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

Hyperspectral image detection method for quality indexes of mutton

A technology of hyperspectral image and detection method, which is applied in the field of non-destructive detection of hyperspectral image of meat products, can solve the problems of weak model prediction ability, unstable characteristic wavelength, and limited number of samples, so as to ensure the quality safety and representativeness of meat products Strong and maintain the effect of consumer health

Active Publication Date: 2017-10-20
SHIHEZI UNIVERSITY
View PDF7 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a hyperspectral image detection method for mutton quality indicators, which organically combines the spatial information of the hyperspectral image of mutton samples with the distribution characteristics of quality indicators to obtain an optimal spectrum to improve the modeling effect and detection results. In the current hyperspectral image modeling process, the number of samples is limited, the prediction ability of the model is not strong, the detection effect is poor, and the extracted characteristic wavelength is unstable, etc.

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
  • Hyperspectral image detection method for quality indexes of mutton
  • Hyperspectral image detection method for quality indexes of mutton
  • Hyperspectral image detection method for quality indexes of mutton

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] Example 1: A hyperspectral image detection method for mutton freshness grade

[0054] Part a: Building a hyperspectral image prediction model for mutton freshness grade

[0055] a1. Sample preparation

[0056] The experimental material is lamb carcass tenderloin, which was purchased from the farmers' market in Shihezi City. After peeling and removing the tendons, the meat samples were sliced ​​to obtain 60 small pieces of about 4 cm×4 cm×1.5 cm, weighing about 25 g. They were packed in sealed bags and stored in a constant temperature box at 4°C for 1 to 14 days. The distribution of freshness is fresh, second-fresh, and spoiled, which is representative.

[0057] a2. Line scan hyperspectral image acquisition

[0058] The line scan hyperspectral image acquisition system consists of an imaging spectrometer (ImSpector V10E, Finland), a linear array CCD camera (hamamastsu), a 150W fiber optic halogen white light source (SCHOTT DCR III, China), an electronically controlled ...

Embodiment 2

[0091] Example 2: A hyperspectral image detection method for volatile basic nitrogen in mutton

[0092] Part c: Establishing a hyperspectral image prediction model for mutton volatile base nitrogen

[0093] c1. Sample preparation

[0094] The mutton samples required for the experiment were taken from the back parts of 12 freshly slaughtered Suffolk sheep, which were purchased from the farmers' market in Shihezi City, Xinjiang. The meat was transported to the animal husbandry laboratory in a fresh-keeping box, the fat and connective tissue of the lamb back were removed, and cut into samples of about 40 mm×40 mm×20 mm, a total of 57 samples. Label the sample package and place it in a constant temperature refrigerator at 4°C for 2-14 days.

[0095] c2. Line scan hyperspectral image acquisition

[0096] The line-scanning hyperspectral imaging system mainly includes an imaging spectrometer (ImSpector V10E, Finland), a CMOS camera (MV-1024E, China), a light source (3900, Illumina...

Embodiment 3

[0127] Example 3: A hyperspectral image detection method for the proportion of adulterated fox meat in mutton

[0128] Part e: Establishing a hyperspectral image prediction model for the proportion of adulterated fox meat in mutton

[0129] e1. Sample preparation

[0130] The experimental materials used for adulteration detection of mutton include mutton and fox meat. Among them, the mutton was taken from the hind legs of sheep, and the fox meat was taken from three frozen fox meat samples. After the meat is transported to the laboratory, the fat and connective tissue are removed, cut into pieces and fully minced into minced meat. According to the actual adulteration ratio, the proportion is 5%, 10%, 15%, 20%, 25%, 30%, 35%, A total of 10 gradients of 40%, 45%, and 50% were mixed with fox meat and mixed in a watch glass to prepare samples. The mass of each sample was 20g, and a total of 80 adulterated mutton samples were prepared. Put the experimental samples into a vacuum ...

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 relates to a hyperspectral image detection method for the quality indexes of mutton, especially to a method for acquiring multiple preferred modeling spectra by making full use of hyperspectral image information so as to improve detection effect of the quality indexes of mutton. The method comprises a first step of establishing a prediction model for the hyperspectral image quality indexes of mutton and a second step of detecting the quality indexes of mutton by using the prediction model. According to the invention, a plurality of preferred spectra are selected for each sample by making full use of hyperspectral image information so as to establish the prediction model, so the a modeling sample amount can be scaled up by times, and the problem of a limited modeling sample amount caused by difficulty in measurement of the chemical values of samples is overcome; the modeling effect of the established model can be improved, and the calibration set and validation set of the model are higher in precision; characteristic wavelengths are extracted on the basis of selection of multiple preferred spectra, extraction results are stable and convergent and better modeling effect is obtained; the optimized prediction model is used for detection of the quality indexes, and detection performance can be improved; and the hyperspectral image detection method provided by the invention is of significance to improvement of the intelligent detection levels of mutton and other meat products and to guaranteeing of the quality safety of meat products.

Description

technical field [0001] The invention belongs to the technical field of hyperspectral image non-destructive testing of meat products, and in particular relates to a method for making full use of hyperspectral image information to optimally obtain multiple modeling spectra to improve the detection effect of mutton quality indicators. The method can be used to improve hyperspectral images of livestock products Qualitative and quantitative analysis of modeling effects and detection results. Background technique [0002] The hyperspectral image detection technology can simultaneously obtain the two-dimensional image information of a certain wavelength point of the beef and mutton sample and the spectral information of each point of the sample, which can realize the simultaneous detection of the internal and external quality of the beef and mutton sample, and is non-destructive, fast, pollution-free, In recent years, it has been rapidly developed and widely used in the detection o...

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 朱荣光范中建黄勇姚雪东邱园园阎聪孟令峰
Owner SHIHEZI UNIVERSITY
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