CN115561233B - Method for visually and intelligently detecting freshness of meat based on hydrogel material - Google Patents
Method for visually and intelligently detecting freshness of meat based on hydrogel material Download PDFInfo
- Publication number
- CN115561233B CN115561233B CN202211141185.9A CN202211141185A CN115561233B CN 115561233 B CN115561233 B CN 115561233B CN 202211141185 A CN202211141185 A CN 202211141185A CN 115561233 B CN115561233 B CN 115561233B
- Authority
- CN
- China
- Prior art keywords
- bromocresol green
- gelatin
- bcg
- hydrogel
- freshness
- 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.)
- Active
Links
- 239000000017 hydrogel Substances 0.000 title claims abstract description 70
- 235000013372 meat Nutrition 0.000 title claims abstract description 69
- 238000000034 method Methods 0.000 title claims abstract description 21
- 239000000463 material Substances 0.000 title abstract description 8
- FRPHFZCDPYBUAU-UHFFFAOYSA-N Bromocresolgreen Chemical compound CC1=C(Br)C(O)=C(Br)C=C1C1(C=2C(=C(Br)C(O)=C(Br)C=2)C)C2=CC=CC=C2S(=O)(=O)O1 FRPHFZCDPYBUAU-UHFFFAOYSA-N 0.000 claims abstract description 103
- 108010010803 Gelatin Proteins 0.000 claims abstract description 89
- 239000008273 gelatin Substances 0.000 claims abstract description 89
- 229920000159 gelatin Polymers 0.000 claims abstract description 89
- 235000019322 gelatine Nutrition 0.000 claims abstract description 89
- 235000011852 gelatine desserts Nutrition 0.000 claims abstract description 89
- 238000001514 detection method Methods 0.000 claims abstract description 28
- 238000006467 substitution reaction Methods 0.000 claims abstract description 6
- 241000251468 Actinopterygii Species 0.000 claims description 32
- 239000000243 solution Substances 0.000 claims description 30
- 238000002360 preparation method Methods 0.000 claims description 13
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 13
- DCUFMVPCXCSVNP-UHFFFAOYSA-N methacrylic anhydride Chemical compound CC(=C)C(=O)OC(=O)C(C)=C DCUFMVPCXCSVNP-UHFFFAOYSA-N 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 239000003086 colorant Substances 0.000 claims description 7
- 238000013136 deep learning model Methods 0.000 claims description 7
- 238000000502 dialysis Methods 0.000 claims description 7
- 238000002156 mixing Methods 0.000 claims description 7
- 238000001035 drying Methods 0.000 claims description 5
- 238000010438 heat treatment Methods 0.000 claims description 5
- 230000001678 irradiating effect Effects 0.000 claims description 5
- 239000008055 phosphate buffer solution Substances 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 239000002253 acid Substances 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 abstract description 10
- 238000013135 deep learning Methods 0.000 abstract description 6
- 235000013305 food Nutrition 0.000 abstract description 6
- 230000000007 visual effect Effects 0.000 abstract description 3
- 125000005395 methacrylic acid group Chemical group 0.000 abstract description 2
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 description 29
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 20
- 229910021529 ammonia Inorganic materials 0.000 description 14
- 230000008859 change Effects 0.000 description 12
- VEXZGXHMUGYJMC-UHFFFAOYSA-N Hydrochloric acid Chemical compound Cl VEXZGXHMUGYJMC-UHFFFAOYSA-N 0.000 description 10
- 229910052757 nitrogen Inorganic materials 0.000 description 10
- 239000008367 deionised water Substances 0.000 description 7
- 229910021641 deionized water Inorganic materials 0.000 description 7
- 239000000499 gel Substances 0.000 description 7
- 239000000843 powder Substances 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 235000013622 meat product Nutrition 0.000 description 5
- 239000000203 mixture Substances 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000004108 freeze drying Methods 0.000 description 3
- 230000000977 initiatory effect Effects 0.000 description 3
- 239000002243 precursor Substances 0.000 description 3
- 229910052710 silicon Inorganic materials 0.000 description 3
- 239000010703 silicon Substances 0.000 description 3
- -1 silicon alkoxide Chemical class 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- MKNQNPYGAQGARI-UHFFFAOYSA-N 4-(bromomethyl)phenol Chemical compound OC1=CC=C(CBr)C=C1 MKNQNPYGAQGARI-UHFFFAOYSA-N 0.000 description 2
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 description 2
- BOTDANWDWHJENH-UHFFFAOYSA-N Tetraethyl orthosilicate Chemical compound CCO[Si](OCC)(OCC)OCC BOTDANWDWHJENH-UHFFFAOYSA-N 0.000 description 2
