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

Aquatic product classification method and system based on machine vision

A technology of machine vision and classification method, applied in the classification/classification of crustaceans/bivalves, fish sorting, processing crustaceans, etc., can solve the problems of low accuracy and slow manual classification speed, and achieve cost savings , to avoid secondary damage and ensure the effect of accuracy

Inactive Publication Date: 2018-11-02
ZHEJIANG OCEAN UNIV
View PDF7 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a machine vision-based aquatic product classification method and system to solve the problems of slow speed and low accuracy of existing manual classification

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
  • Aquatic product classification method and system based on machine vision
  • Aquatic product classification method and system based on machine vision
  • Aquatic product classification method and system based on machine vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] refer to figure 1 , figure 1 A method for classifying aquatic products based on machine vision is provided, including steps:

[0048] S10: Acquire image information of the aquatic product, perform image preprocessing on the image information, and obtain the image contour area of ​​the aquatic product;

[0049] S20: Obtain the weight data of the aquatic product, and establish a prediction model according to the weight data of the aquatic product and the image contour area;

[0050] S30: Receive the classification signal, obtain the image contour area of ​​the current aquatic product, and obtain the predicted weight of the current aquatic product according to the prediction model;

[0051] S40: Classify the current aquatic product according to the predicted weight of the current aquatic product.

[0052] Aquatic products are mainly fish. Fish have a smooth surface. Generally, fish have a complete and uniform shape. Although there are differences between different fish ...

Embodiment 2

[0072] refer to Figure 7 , Figure 7 A kind of aquatic product classification method based on machine vision provided for the present embodiment, comprises steps:

[0073] S10: Acquire image information of the aquatic product, perform image preprocessing on the image information, and obtain the image contour area of ​​the aquatic product;

[0074] S20: Obtain the weight data of the aquatic product, and establish a prediction model according to the weight data of the aquatic product and the image contour area;

[0075] S30: Receive the classification signal, obtain the image contour area of ​​the current aquatic product, and obtain the predicted weight of the current aquatic product according to the prediction model;

[0076] S401: Receive a preset weight range, determine that the predicted weight is within the preset weight range, and if so, send a trigger signal to a corresponding sorting controller to sort the current aquatic product.

[0077] The difference between this...

Embodiment 3

[0082] refer to Figure 8 , the present embodiment provides a system structure diagram of a machine vision-based aquatic product classification system, including:

[0083] Image processing module 81: used to obtain image information of aquatic products, perform image preprocessing on the image information, and obtain the image contour area of ​​the aquatic products;

[0084] Weight collection module 82: used to obtain the weight data of the aquatic product, and establish a prediction model according to the weight data and image outline area of ​​the aquatic product;

[0085] Prediction module 83: used to receive the classification signal, obtain the image outline area of ​​the current aquatic product, and obtain the predicted weight of the current aquatic product according to the prediction model;

[0086] Classification module 84: for classifying the current aquatic product according to the predicted weight of the current aquatic product.

[0087] The system also includes a...

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 an aquatic product classification method and system based on machine vision. The method and system are used for solving the problems of poor precision and low efficiency of aquatic product manual classification. The method comprises the following steps of S10, obtaining image information of an aquatic product; performing image preprocessing on the image information to obtainthe image profile area of the aquatic product; S20, obtaining the weight data of the aquatic product; building a prediction model according to the weight data and the image profile area of the aquatic product; S30, receiving classification signals; obtaining the image profile area of the current aquatic product; obtaining the prediction weight of the current aquatic product according to the prediction model; S40, classifying the current aquatic product according to the prediction weight of the current aquatic product. By using the method and the system, the size of the aquatic product is judged through machine vision; the weight information is further obtained, so that the water product is subjected to automatic classification; the classification efficiency and the precision are improved;the labor cost is reduced.

Description

technical field [0001] The invention relates to the technical field of machine vision, in particular to a machine vision-based aquatic product classification method and system. Background technique [0002] Aquatic products are mainly fish in fresh water or sea water. After the fish is caught, it is necessary to classify and screen the fish to meet various needs in the market. After the fish is landed, enterprises or farmers will classify large yellow croakers according to their weight and quality, so as to facilitate their sale and profit. At present, the equipment for grading fish mainly includes weighing type, optical principle type, shape type, etc. according to the different grading principles. The weighing type grading machine uses a mass sensor to classify according to the weight of the fish body, and the grading accuracy is high, but it needs Weighing one by one, the efficiency is low; the optical principle grading machine is based on photoelectric distance measurem...

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): A22C25/04A22C29/00
CPCA22C25/04A22C29/005
Inventor 吴远红庄瑞崔振东
Owner ZHEJIANG OCEAN UNIV
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