Automatic grading system and method based on mass tobacco leaf data

A tobacco leaf and data technology, applied in the field of automatic grading system, can solve the problems that there are no equipment and technical inventions that can comprehensively detect and extract the characteristics of tobacco leaf automatic grading, and can not meet the actual requirements, so as to improve the speed, ensure the effectiveness, reduce the effect of complexity

Active Publication Date: 2014-04-23
SHANGHAI UNIV
View PDF5 Cites 47 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, until recently, the research on extracting the characteristic parameters of tobacco leaves and the system software for automatic grading of tobacco leaves is still in the stage of experimentation and discussion. There is no equipment and technical invention that can fully detect and extract characteristics

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
  • Automatic grading system and method based on mass tobacco leaf data
  • Automatic grading system and method based on mass tobacco leaf data
  • Automatic grading system and method based on mass tobacco leaf data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] see figure 1 , the automatic grading system based on massive tobacco leaf data is characterized in that it includes the following components, connected through a gigabit switch (8):

[0054] Camera and video capture card (2): used to collect images of tobacco leaves (1);

[0055] PC1 image acquisition and processor (3): by using the camera (2) and video acquisition card to collect, preprocess and feature extract the real scene, construct the classification model of relevant tobacco leaves;

[0056] PC2 storage and search engine processor (4): responsible for system data query, storage and search of relevant tobacco images and feature data, and management of expert tobacco leaf grading rule base;

[0057] PC3 communication and system monitoring processor (5): it is the communication and control center of the system, and also completes tasks such as grading information audio output control, grading information display control, and hardware equipment status monitoring;

...

Embodiment 2

[0066] This embodiment is basically the same as Embodiment 1, and the special features are as follows:

[0067] 1) The camera and video capture card (2): The LCH-P49A industrial camera of CBC Company is used, which has backlight compensation, automatic white balance, automatic gain control and other functions. Its camera uses 1 / 4"CCD (3.2×2.4mm), with a horizontal resolution of 500 lines. The parameters of the lens are adjustable, the focal length range is 4-9mm, the maximum aperture ratio is 1:1.6, and the horizontal viewing angle range is 51.8°- 23.8°, the adjustable range of vertical viewing angle is 38.3°-17.8°, the camera has many adjustable parameters, the resolution is high, and the image quality captured by it is very good, it is a choice that is more in line with the original design intention; for the camera, The Microview V211 video capture card is used, which is based on the PCI bus and collects two-way high-quality real-time professional image capture cards of PAL ...

Embodiment 3

[0074] see figure 2 , this automatic grading method based on massive tobacco leaf data, adopts the above-mentioned system to operate, and its characteristics are as follows:

[0075] 1): Image collection: use a camera and a video capture card (2) to collect images of tobacco leaves in the area to be detected;

[0076] 2): Feature acquisition: analyze and preprocess the tobacco leaf image, retain the image part of visual concern, remove noise, and then extract the relevant detailed features of the tobacco leaf to ensure the sparsity and relevance of the data;

[0077] 3): Model construction: Obtain different types of tobacco leaf characteristic data from the tobacco leaf characteristic database, carry out model construction, and provide models for subsequent decision-making;

[0078] 4): Tobacco leaf grading: analyze the tobacco leaf image and characteristic data, obtain expert knowledge through the expert tobacco leaf grading rule base, and obtain the corresponding tobacco l...

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

PropertyMeasurementUnit
Horizontal viewing angleaaaaaaaaaa
Login to view more

Abstract

The invention relates to an automatic grading system and an automatic grading method based on mass tobacco leaf data. The automatic grading system belongs to a system for carrying out analysis, storage, retrieval and automatic grading on tobacco leaf images by utilizing computer vision, image analysis, machine learning, big data retrieval and artificial intelligence technological algorithms. A mass data retrieval technology is introduced into an automobile tobacco leaf grading system, and corresponding databases and efficient retrieval engines are built, so grading results are more accurate, and the big data concept can become an irresistible trend along with the computer technology development. An artificial intelligence expert system algorithm is introduced, tobacco leaf knowledge in the specific fields is utilized for constructing an expert knowledge base, various complicated tobacco grading problems which can only be solved by human experts are simulated, and the computer intelligence with the same problem solving capability as the experts in the field is reached.

Description

technical field [0001] The present invention relates to an automatic grading system and method based on massive tobacco leaf data, specifically a technical algorithm that uses computer vision, image analysis, machine learning, big data retrieval and artificial intelligence to analyze tobacco leaf images, A system and related method for storage, retrieval and automatic rating. Background technique [0002] For a long time, whether at home or abroad, the detection and grading of tobacco leaf quality refer to the tobacco leaf grading standards and standard tobacco leaf samples promulgated by various regions, and rely on human visual and tactile senses to judge and grade. Therefore, before the purchase of tobacco leaves, each tobacco area in the country must set up a study class to collect a large number of standard tobacco leaf samples as training materials to train the tobacco leaf grading personnel at the purchase station. Such a grading method requires a lot of consumption a...

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): G01J3/46G01B11/00G01B11/24G01N21/84G06K9/54G06K9/62
Inventor 陈一民邹一波黄晨张典华张云华李泽宇
Owner SHANGHAI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap