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

Method and device for rapid nondestructive detection of fish freshness based on computer vision

A computer vision and non-destructive testing technology, applied in computer parts, computing, instruments, etc., can solve the problems of inability to achieve rapid non-destructive testing, low detection accuracy, time-consuming and labor-intensive, etc., to avoid poor detection accuracy, accurate classification results, etc. Good application prospects

Active Publication Date: 2019-11-12
SHANGHAI OCEAN UNIV
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to overcome the defects that the process of distinguishing the freshness of fish body in the prior art is cumbersome, slow, time-consuming and laborious, cannot realize fast non-destructive detection and low detection accuracy, and provide a fast detection method for fish freshness with high detection accuracy. Non-destructive testing method and device thereof

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
  • Method and device for rapid nondestructive detection of fish freshness based on computer vision
  • Method and device for rapid nondestructive detection of fish freshness based on computer vision
  • Method and device for rapid nondestructive detection of fish freshness based on computer vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] The present invention verifies the accuracy of the fast non-destructive detection method for fish body freshness based on computer vision:

[0064] Its step (3.1) concrete operation is as follows:

[0065] Put 75 grass carp that had just died into fresh-keeping bags, and then put them in a 4°C incubator. Every other day, 15 samples were randomly selected for shooting, and the pictures of the left and right eyes of grass carp were obtained for 8 consecutive days. Among them, the specific parameters of the camera Parameters: sensitivity ISO: 100, aperture F: 5.3, exposure time: 1 / 250s, flash: none, mode: manual, focal length: 45mm, white balance: automatic, image format: PNG.

[0066] Then use the algorithm in the MATLAB software to obtain 9 color eigenvalue data of RGB, L*a*b* and HIS color space from the obtained grass carp left and right eye pictures, and store the 9 color eigenvalue data in EXCLE. One set of data is obtained by only one eye, and 150 sets of data can ...

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 method and a device for rapid nondestructive detection of fish freshness based on computer vision. The method comprises the following steps: acquiring characteristic information of a fish body, and confirming the freshness grade of the fish body; wherein the feature information is obtained by collecting an image of a fisheye and processing the image, and the processing refers to extracting color feature values of RGB, HIS and L * a * b * color space in the image; wherein the freshness level is determined by taking the freshness level, the feature information of the fish body with the known freshness level and the feature information of the current fish body with the to-be-determined freshness level as categories respectively and correspondingly, and adopting a one-to-one SVM classification method for the training sample and the test sample. The device comprises a computer for operating the method. According to the method for detecting the freshness of the fishbody, samples do not need to be pretreated and the detection precision is high. No chemical reagent is used, the environmental friendliness is good, and the detection cost is low. The device is simple in structure, high in detection speed and good in application prospect.

Description

technical field [0001] The invention belongs to the technical field of freshness detection of aquatic products, and relates to a computer vision-based fast and non-destructive detection method and device for freshness of fish. Background technique [0002] Fish is not only rich in protein, vitamins and minerals, but also low in fat, good in taste, easy to digest and absorb, and is an important source of human nutrients. However, compared with other meats, fish contains many endogenous enzymes and psychrophilic microorganisms. The loose connective tissue of fish divides fish into many small muscle groups, and bacteria are more likely to invade muscles along the loose interstitium. Therefore, in the case of improper handling, transportation or storage, a series of physical, chemical and microbial changes will occur in the fish body, resulting in spoilage and deterioration of the fish body, such as the decomposition of protein into amino acids and other alkaline substances, oxi...

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): G06K9/46G06K9/62
CPCG06V10/56G06F18/2411Y02A40/81
Inventor 卢瑛杨明远
Owner SHANGHAI 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