CN111929257A - Meat product freshness detection method based on spectral imaging technology - Google Patents

Meat product freshness detection method based on spectral imaging technology Download PDF

Info

Publication number
CN111929257A
CN111929257A CN202010895363.1A CN202010895363A CN111929257A CN 111929257 A CN111929257 A CN 111929257A CN 202010895363 A CN202010895363 A CN 202010895363A CN 111929257 A CN111929257 A CN 111929257A
Authority
CN
China
Prior art keywords
meat product
freshness
product sample
meat
image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202010895363.1A
Other languages
Chinese (zh)
Inventor
彭伟峰
熊子瑜
彭炜
谢茂兵
彭珍
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huaihua City Mingyou Food LLC
Original Assignee
Huaihua City Mingyou Food LLC
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Huaihua City Mingyou Food LLC filed Critical Huaihua City Mingyou Food LLC
Priority to CN202010895363.1A priority Critical patent/CN111929257A/en
Publication of CN111929257A publication Critical patent/CN111929257A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/12—Edge-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N2021/1734—Sequential different kinds of measurements; Combining two or more methods
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N2021/1765—Method using an image detector and processing of image signal
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10032—Satellite or aerial image; Remote sensing
    • G06T2207/10036—Multispectral image; Hyperspectral image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30128—Food products

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Biochemistry (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Quality & Reliability (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)

Abstract

The invention discloses a meat product freshness detection method based on a spectral imaging technology, which comprises the following steps of: refrigerating the meat product sample at 4 ℃ to obtain hyperspectral images under different preset storage times; detecting a freshness evaluation index corresponding to the meat product sample at each preset storage time; analyzing the hyperspectral image, and selecting spectral characteristics and image texture characteristics of the interested area of the meat product sample; constructing a network model of the freshness grade of the meat product to be detected according to the spectral characteristics and the image texture characteristics of the region of interest; according to the spectral characteristics and the image texture characteristics of the meat product to be detected, the freshness component content of the meat product to be detected is obtained by adopting network model inversion; the method can meet the requirement of quickly, accurately and stably detecting the freshness of the meat products.

