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

Tobacco leaf image quality evaluation method, system, memory, and electronic equipment

A quality evaluation and image quality technology, applied in image analysis, image data processing, instruments, etc., can solve problems such as poor stability and long time-consuming

Active Publication Date: 2021-07-06
SHANGHAI TOBACCO GRP CO LTD +1
View PDF21 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the shortcomings of the prior art described above, the purpose of the present invention is to provide an evaluation method, system, memory, and electronic equipment for tobacco leaf image quality, which are used to solve the problem of poor stability when evaluating the quality of tobacco leaf image in the existing tobacco leaf image quality evaluation method. time-consuming issues

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
  • Tobacco leaf image quality evaluation method, system, memory, and electronic equipment
  • Tobacco leaf image quality evaluation method, system, memory, and electronic equipment
  • Tobacco leaf image quality evaluation method, system, memory, and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] see figure 1 , the present embodiment provides a tobacco leaf image quality evaluation method with high stability and short calculation time, which mainly includes the following steps:

[0031] S1: Extract the component values ​​of each pixel in the RGB color space of the tobacco leaf image to be evaluated.

[0032] It should be noted that the RGB color space here is a new color space converted from the traditional machine vision RGB (R, G, B) space according to RGB (R+G, 0.7B, 0.3B). As we all know, R, G, and B are red, green, and blue spaces, and the basic color theme of tobacco leaves is yellow, and the characterization of yellow is determined by (R+G) / B. The larger the value, the closer the color is to yellow. Therefore, it is necessary to split RGB into R+G and B during color conversion. In addition, since the B value is also an indicator to measure the brightness of the shooting environment, the B value also has a certain meaning, so the B value also needs to be...

Embodiment 2

[0042] according to figure 1 The method flow shown for figure 2 Tobacco leaf image quality evaluation, the specific steps are as follows:

[0043] Step 1, extract the component values ​​of each pixel in the RGB color space of the tobacco leaf image to be evaluated:

[0044] When i=1: R 1 =RGB(1,1)=336.22; G 1 =RGB(1,2)=22.32; B 1 =RGB(1,3)=9.56.

[0045] When i=2: R 2 =RGB(2,1)=310.37; G 2 =RGB(2,2)=22.89; B 2 =RGB(2,3)=9.76.

[0046] When i=3: R 3 =RGB(3,1)=325.22; G 3 =RGB(3,2)=23.13; B 3 =RGB(3,3)=9.32.

[0047] ………………

[0048] When i=n: R n =RGB(n,1)=325.22; G n =RGB(n,2)=23.76; B n =RGB(n,3)=9.18.

[0049] Step 2, solving the color gamut index of each pixel of the tobacco leaf image to be evaluated:

[0050] When i=1: CGIR 1 =R 1 / (G 1 +B 1 ) = 10.546; CGIG 1 =G 1 / (R 1 +B 1 ) = 0.0645; CGIB 1 =B 1 / (R 1 +G 1 ) = 0.02941.

[0051] When i=2: CGIR 2 =R 2 / (G 2 +B 2 ) = 9.506; CGIG 2 =G 2 / (R 2 +B 2 ) = 0.0715; CGIB 2 =B 2 / (R 2 +G ...

Embodiment 3

[0066] use figure 1 The method flow shown, for Figure 3a-3d The quality of the four tobacco leaf images is evaluated and sorted to obtain the quality evaluation of each tobacco leaf image The values ​​and their ordering are shown in Table 1. visible, Figure 3d of The value is the largest, and the ranking is first, indicating that the quality of the tobacco leaf image is the best; Figure 3b of The smallest value indicates that the quality of the tobacco leaf image is the worst. In fact, Figure 3d Capture images for high-quality camera + high-quality light source conditions, while Figure 3b It is an image taken under the condition of ordinary industrial camera + online light source. It can be seen that the quality evaluation result given by the present invention also conforms to the subjective cognition of human vision and the actual objective factors.

[0067] Table 1

[0068]

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 present invention provides a tobacco leaf image quality evaluation method, system, memory, and electronic equipment, wherein the method includes: extracting each component value of each pixel in the color space of the tobacco leaf image to be evaluated; wherein, the color space consists of a yellow color gamut components, bright color gamut components, and black color gamut components; according to each component value of each pixel, calculate each color gamut index of each pixel; according to each color gamut index of each pixel , determining the quality evaluation index of each pixel; calculating the average value of each quality evaluation index, and comparing it with a preset quality evaluation index, so as to judge the quality of the tobacco leaf image to be evaluated. The invention utilizes the color gamut index to evaluate the tobacco leaf image quality. Compared with the existing tobacco leaf image quality evaluation method, the method has lower calculation complexity, less calculation amount, shorter calculation time, and better stability of quality evaluation results.

Description

technical field [0001] The invention belongs to the technical field of tobacco leaf image processing, and in particular relates to a tobacco leaf image quality evaluation method, system, storage medium and electronic equipment based on color gamut index. Background technique [0002] Tobacco leaf image quality evaluation is the basis and key to evaluate the imaging equipment, grading, appearance quality inspection and pattern recognition of tobacco leaves. At present, the evaluation methods of tobacco leaf image quality mainly include peak signal-to-noise ratio method PSNR and information entropy method SSEQ (Ji Jiangtao, Deng Mingli, He Zhitao, et al. Gaussian denoising method for flue-cured tobacco leaf image based on OpenCV[J]. Jiangsu Agricultural Science, 2016 , 44(11): 373-376.): (1) Peak Signal-to-Noise Ratio method PSNR: This method has been studied more and is the most mature, such as the invention patent of Tsinghua University Dai Qionghai, Ma Xiao, Cao Xun, etc. "...

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): G06T7/00G06T7/90
CPCG06T7/0004G06T7/90
Inventor 蔡宪杰薛超群张军窦家宇宋纪真薛庆逾郭文卢晓华张伟峰沈钢程森顾毓敏高远牟文君
Owner SHANGHAI TOBACCO GRP 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