agents!

Large-field tobacco image de-noising method

An image and tobacco leaf technology, applied in the field of digital image processing, can solve problems such as poor texture suppression effect, and achieve the effects of reducing double edge and pseudo edge phenomenon, suppressing noise, and enhancing edge coefficients

Inactive Publication Date: 2015-12-09
GUANGDONG BRANCH OF CHINA TOBACCO GENERAL
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing methods are suitable for edges with large steps, but for the detection of weak edges, the suppression effect of texture is not good

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
  • Large-field tobacco image de-noising method
  • Large-field tobacco image de-noising method
  • Large-field tobacco image de-noising method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] like figure 1 As shown in the figure, a method for denoising an image of tobacco leaves in the field includes the following steps:

[0040] S1: Perform multi-scale and multi-direction non-subsampling Shearlet transform (NSST) decomposition on the noisy image to obtain the high-frequency coefficients of the noisy image in the NSST domain;

[0041] S2: Select two adjacent large-scale high-frequency coefficients to perform an improved scale product operation to obtain a scale and multi-directional high-frequency coefficient;

[0042] S3: Perform NSST modulus maximum operation on the high-frequency coefficients obtained in S2 to obtain an edge binary image;

[0043] S4: Translate the edge binary image to the upper left corner, and remove the remaining isolated noise points in the edge binary image according to the regional connectivity to obtain the final edge image.

[0044] The process of improving the scale product operation in step S2 is as follows:

[0045] S21: Per...

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 large-field tobacco image de-noising method. In the case of a noise-containing image, a large-scale high-frequency coefficient in a NSST domain has few noise and texture components. Large-scale edge detection enhances the anti-noise characteristic of the method, effectively prevents multiple edges and reduces pseudo edges. Single-pixel edge is acquired by using NSST-mode maximum value method and residual isolated noise points are removed by using area connectivity, thereby enhancing the anti-noise characteristic of the edge detection method again. The method has a better anti-noise characteristic and a texture inhibition capability and is an effective noise-containing image edge detection method. The detected edges are most single-pixel responses and good in continuity.

Description

technical field [0001] The invention relates to the field of digital image processing, and more particularly, to a method for denoising an image of field tobacco leaves. Background technique [0002] Edge detection is one of the basic links in tobacco leaf image analysis, and the quality of its detection results will directly affect the subsequent feature extraction and classification and recognition. In the actual imaging process, due to the imaging system itself and external factors, the image will inevitably be polluted by noise. Therefore, it is of great practical significance to study an edge detection method with anti-noise to extract the edge of the image more robustly. Existing edge detection methods are mainly divided into spatial domain methods and transform domain methods. The spatial edge detection methods are further divided into surface fitting method and gradient threshold method. The edge location extracted by the surface fitting method is accurate, and it...

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): G06T7/00
CPCG06T7/0012G06T2207/10004G06T2207/20048G06T2207/20192G06T2207/30004
Inventor 陈泽鹏
Owner GUANGDONG BRANCH OF CHINA TOBACCO GENERAL
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com