Description

Meat product freshness detection method based on spectral imaging technology
Technical Field
The invention relates to the technical field of meat product freshness detection, in particular to a meat product freshness detection method based on a spectral imaging technology.
Background
Meat products refer to cooked meat products or semi-products prepared by taking livestock and poultry meat as a main raw material and seasoning, such as sausages, hams, bacon, sauced meat, barbecue and the like. That is, all the products of the meat which takes the livestock and poultry meat as the main raw material and is added with the seasoning are not different according to different processing technologies and are called meat products, including sausages, hams, bacon, sauced meat, barbecue, jerky, dried meat, meatballs, conditioned meat strings, meat cakes, cured meat, crystal meat and the like.
The meat product is rich in protein, fat and mineral substances, and is deeply favored by consumers due to the advantages of delicious taste, convenient eating and the like. The problems of deterioration degree of meat products during storage and authenticity of shelf life have been the focus of attention. The freshness is a direct reflection of the quality of meat and is one of the important measurement indexes of the quality of fresh meat and meat products. Therefore, the detection of the freshness of the meat products for clarifying the freshness evaluation standard and judging the storage period of the putrefaction and deterioration of the meat meets the increasing requirements of consumers on the quality of the meat products, and has important practical significance and application value for scientifically guiding the processing and storage processes of the meat products.
Meat spoilage is a complex changing process, and the degree and the characteristics of spoilage are closely related to the types of pollution microorganisms and the degradation effects thereof. The traditional method for detecting the freshness of the meat mainly comprises sensory evaluation, physicochemical index detection, microbial colony detection and the like. The sensory evaluation has strong subjectivity and is not easy to quantify, and the opinions of evaluators are difficult to be consistent; the problems of complex sample treatment, large consumption of chemical reagents, long detection period, high cost and the like exist in physicochemical indexes and microbial detection, and the requirements of rapid, accurate and stable detection on the freshness of meat products cannot be met.
Disclosure of Invention
The invention aims to provide a meat product freshness detection method based on a spectral imaging technology, which aims to solve the problems that the sensory evaluation subjectivity is strong, the quantification is difficult, and the opinions of evaluators are difficult to be consistent; the problems of complex sample treatment, large consumption of chemical reagents, long detection period, high cost and the like exist in physicochemical indexes and microbial detection, and the requirement of quickly, accurately and stably detecting the freshness of meat products cannot be met.
In order to achieve the purpose, the invention provides the following technical scheme: a method for detecting freshness of a meat product based on a spectral imaging technology comprises the following steps:
preparing a meat product sample, refrigerating at 4 ℃, and acquiring hyperspectral images of the meat product sample under different preset storage times;
detecting a freshness evaluation index corresponding to the meat product sample in each preset storage time;
analyzing the hyperspectral image of the obtained meat product sample, and selecting the spectral characteristics and image texture characteristics of the interested area of the meat product sample;
fourthly, a network model of the freshness grade of the meat product to be detected is constructed according to the freshness evaluation index of the meat product sample and the spectral characteristics and the image texture characteristics of the region of interest corresponding to the meat product sample;
and fifthly, obtaining the freshness component content of the meat product to be detected by adopting network model inversion according to the spectral characteristics and the image texture characteristics of the meat product to be detected.
Preferably, the number of days of different preset storage time in the step one is 0, 1, 2, 3, 4, 5, 6 and 7 days.
Preferably, in the first step, meat product samples with different storage days are scanned by using a spectral imaging technology, image information of the meat product samples under different wavelength conditions is obtained, and hyperspectral images of the meat product samples are obtained.
Preferably, the freshness evaluation index of the meat product sample in the second step is volatile basic nitrogen TVB-N of the meat product sample.
Preferably, the hyperspectral image of the meat product sample is subjected to size correction, masking, smoothing filtering and binarization processing in the third step, so that a gray level image of the meat product sample is obtained; processing the gray level image of the meat product sample by using edge image thresholding and local region watershed segmentation technologies, separating a background from the meat product image, determining a meat product region of interest, and extracting corresponding spectral features; and establishing a corresponding relation between the spectral characteristics of the meat product sample and the freshness index TVB-N of the meat product sample by using partial least squares regression, and determining characteristic wavelengths which can most reflect the freshness of the meat product sample to be 600nm, 615nm, 660nm, 720nm, 790nm, 840nm, 860nm and 950nm through a covariance regression coefficient and the optimal variable number.
Preferably, the step three of extracting the image texture features of the region of interest corresponding to the meat product sample includes: and extracting the image texture characteristics of the interested region corresponding to the meat product sample by utilizing a characteristic extraction algorithm combining a Local Binary Pattern (LBP) and a Tamura texture characteristic method.
Preferably, the network model in the fourth step is a particle swarm optimization neural network.
The invention has the beneficial effects that: the method adopted by the invention can meet the requirements of quickly, accurately and stably detecting the freshness of the meat products; theoretical support and guarantee are provided for improving the detection level and technology of meat products, and direct practical significance is provided for guaranteeing the quality safety of meat products and maintaining the health of consumers.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention.
The first embodiment is as follows:
the invention provides a meat product freshness detection method based on a spectral imaging technology, which comprises the following steps:
preparing a meat product sample, refrigerating at 4 ℃, and acquiring hyperspectral images of the meat product sample under different preset storage times;
detecting a freshness evaluation index corresponding to the meat product sample in each preset storage time;
analyzing the hyperspectral image of the obtained meat product sample, and selecting the spectral characteristics and image texture characteristics of the interested area of the meat product sample;
fourthly, a network model of the freshness grade of the meat product to be detected is constructed according to the freshness evaluation index of the meat product sample and the spectral characteristics and the image texture characteristics of the region of interest corresponding to the meat product sample;
and fifthly, obtaining the freshness component content of the meat product to be detected by adopting network model inversion according to the spectral characteristics and the image texture characteristics of the meat product to be detected.
The days of different preset storage time in the step one are 0, 1, 2, 3, 4, 5, 6 and 7 days.
In the first step, meat product samples with different storage days are scanned by using a spectral imaging technology, image information of the meat product samples under different wavelength conditions is obtained, and hyperspectral images of the meat product samples are obtained.
And the freshness evaluation index of the meat product sample in the second step is volatile basic nitrogen TVB-N of the meat product sample.
Thirdly, performing size correction, masking, smoothing filtering and binarization processing on the hyperspectral image of the meat product sample to obtain a gray level image of the meat product sample; processing the gray level image of the meat product sample by using edge image thresholding and local region watershed segmentation technologies, separating a background from the meat product image, determining a meat product region of interest, and extracting corresponding spectral features; and establishing a corresponding relation between the spectral characteristics of the meat product sample and the freshness index TVB-N of the meat product sample by using partial least squares regression, and determining characteristic wavelengths which can most reflect the freshness of the meat product sample to be 600nm, 615nm, 660nm, 720nm, 790nm, 840nm, 860nm and 950nm through a covariance regression coefficient and the optimal variable number.
Extracting image texture features of the region of interest corresponding to the meat product sample in the third step, including: and extracting the image texture characteristics of the interested region corresponding to the meat product sample by utilizing a characteristic extraction algorithm combining a Local Binary Pattern (LBP) and a Tamura texture characteristic method.
And the network model in the fourth step is a particle swarm optimization neural network.
And the freshness evaluation index of the meat product sample in the second step is volatile basic nitrogen TVB-N of the meat product sample. TVB-N means that in the putrefaction process of animal food, protein is decomposed to generate alkaline nitrogen-containing substances such as ammonia and amines due to the action of enzyme and bacteria, and the substances have volatility, and the higher the content of the substances, the more amino acids are destroyed, particularly methionine and tyrosine, so that the animal food has high nutritional value
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.