- 230000004913 activation Effects 0.000 description 2
- 239000002390 adhesive tape Substances 0.000 description 2
- 230000000052 comparative effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000003550 marker Substances 0.000 description 2
- 125000002496 methyl group Chemical group [H]C([H])([H])* 0.000 description 2
- 239000003755 preservative agent Substances 0.000 description 2
- 230000002335 preservative effect Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- CPUDPFPXCZDNGI-UHFFFAOYSA-N triethoxy(methyl)silane Chemical compound CCO[Si](C)(OCC)OCC CPUDPFPXCZDNGI-UHFFFAOYSA-N 0.000 description 2
- GJKGAPPUXSSCFI-UHFFFAOYSA-N 2-Hydroxy-4'-(2-hydroxyethoxy)-2-methylpropiophenone Chemical compound CC(C)(O)C(=O)C1=CC=C(OCCO)C=C1 GJKGAPPUXSSCFI-UHFFFAOYSA-N 0.000 description 1
- 241000272525 Anas platyrhynchos Species 0.000 description 1
- 241000287828 Gallus gallus Species 0.000 description 1
- 239000002696 acid base indicator Substances 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 239000003054 catalyst Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011109 contamination Methods 0.000 description 1
- 238000013401 experimental design Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 230000000813 microbial effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 231100000614 poison Toxicity 0.000 description 1
- XOFYZVNMUHMLCC-ZPOLXVRWSA-N prednisone Chemical compound O=C1C=C[C@]2(C)[C@H]3C(=O)C[C@](C)([C@@](CC4)(O)C(=O)CO)[C@@H]4[C@@H]3CCC2=C1 XOFYZVNMUHMLCC-ZPOLXVRWSA-N 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 235000014102 seafood Nutrition 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
- 238000003756 stirring Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
- 239000003440 toxic substance Substances 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
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
- G01N21/75—Systems in which material is subjected to a chemical reaction, the progress or the result of the reaction being investigated
- G01N21/77—Systems in which material is subjected to a chemical reaction, the progress or the result of the reaction being investigated by observing the effect on a chemical indicator
- G01N21/78—Systems in which material is subjected to a chemical reaction, the progress or the result of the reaction being investigated by observing the effect on a chemical indicator producing a change of colour
-
- C—CHEMISTRY; METALLURGY
- C08—ORGANIC MACROMOLECULAR COMPOUNDS; THEIR PREPARATION OR CHEMICAL WORKING-UP; COMPOSITIONS BASED THEREON
- C08F—MACROMOLECULAR COMPOUNDS OBTAINED BY REACTIONS ONLY INVOLVING CARBON-TO-CARBON UNSATURATED BONDS
- C08F220/00—Copolymers of compounds having one or more unsaturated aliphatic radicals, each having only one carbon-to-carbon double bond, and only one being terminated by only one carboxyl radical or a salt, anhydride ester, amide, imide or nitrile thereof
- C08F220/02—Monocarboxylic acids having less than ten carbon atoms; Derivatives thereof
- C08F220/04—Acids; Metal salts or ammonium salts thereof
- C08F220/06—Acrylic acid; Methacrylic acid; Metal salts or ammonium salts thereof
-
- C—CHEMISTRY; METALLURGY
- C08—ORGANIC MACROMOLECULAR COMPOUNDS; THEIR PREPARATION OR CHEMICAL WORKING-UP; COMPOSITIONS BASED THEREON
- C08J—WORKING-UP; GENERAL PROCESSES OF COMPOUNDING; AFTER-TREATMENT NOT COVERED BY SUBCLASSES C08B, C08C, C08F, C08G or C08H
- C08J3/00—Processes of treating or compounding macromolecular substances
- C08J3/02—Making solutions, dispersions, lattices or gels by other methods than by solution, emulsion or suspension polymerisation techniques
- C08J3/03—Making solutions, dispersions, lattices or gels by other methods than by solution, emulsion or suspension polymerisation techniques in aqueous media
- C08J3/075—Macromolecular gels
-
- 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
- G01N21/75—Systems in which material is subjected to a chemical reaction, the progress or the result of the reaction being investigated
- G01N21/77—Systems in which material is subjected to a chemical reaction, the progress or the result of the reaction being investigated by observing the effect on a chemical indicator
- G01N21/78—Systems in which material is subjected to a chemical reaction, the progress or the result of the reaction being investigated by observing the effect on a chemical indicator producing a change of colour
