Supercharge Your Innovation With Domain-Expert AI Agents!

Combined light perspective based visual recognition detection method of stems and stem ratios in leaves

A detection method and visual recognition technology, applied in the direction of character and pattern recognition, image data processing, instruments, etc., can solve the problems of not being able to satisfy the real-time control of production dynamics, destroying the shape of tobacco leaves, and losing the original value of tobacco leaves, etc. , to achieve easy engineering implementation and popularization and application, reduce the impact of detection results, and overcome the effect of long detection cycle

Active Publication Date: 2012-02-01
南京焦耳科技有限责任公司
View PDF7 Cites 45 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These devices are of positive significance for improving the threshing performance and leaf stem separation of the threshing and re-roasting production line, but they are not suitable as an online real-time detection method, because the detection cycle of this equipment method is long (several hours) It has hysteresis and cannot well meet the requirements of dynamic real-time control of production
And after the detection, the shape of the tobacco leaves is destroyed, so that the tobacco leaves lose their original value
Therefore, it is necessary to research and develop new detection methods to change the current detection hysteresis

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
  • Combined light perspective based visual recognition detection method of stems and stem ratios in leaves
  • Combined light perspective based visual recognition detection method of stems and stem ratios in leaves
  • Combined light perspective based visual recognition detection method of stems and stem ratios in leaves

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] The present invention uses a tobacco leaf and stem detection and sorting device to carry out a method for visual recognition and detection of stems in leaves based on transmitted light. image 3 An example of detection of stalk content in leaves of threshing and re-roasting production line. Proceed as follows:

[0044] The first step, sampling and fully diluted. Firstly, a 3 kg leaf threshing sample is taken online from the leaf threshing and re-roasting production line through the sampling device. One of the implementation methods of the sampling device is a combination of mechanical grabbing (or funnel) and weighing. The thinning system is mainly composed of vibrating plate, seven-star roller, high-speed belt conveyor, flat sorting pipeline and recycling channel, etc. The principle and process of dilution are described as follows:

[0045] 1) 3 kg of sampled tobacco leaves are first conveyed to the seven-star rollers through the vibrating disc, and the gap between ...

Embodiment 2

[0064] The light source in step 2 in Example 1 is replaced by a near-infrared light source with a wavelength of 920nm and a power of 100W surface light source. The example of backlight transmission to obtain the tobacco leaf image is as follows: Figure 6 (a), (b) and (c), the slender area with darker color in the figure is the tobacco stem. It can be seen from the figure that the blade and the tobacco stem area can be clearly distinguished by using the near-infrared light source, and the corresponding identification Test results such as Figure 6 (d), (e) and (f), the white area in the figure represents the identified tobacco stem area, and the results show that the near-infrared light source can better obtain clear perspective images of tobacco leaves and stems. Figure 6 (c) The middle part of the upper and lower tobacco stems is the overlapping area of ​​leaves. From the results, when the leaves do not cover the next layer of tobacco stems, the upper and lower tobacco stem...

Embodiment 3

[0066] Considering that the tobacco leaves have more overlapping adaptability, the light source of this example chooses a light source with high penetrating power such as a soft X-ray light source, and other steps are similar to the first embodiment. Examples of tobacco leaf images and tobacco stem detection and recognition results obtained in the experiment Figure 7 shown. Figure 7 (a) is a photo of the real object. The tobacco stems in the area indicated by the red frame in the figure are completely wrapped by tobacco leaves, and the blue frame is covered by multiple tobacco leaves (more than 5 pieces). Figure 7 (b) is the obtained soft X-ray fluoroscopy image, Figure 7 (c) is the result of extraction of tobacco stems after treatment. From Figure 7 (b) It can be seen that the tobacco stem (slender white area) is very clear and easy to identify, whether it is wrapped by tobacco leaves or covered by multiple tobacco leaves, Figure 7 The recognition results of (c) als...

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 combined light perspective based visual recognition detection method of stems and stem ratios in leaves. The method comprises the following steps of: thinning and spreading tobacco leaves by vibration plates, star-like rollers and a high-speed belt conveyer; forming perspective images of leaves and tobacco stems based on parallel combined light perspective; extracting image characteristics to recognize the tobacco stems and the leaves; and calculating the stem ratios in the leaves, namely calculating the volumes of the tobacco stems and the leaves according to the obtained shape and size characteristics of the tobacco stems and the leaves, and combining the measured density of the tobacco stems and the leaves to calculate the masses of the tobacco stems and the leaves, thus obtaining the stem ratios in the leaves. The invention has the following advantages: non-contact visual online detection of the stems in the leaves is realized, the visual method has the obvious characteristics of fastness, high efficiency and the like, and the following problem is solved: at present, the threshing and re-drying production line offline detection method has a longer detection period (several hours), has hysteretic nature relative to production and can not well meet the requirement for dynamic real-time control of production.

Description

technical field [0001] The invention belongs to the technical field of identification and detection of tobacco leaf and tobacco sheet structures in the tobacco industry, in particular to a method for visual identification and detection of stalk content and stalk content rate in leaves based on combined light perspective. Background technique [0002] Judging from the demand of cigarette industry enterprises for raw materials of tobacco leaves, it is hoped that the index of stalk content in the finished tobacco sheets provided by threshing and redrying enterprises should be as low as possible, because a high stalk content rate in leaves will not only make cut tobacco The amount of middle stem sticks and stem blocks increases, and the purity of shredded tobacco is low, which will affect the operating efficiency of the cigarette making machine and the quality of cigarette products. At the same time, the stalk content rate in the leaves has an impact on the quality of threshing ...

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): G06K9/46G06T7/00A24B3/16G06T7/136
Inventor 刘永刘承钧
Owner 南京焦耳科技有限责任公司
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