Claims (7)

1. A meat product freshness detection method based on a spectral imaging technology is characterized by comprising the following steps: the method for detecting freshness of the meat product comprises the following steps:
preparing a meat product sample, refrigerating at 4 ℃, and acquiring hyperspectral images of the meat product sample under different preset storage times;
detecting a freshness evaluation index corresponding to the meat product sample in each preset storage time;
analyzing the hyperspectral image of the obtained meat product sample, and selecting the spectral characteristics and image texture characteristics of the interested area of the meat product sample;
fourthly, a network model of the freshness grade of the meat product to be detected is constructed according to the freshness evaluation index of the meat product sample and the spectral characteristics and the image texture characteristics of the region of interest corresponding to the meat product sample;
and fifthly, obtaining the freshness component content of the meat product to be detected by adopting network model inversion according to the spectral characteristics and the image texture characteristics of the meat product to be detected.
2. The method for detecting freshness of meat products based on spectral imaging technology of claim 1, wherein: the days of different preset storage time in the step one are 0, 1, 2, 3, 4, 5, 6 and 7 days.
3. The method for detecting freshness of meat products based on spectral imaging technology of claim 1, wherein: in the first step, meat product samples with different storage days are scanned by using a spectral imaging technology, image information of the meat product samples under different wavelength conditions is obtained, and hyperspectral images of the meat product samples are obtained.
4. The method for detecting freshness of meat products based on spectral imaging technology of claim 1, wherein: and the freshness evaluation index of the meat product sample in the second step is volatile basic nitrogen TVB-N of the meat product sample.
5. The method for detecting freshness of meat products based on spectral imaging technology of claim 1, wherein: thirdly, performing size correction, masking, smoothing filtering and binarization processing on the hyperspectral image of the meat product sample to obtain a gray level image of the meat product sample; processing the gray level image of the meat product sample by using edge image thresholding and local region watershed segmentation technologies, separating a background from the meat product image, determining a meat product region of interest, and extracting corresponding spectral features; and establishing a corresponding relation between the spectral characteristics of the meat product sample and the freshness index TVB-N of the meat product sample by using partial least squares regression, and determining characteristic wavelengths which can most reflect the freshness of the meat product sample to be 600nm, 615nm, 660nm, 720nm, 790nm, 840nm, 860nm and 950nm through a covariance regression coefficient and the optimal variable number.
6. The method for detecting freshness of meat products based on spectral imaging technology of claim 1, wherein: extracting image texture features of the region of interest corresponding to the meat product sample in the third step, including: and extracting the image texture characteristics of the interested region corresponding to the meat product sample by utilizing a characteristic extraction algorithm combining a Local Binary Pattern (LBP) and a Tamura texture characteristic method.
7. The method for detecting freshness of meat products based on spectral imaging technology of claim 1, wherein: and the network model in the fourth step is a particle swarm optimization neural network.
CN202010895363.1A 2020-08-31 2020-08-31 Meat product freshness detection method based on spectral imaging technology Pending CN111929257A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010895363.1A CN111929257A (en) 2020-08-31 2020-08-31 Meat product freshness detection method based on spectral imaging technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010895363.1A CN111929257A (en) 2020-08-31 2020-08-31 Meat product freshness detection method based on spectral imaging technology