- G01N21/783—Systems in which material is subjected to a chemical reaction, the progress or the result of the reaction being investigated by observing the effect on a chemical indicator producing a change of colour for analysing gases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- 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
- G01N2021/8411—Application to online plant, process monitoring
Landscapes
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Dispersion Chemistry (AREA)
- Analytical Chemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Medicinal Chemistry (AREA)
- Polymers & Plastics (AREA)
- Organic Chemistry (AREA)
- Evolutionary Computation (AREA)
- Multimedia (AREA)
- Plasma & Fusion (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Biochemistry (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Investigating Or Analyzing Non-Biological Materials By The Use Of Chemical Means (AREA)
Abstract
The invention discloses a method for visually and intelligently detecting freshness of meat based on a hydrogel material, and belongs to the technical field of food detection. The method comprises the following steps: preparing methacrylic gelatin GelMA hydrogel with high substitution degree; taking the GelMA hydrogel as a bromocresol green carrier, embedding bromocresol green BCG to prepare a visual film as an indication label; the obtained indication tag and meat food to be detected are placed in the same closed space, after standing, an image of the indication tag is obtained by photographing through a smart phone, deep learning of a deep convolutional neural network CNN is utilized, a VGG 16 algorithm and a watershed algorithm of the CNN are integrated into a mobile phone APP, and a consumer can identify meat freshness within 30 seconds by scanning the indication tag through the mobile phone APP. The method can realize sensitive, automatic and nondestructive detection of the freshness of the meat, has low detection cost and is simple and convenient to operate.
Description
Technical Field
The invention relates to a method for visually and intelligently detecting freshness of meat based on a hydrogel material, and belongs to the technical field of food detection.
Background
The meat food has rich nutrient substances and is popular with consumers. However, during the production and sales of meat products, they are extremely susceptible to microbial contamination and spoilage. The spoiled meat not only damages the nutritional ingredients of the meat, but also has the possibility of generating toxic substances, thus endangering the health and even the life of consumers. Therefore, it is important to develop a new method for detecting the freshness of meat products.
Bromocresol green (bromocresol green, BCG) is an acid-base indicator that has great potential in the application of food detection indicator tags, but low concentrations of bromocresol green often do not accurately indicate meat freshness. Therefore, a high-efficiency embedding carrier is needed to embed high-concentration bromocresol green, so that the bromocresol green accurately and efficiently indicates the freshness of meat.
Disclosure of Invention
[ Technical problem ]
The existing meat freshness detection mode is time-consuming and labor-consuming, and cannot realize real-time, nondestructive and accurate detection when facing a large number of detection samples.
Meanwhile, because individual differences among people and other subjective or objective reasons are insensitive to color change of the labels and are easy to cause errors, the color change of the indication labels is combined with a neural network, and a method for constructing a smart phone platform for detecting fish freshness by using a deep learning model of the indication labels combined with the neural network prepared by using methacrylic gelatin (GELATIN METHACRYLATED, gelMA) hydrogel is developed, so that the fish freshness can be better detected.
Technical scheme
The invention provides a method for visually and intelligently detecting meat freshness based on a hydrogel material and an intelligent detection system APP. The method has the advantages that the hydrogel (GelMA-BCG) of the bromocresol green embedded by the methylated gelatin can cause the color reaction of the indication tag by utilizing the volatile basic nitrogen released by meats with different freshness, the color change of the indication tag is combined with the deep learning model of the neural network, and a smart phone platform is constructed, so that the rapid, accurate, real-time and nondestructive detection of the freshness of the meats is realized, and the detection cost is low and the operation is simple and convenient.
