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

Method and device for identifying fresh meat, chilled meat, and frozen meat based on hyperspectrum

A hyperspectral and meat-cooling technology, which is applied in the field of chilled meat and frozen meat, to identify fresh meat, can solve the problems of inability to distinguish between chilled meat and frozen meat, complicated operation steps, and large destructiveness, so as to block the interference of external light, Overcoming the effects of destructiveness and accurate model classification

Active Publication Date: 2015-09-09
SOUTH CHINA UNIV OF TECH
View PDF5 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the above method has the disadvantages of high destructiveness, low efficiency, and complicated operation steps, and cannot effectively distinguish chilled meat from frozen meat quickly.

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 identifying fresh meat, chilled meat, and frozen meat based on hyperspectrum
  • Method and device for identifying fresh meat, chilled meat, and frozen meat based on hyperspectrum
  • Method and device for identifying fresh meat, chilled meat, and frozen meat based on hyperspectrum

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] like figure 1 As shown, the hyperspectral-based device for identifying fresh meat, chilled meat and frozen meat in this embodiment includes a darkroom 2-1, a hyperspectral image acquisition system, a transport device 2-7, an object stage 2-8 and a computer 2 -10, the hyperspectral image acquisition system, transmission device, and object stage are installed in the darkroom and connected to the computer installed outside the darkroom; the object stage is fixed on the transmission device, and the object stage adopts light-transmitting Made of PET material; the hyperspectral image acquisition system is located under the conveying device.

[0057] The hyperspectral image acquisition system includes a hyperspectral camera 2-2, a lens 2-3, an adjustable light source 2-4 for a retractable shading cylinder, an adjustable light source 2-5 and a line light source 2-6; The upper part of the camera; the telescopic shading tube is installed on the top of the lens and sleeved on the...

Embodiment 2

[0077] The method for identifying fresh meat, chilled meat and frozen meat based on hyperspectral of the present embodiment comprises the following steps:

[0078] (1) Carry out hyperspectral scanning to the beef sample, obtain 0 reflectance hyperspectral image and total reflectance hyperspectral image, and correct the acquired hyperspectral image;

[0079] (2) Select the region of interest of the beef sample on the corrected 0-reflectance hyperspectral image and total reflectance hyperspectral image, and obtain the spectral reflectance values ​​of the region of interest at characteristic wavelengths (479nm, 601nm and 776nm); The hyperspectral image is subjected to principal component analysis to obtain the PC image, and the PC image with the highest weight coefficient is extracted. Using the gray gradient co-occurrence matrix model, the step size is selected as 1, and the correlation T of the 0-degree angle is extracted. 1 , gray entropy T 2 , and gradient entropy T 3 , and...

Embodiment 3

[0092] The method for identifying fresh meat, chilled meat and frozen meat based on hyperspectral of the present embodiment comprises the following steps:

[0093] (1) Carry out hyperspectral scanning on the mutton sample, obtain hyperspectral images of 0 reflectance and total reflectance hyperspectral images, and correct the acquired hyperspectral images;

[0094] (2) Select the region of interest of the mutton sample on the corrected 0-reflectance hyperspectral image and total reflectance hyperspectral image, and obtain the spectral reflectance values ​​of the region of interest at the characteristic wavelengths (549nm, 638nm and 774nm); The hyperspectral image is subjected to principal component analysis to obtain the PC image, and the PC image with the highest weight coefficient is extracted. Using the gray gradient co-occurrence matrix model, the step size is selected as 1, and the correlation T of the 0-degree angle is extracted. 1 , gray entropy T 2 , and gradient entr...

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 for identifying fresh meat, chilled meat, and frozen meat based on hyperspectrum. The method comprises the following steps: (1) obtaining a zero-reflectivity hyperspectral image and a total-reflectivity hyperspectral image of a meat sample; (2) selecting an area-of-interest of the meat sample on the corrected hyperspectral image, obtaining a spectral reflectance value of the area-of-interest under characteristic wavelength, extracting a PC image with highest weight coefficient of the hyperspectral image, and calculating textural features of the PC image; (3) discriminating by adopting a first discriminant analysis model based on the Fisher discriminant; and (4) discriminating by adopting a second discriminant analysis model based on the Fisher discriminant. With the method, the robustness of a classification model is greatly improved, and the classification of the model is accurate. The invention further discloses a device for identifying fresh meat, chilled meat, and frozen meat based on the hyperspectrum, and the quality of the hyperspectral image is improved.

Description

technical field [0001] The invention relates to the field of hyperspectral non-destructive testing, in particular to a hyperspectral-based method and device for identifying fresh meat, chilled meat and frozen meat. Background technique [0002] Meat is one of the important ingredients in people's daily life. The meat sold on the market can be roughly divided into fresh meat and cold-processed meat. Cold-processed meat includes chilled meat and frozen meat. Generally speaking, fresh meat and chilled meat have higher nutritional value and better taste; frozen meat generally has a longer storage time, more water loss, serious nutrient loss, and poorer taste. At the same time, the price of frozen meat is much lower than that of fresh meat and chilled meat. By controlling the freezing and thawing conditions, it is difficult to distinguish some frozen meat from chilled meat after thawing, leading some unscrupulous traders to use frozen meat as shoddy and earn huge profits. It is...

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): G01N21/25
Inventor 孙大文马骥蒲洪彬曾新安高文宏曲佳欢
Owner SOUTH CHINA UNIV OF TECH
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