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

Cigar harvesting maturity identification method and system based on ensemble learning

An integrated learning and recognition method technology, applied in the field of cigar harvest maturity recognition method and system, can solve problems such as difficulty in ensuring accuracy and efficiency, decline in tobacco leaf quality, impact, etc., to ensure extraction and utilization, and reduce training costs , Improve the effect of harvesting efficiency

Active Publication Date: 2022-08-05
HUBEI TOBACCO SCI RES INST
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, in the production of air-cured tobacco leaves, due to different regions, climate, soil fertility, moisture, cultivation methods, etc. are quite different, and the standards for suitable maturity are different. adversely affect
In addition, most of the agricultural fields still use manual harvesting and naked eye identification of maturity, which is difficult to ensure accuracy and efficiency. The phenomenon of overripe picking in the lower part, raw picking in the middle part, and green picking in the upper part is common, resulting in a decline in the quality of tobacco leaves after air curing and affecting tobacco leaves. Industrial Availability of Tobacco Leaf

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
  • Cigar harvesting maturity identification method and system based on ensemble learning
  • Cigar harvesting maturity identification method and system based on ensemble learning
  • Cigar harvesting maturity identification method and system based on ensemble learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0071] The invention provides a method for identifying the maturity of cigar harvesting based on integrated learning, which is mainly applied to the work of harvesting cigars in the field. like figure 1 As shown, the method includes: a cigar collection step; an image preprocessing step; a vectorization dimension reduction step; a feature dimension reduction step and a model identification step.

[0072] The specific implementation is as follows:

[0073] S1. Cigar collection step: collect cigar image data during the collection process, upload it to the cloud platform database through a transmission device, and form the original data set for model training.

[0074] S2. Image preprocessing step: using non-local average denoising algorithm, dark channel dehazing algorithm and image color correction algorithm to preprocess the collected cigar image to improve image quality.

[0075] The preprocessing steps for cigar smoke images are as follows:

[0076] S21 , denoising the cig...

Embodiment 2

[0113] According to an aspect of the specification of the present invention, a cigar harvest maturity identification system based on integrated learning is provided, including: an acquisition module for acquiring a cigar image; a preprocessing module for preprocessing the cigar image ;Vectorized dimensionality reduction module, used to perform vectorized dimensionality reduction on the preprocessed cigar image, and extract RGB and HSV eigenvalues ​​to obtain a feature set; Feature dimensionality reduction module, used for infinite data in the feature set Generalize operation, and use Wrapper packaging algorithm to reduce the feature dimension of the data in the feature set to obtain the initial data set of the cigar image to be tested; the model recognition module is used to input the initial data set into the trained random forest model, A ripeness identification result of the cigar image is output.

[0114] Further, the system further includes a data cleaning module, which p...

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 cigar harvesting maturity identification method and system based on integrated learning, and the method comprises the steps: obtaining a to-be-detected cigar image, and carrying out the preprocessing of the to-be-detected cigar image; vectorization dimension reduction is carried out on the preprocessed to-be-detected cigar image, RGB and HSV feature values are extracted, and a feature set is obtained; performing feature dimension reduction on data in the feature set by using a Wrapper packaging algorithm to obtain an initial data set of the to-be-detected cigar image; and inputting the initial data set into the trained random forest model, and outputting a maturity identification result of the cigar image. According to the method, vectorization dimension reduction is carried out on cigar image data, and efficient extraction and utilization of cigar image data information are guaranteed; meanwhile, by means of the advantages of integrated learning, the tobacco leaf texture and color serve as input features of a maturity level identification model, and the problem that data value is damaged is solved; and feature dimension reduction is carried out while feature selection is realized by using a Wrapper packaging algorithm, so that the training cost of the model is reduced.

Description

technical field [0001] The invention relates to the technical field of cigar classification, in particular to a method and system for identifying the maturity of cigar harvesting based on integrated learning. Background technique [0002] The physical and biochemical properties of tobacco leaves grown in the field will change significantly during the development and maturity. The maturity state of cigars at harvest directly determines the quality of tobacco leaves before air-curing, and is closely related to the appearance, internal and sensory quality of tobacco leaves after air-curing. Even for the same variety of tobacco leaves, the difference in maturity will affect the yellowing, color fixing characteristics and water loss characteristics of the cured tobacco leaves, which will affect the quality of tobacco leaves to a certain extent. The premise and foundation of tobacco leaves. [0003] When harvesting cigars, farmers often further subdivide the cigars in different ...

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): G06T7/00G06T5/00G06V10/30G06V10/762G06V10/764G06V10/774G06K9/62G06N20/00G06N20/20
CPCG06T7/0012G06V10/30G06V10/763G06V10/774G06V10/764G06N20/00G06N20/20G06T2207/10024G06T2207/20081G06F18/23213G06F18/22G06F18/214G06F18/24323G06T5/90G06T5/73G06T5/70Y02P90/30G06V20/68G06V20/80G06V10/76G06V10/7625G06T7/90G06T2207/20182G06T2207/30188
Inventor 杨春雷孙光伟杨锦鹏余君饶雄飞裴文灿刘小伟刘竞黄金国
Owner HUBEI TOBACCO SCI RES INST
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