Specifically, the invention provides a method for visually and intelligently detecting the freshness of meat based on a hydrogel material, which utilizes volatile basic nitrogen released by meats with different freshness to enable a hydrogel indication tag (GelMA-BCG) of methylated gelatin embedded bromocresol green to generate a color reaction, so as to realize the visual detection of the freshness of the meats.
A methylated gelatin-embedded bromocresol green hydrogel (GelMA-BCG) indicator tag for visually and intelligently detecting meat freshness, the preparation method comprising the steps of:
S1, dissolving gelatin in a phosphate buffer solution, and heating to dissolve to obtain a gelatin solution; adding methacrylic anhydride into gelatin solution, uniformly mixing and reacting, transferring to a dialysis bag for dialysis after finishing reaction, and then drying to obtain methylated gelatin (GelMA);
s2, adding bromocresol green (BCG) and a photoinitiator into water, and uniformly mixing to obtain a BCG solution; adding the methylated gelatin (GelMA) obtained in the step S1 into a BCG solution, dissolving and mixing uniformly, and irradiating with an ultraviolet lamp to initiate a reaction, thus obtaining the methylated gelatin hydrogel (GelMA-BCG) embedded with bromocresol green after the reaction is finished;
S3, adjusting the pH value of the bromocresol green embedded methylated gelatin hydrogel (GelMA-BCG) obtained in the S2 to 3-5 by using acid, then dripping the bromocresol green embedded methylated gelatin hydrogel (GelMA-BCG) onto filter paper until the bromocresol green embedded methylated gelatin hydrogel is completely immersed, irradiating by using an ultraviolet lamp, and drying to obtain the bromocresol green embedded methylated gelatin hydrogel (GelMA-BCG) indication label.
In one embodiment of the invention, the meats include chicken, duck, fish, and various seafood meats.
In one embodiment of the invention, the methylated gelatin is methacrylic anhydride modified gelatin having a degree of substitution of 90.9%.
In one embodiment of the invention, in S1, the concentration of the gelatin solution is 5-20wt%; and particularly 10 wt percent.
In one embodiment of the invention, in S1, the volume fraction of methacrylic anhydride relative to the gelatin solution is 0.1% -2% (v/v); specifically, 0.8% (v/v) is optional.
In one embodiment of the invention, in S2, the mass ratio of bromocresol green to methylated gelatin is 1:80.
In one embodiment of the invention, in S2, the concentration of photoinitiator in the BCG solution is 0.3-0.8 wt%; specifically, 0.5 wt% is selected.
In one embodiment of the invention, in S2, the photoinitiation is Irgacure 2959.
In one embodiment of the present invention, in S2, the concentration of bromocresol green in the BCG solution is from 0.05mg/mL to 2mg/mL; specifically, the concentration of the catalyst is 0.8 mg/mL.
In one embodiment of the present invention, in S2, an ultraviolet lamp of 365 nm is used for irradiation of the ultraviolet lamp.
In one embodiment of the invention, in S2, the reaction time is 20-60min; and particularly optionally 30min.
In one embodiment of the invention, in S3, the pH is specifically adjustable to 3.5.
In one embodiment of the present invention, in S3, the ultraviolet lamp irradiation is performed for 30 minutes using an ultraviolet lamp of 365 nm.
In one embodiment of the invention, in S3, the acid is hydrochloric acid.
In one embodiment of the present invention, in S3, the filter paper has a size of 2 mm by 3mm.
In one embodiment of the present invention, the preparation step of the methylated gelatin-embedded bromocresol green hydrogel (GelMA-BCG) indicator tag comprises the steps of:
S1, preparation of methylated gelatin (GelMA): dissolving gelatin in phosphate buffer solution with pH=7.5, heating in water bath at 50 ℃, slowly dripping methacrylic anhydride solution into gelatin solution, reacting 1 h, transferring into dialysis bag (MWCO 8000-14000), dialyzing in deionized water at 40 ℃ for 2 days, and freeze drying to obtain methylated gelatin (GelMA) powder with substitution degree of 90.9%;
S2, preparing bromocresol green embedded methylated gelatin hydrogel (GelMA-BCG): bromocresol green (BCG) was dissolved in deionized water containing 0.5% photoinitiator to obtain BCG solution. Dissolving the methylated gelatin (GelMA) powder prepared in the step S1 in bromocresol green (BCG) solution, and initiating 30min by using a 365 nm ultraviolet lamp to obtain bromocresol green embedded methylated gelatin hydrogel (GelMA-BCG);
S3, preparation of a bromocresol green embedded methylated gelatin hydrogel (GelMA-BCG) indication label: the pH of the bromocresol green embedded methylated gelatin hydrogel (GelMA-BCG) prepared in S2 is adjusted to 3.5 by hydrochloric acid, and then the bromocresol green embedded methylated gelatin hydrogel (GelMA-BCG) is dripped on filter paper until the bromocresol green embedded methylated gelatin hydrogel is completely immersed, 30min is irradiated by a 365 nm ultraviolet lamp, and the bromocresol green embedded methylated gelatin hydrogel (GelMA-BCG) indication label is obtained after the bromocresol green embedded methylated gelatin hydrogel is transferred to an oven until the bromocresol green embedded methylated gelatin hydrogel is completely dried.
The invention also provides application of the bromocresol green embedded methylated gelatin hydrogel (GelMA-BCG) indication tag in detecting fish freshness.
In one embodiment of the invention, a bromocresol green embedded methylated gelatin hydrogel (GelMA-BCG) indicates that the tag is capable of color response to varying concentrations of ammonia in the environment. As the concentration of ammonia increases, the color difference value Δe increases; i.e. the indicator tag may be responsive to volatile ammonia for detecting freshness of meat quality.
The invention also provides a detection system APP based on the hydrogel material visualization intelligent detection of the meat freshness, which is used for extracting a large number of characteristic structures of tags with different meat freshness colors through a deep learning model, and detecting the meat freshness by scanning the tag colors of the meat to be detected through a mobile phone after the training model is continuously iterated.
In one embodiment of the invention, the indication tag and the meat food to be detected are placed in the same closed space, an image of the indication tag is obtained by photographing through a smart phone after standing, a VGG 16 algorithm and a watershed algorithm of a deep convolutional neural network (convolutional neural network, CNN) are integrated into a mobile phone APP by deep learning of the CNN, and a consumer can identify the freshness of meat quality within 30 s by scanning the indication tag through the mobile phone APP.
In one embodiment of the present invention, the detection system APP comprises the following implementation steps:
S1, data acquisition: after the label color acquisition is performed on meat samples with different freshness by the method described in the above embodiment, each image of the color label is matched with its potential category according to the training factor, and the features are collected for classification. The acquired images are classified into three categories according to the volatile nitrogen value: fresh (< 15 mg/100 g refers to volatile basic nitrogen, equivalent to <150 ppm ammonia), less fresh (15-30 mg/100 g refers to volatile basic nitrogen, equivalent to 150-300 ppm ammonia) and spoilage (> 30 mg/100 g refers to volatile basic nitrogen, equivalent to >300 ppm ammonia);
s2, label scanning and developing: according to the characteristics of the experimental image in S1, a color label is segmented from the whole image by using a watershed algorithm based on a mark in an Open CV library;
S3, establishing a deep learning model: designing a three-class image classification network with VGG-16, including input, convolution, full Connection (FC) and output layers, using a rectifying linear unit (ReLU) function as an activation function for each convolution layer;
S4, APP development: the color indicator tag is combined with a marker-based watershed algorithm for image segmentation and the VGG 16 algorithm for deep learning is integrated therewith to form a mobile application to provide automatic recognition of freshness.
The detection system can be a smart phone APP, and the specific detection method comprises the following steps: in the production and sales process of meat products, the methylated gelatin embedded bromocresol green hydrogel (GelMA-BCG)) indication tag and meat are packaged, transported and stored together, and the color change of the indication tag is scanned by a smart phone APP in the process so as to accurately, quickly reflect the freshness of the meat in real time.
The invention has the remarkable advantages that:
The bromocresol green embedded methylated gelatin hydrogel (GelMA-BCG) indication label can respond to the change of ammonia concentration in the environment in color, and can be used for detecting the freshness of meat quality. After storage for various times, the bromocresol green embedded methylated gelatin hydrogel (GelMA-BCG) indicated that the tag displayed different colors as a function of fish freshness.