Publications (1)

Publication Number Publication Date
CN111929257A true CN111929257A (en) 2020-11-13

Family

ID=73309757

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010895363.1A Pending CN111929257A (en) 2020-08-31 2020-08-31 Meat product freshness detection method based on spectral imaging technology

Country Status (1)

Country Link
CN (1) CN111929257A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113588571A (en) * 2021-09-29 2021-11-02 广东省农业科学院动物科学研究所 Hyperspectral imaging-based method and system for identifying fishy smell of aquatic product

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103439285A (en) * 2013-08-19 2013-12-11 华南理工大学 Fish fillet freshness detection method based on hyperspectral imaging
CN105548029A (en) * 2015-12-14 2016-05-04 北京农业质量标准与检测技术研究中心 Meat product freshness detection method based on spectral imaging technology

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103439285A (en) * 2013-08-19 2013-12-11 华南理工大学 Fish fillet freshness detection method based on hyperspectral imaging
CN105548029A (en) * 2015-12-14 2016-05-04 北京农业质量标准与检测技术研究中心 Meat product freshness detection method based on spectral imaging technology

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113588571A (en) * 2021-09-29 2021-11-02 广东省农业科学院动物科学研究所 Hyperspectral imaging-based method and system for identifying fishy smell of aquatic product
CN113588571B (en) * 2021-09-29 2021-12-03 广东省农业科学院动物科学研究所 Hyperspectral imaging-based method and system for identifying fishy smell of aquatic product

Similar Documents

Publication Publication Date Title
Liu et al. Hyperspectral imaging technique for evaluating food quality and safety during various processes: A review of recent applications
Ma et al. Applications of computer vision for assessing quality of agri-food products: a review of recent research advances
Özdoğan et al. Rapid and noninvasive sensory analyses of food products by hyperspectral imaging: Recent application developments
Siche et al. Evaluation of food quality and safety with hyperspectral imaging (HSI)
Hassoun et al. Quality evaluation of fish and other seafood by traditional and nondestructive instrumental methods: Advantages and limitations
Khulal et al. Intelligent evaluation of total volatile basic nitrogen (TVB-N) content in chicken meat by an improved multiple level data fusion model
ElMasry et al. Meat quality evaluation by hyperspectral imaging technique: an overview
Jia et al. Prediction of pH of fresh chicken breast fillets by VNIR hyperspectral imaging
Du et al. Recent developments in the applications of image processing techniques for food quality evaluation
Liu et al. NIR spectroscopy and imaging techniques for evaluation of fish quality—a review
Cheng et al. Hyperspectral imaging as an effective tool for quality analysis and control of fish and other seafoods: Current research and potential applications
CN103439285B (en) A kind of fillet Noninvasive Measuring Method of Freshness based on high light spectrum image-forming
Konda Naganathan et al. Partial least squares analysis of near-infrared hyperspectral images for beef tenderness prediction
Peng et al. Optical methods and techniques for meat quality inspection
Su et al. Development of near infrared reflectance spectroscopy to predict chemical composition with a wide range of variability in beef
CN106769894A (en) Salt distribution detection method in a kind of bacon curing process based on high light spectrum image-forming
Falkovskaya et al. Literature review: Spectral imaging applied to poultry products
Ghasemi-Varnamkhasti et al. Application of image analysis combined with computational expert approaches for shrimp freshness evaluation
Modzelewska-Kapituła et al. The application of computer vision systems in meat science and industry–A review
CN109856079B (en) Method for rapidly and nondestructively evaluating fat oxidation degree of fish meat through near-infrared multispectral imaging
Yang et al. Detection of the freshness state of cooked beef during storage using hyperspectral imaging
Rady et al. Feasibility of utilizing color imaging and machine learning for adulteration detection in minced meat
CN111929257A (en) Meat product freshness detection method based on spectral imaging technology
CN104089925A (en) Hyperspectral imaging-based Target area extraction method for detecting shrimp quality
Kamruzzaman Optical sensing as analytical tools for meat tenderness measurements-A review

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20201113