According to the invention, the high-substitution GelMA hydrogel is adopted to realize the maximum concentration embedding of the bromocresol green, so that the indication label sensitive to the TVB-N content is constructed, and the indication label is combined with the deep learning smart phone APP, so that the error analysis of naked eyes on the indication label caused by subjective or objective reasons is reduced, the accuracy of the indication label is improved, expensive instruments are not needed, the operation is simple, and the accurate, real-time and rapid detection of the freshness of meat products can be realized.
Drawings
FIG. 1 is a graph of the color response of a methylated gelatin hydrogel (GelMA-BCG) embedded with bromocresol green to ammonia;
FIG. 2 is a graph of a methylated gelatin hydrogel embedded with bromocresol green (GelMA-BCG) indicating the change in label with fish freshness;
FIG. 3 is a deep learning experimental design and composition of convolutional neural network (Convolutional Neural Network, CNN);
FIG. 4 is an operational flow of a smart phone APP;
FIG. 5 is a graph showing changes in bromocresol green sol-gel type fish freshness indicator card with fish meat freshness at various times; wherein (a) is 0h; (b) 18h; (c) 22h; (d) 24h.
Detailed Description
The present invention is further described below with reference to examples, but embodiments of the present invention are not limited thereto.
The gelatin manufacturers described in the examples below are microphone, CAS numbers 9000-70-8, unless otherwise specified; methacrylic anhydride manufacturer is microphone with CAS number 760-93-0; bromocresol green manufacturer is microphone, CAS number 76-60-8.
Example 1
The preparation steps of the methylated gelatin-embedded bromocresol green hydrogel (GelMA-BCG) indicator tag comprise the following steps:
S1, preparation of methylated gelatin (GelMA): dissolving gelatin in phosphate buffer solution with pH=7.5 to form gelatin solution of 10% (w/v), heating in water bath at 50 ℃, slowly dripping methacrylic anhydride to volume fraction of methacrylic anhydride of 0.8% (v/v) into the gelatin solution, reacting for 1h, transferring into dialysis bag (MWCO 8000-14000), dialyzing in deionized water of 40 ℃ for 2 days, and freeze drying to obtain methylated gelatin (GelMA) powder with substitution degree of 90.9%;
s2, preparing bromocresol green embedded methylated gelatin hydrogel (GelMA-BCG): bromocresol green (BCG) was dissolved in deionized water containing 0.5% photoinitiator to give a 0.8 mg/ml BCG solution. Dissolving the methylated gelatin (GelMA) powder prepared in the step S1 in bromocresol green (BCG) solution, and initiating 30min by using a 365 nm ultraviolet lamp to obtain bromocresol green-embedded methylated gelatin hydrogel (GelMA-BCG) (the mass ratio of bromocresol green to GelMA is 1:80);
S3, preparation of a bromocresol green embedded methylated gelatin hydrogel (GelMA-BCG) indication label: the bromocresol green embedded methylated gelatin hydrogel (GelMA-BCG) prepared in S2 is adjusted to 3.5 pH by hydrochloric acid, then is dripped on 2mm x 3mm filter paper until the bromocresol green embedded methylated gelatin hydrogel is completely immersed, is irradiated by 365 nm ultraviolet lamp for 30 min, and is transferred to an oven until the bromocresol green embedded methylated gelatin hydrogel (GelMA-BCG) indication label is completely dried.
Detection of fish freshness using bromocresol green embedded methylated gelatin hydrogel (GelMA-BCG) indicator tag:
40g of fish meat is placed in a culture dish of 90 mm, a methyl gelatin hydrogel (GelMA-BCG) indicating label embedded with bromocresol green is stuck on the inner side of a culture dish cover by using an adhesive tape, the culture dish is covered, the culture dish is sealed, and the culture dish is placed in a refrigerator at 4 ℃. As shown in fig. 1, bromocresol green embedded methylated gelatin hydrogels (GelMA-BCG) indicated that the tag was able to respond color to ammonia gas at different concentrations in the environment. As the concentration of ammonia increases, the color difference value DeltaE increases, so that the prepared indicator label can respond to the volatilized ammonia and is used for detecting the freshness of meat quality. Fresh (< 15 mg/100 g refers to volatile basic nitrogen, corresponding to <150 ppm ammonia), less fresh (15-30 mg/100 g refers to volatile basic nitrogen, corresponding to 150-300 ppm ammonia) and spoilage (> 30 mg/100 g refers to volatile basic nitrogen, corresponding to >300 ppm ammonia).
As shown in fig. 2, after storage for various times, the methylated gelatin hydrogel (GelMA-BCG) embedded with bromocresol green indicates that the tag shows various colors according to the change of freshness of fish meat, yellow indicates that the fish meat is fresh, green indicates that the fish meat is fresher, and blue indicates that the fish meat has deteriorated.
Comparative example 1 comparison of existing method for detecting freshness of fish meat based on bromocresol green
The preparation method of the bromocresol green sol-gel type fish freshness indicator comprises the following steps:
S1, preparation of a silicon alkoxide precursor mixture: uniformly mixing 1.206 mL tetraethyl silicate (TEOS) and 1.259 mL Methyltriethoxysilane (MTEOS);
s2, adding 20 mg bromocresol green into 3.676 mL ethanol and 0.85 mL hydrochloric acid solution (0.1 mol/L) to completely dissolve the bromocresol green, dropwise adding the silicon alkoxide precursor mixture prepared in the step S1 into the solution, magnetically stirring for 1h, and adding deionized water and the silicon alkoxide precursor mixture (the molar ratio is 4:1) to obtain a sol-gel solution.
S3, taking filter paper as an indicator substrate, standing in the sol-gel solution in the S2 for overnight, and then drying at room temperature to obtain the bromocresol green sol-gel type fish freshness indicator.
Detecting the freshness of fish meat by using bromocresol green sol-gel type fish freshness indicator card:
the testing process comprises the following steps: placing 40g of fish in a culture dish with a size of 90 mm, attaching a freshness indicator card to a preservative film, covering the culture dish with the preservative film, enabling the freshness indicator card to be positioned at a sample headspace, observing the color change of the indicator card, photographing, processing the photo into RGB values by Image J Image processing software, and converting the RGB values into H values according to an HSV (hue saturation value) color model.
Test results: as shown in fig. 5, the bromocresol green sol-gel type fish freshness indicator card shows different colors according to the change of the fish meat freshness, yellow indicates that the fish meat is fresh, green and blue indicate that the fish meat is fresher, and deep blue indicates that the fish meat has degenerated. From fig. 5 it can be seen that the distinction between green, blue and deep blue is not obvious, and that the next fresh and spoiled meat cannot be distinguished accurately and quickly by the H value.
Comparative example 2 detection of tags obtained with different mass ratios of bromocresol green to GelMA
The preparation steps of the methylated gelatin-embedded bromocresol green hydrogel (GelMA-BCG) indicator tag comprise the following steps:
S1, preparation of methylated gelatin (GelMA): dissolving gelatin in phosphate buffer solution with pH=7.5 to form 10% (w/v) gelatin water solution, heating in water bath at 50deg.C, slowly dripping methacrylic anhydride solution to 0.8% (v/v) gelatin solution, reacting for 1h, transferring into dialysis bag (MWCO 8000-14000), dialyzing in deionized water at 40deg.C for 2 days, and freeze drying to obtain methylated gelatin (GelMA) powder;
s2, preparing bromocresol green embedded methylated gelatin hydrogel (GelMA-BCG): bromocresol green (BCG) was dissolved in deionized water containing 0.5% photoinitiator to give a 0.8% (v/v) BCG solution. Dissolving the methylated gelatin (GelMA) powder prepared in the step S1 in bromocresol green (BCG) solution, and initiating 30min by using a 365 nm ultraviolet lamp to obtain bromocresol green-embedded methylated gelatin hydrogel (GelMA-BCG) (the mass ratio of bromocresol green to GelMA is 1:100);
s3, preparation of a bromocresol green embedded methylated gelatin hydrogel (GelMA-BCG) indication label: regulating the pH value of the bromocresol green embedded methylated gelatin hydrogel (GelMA-BCG) prepared in the step S2 to 3.5 by using hydrochloric acid, dripping the bromocresol green embedded methylated gelatin hydrogel (GelMA-BCG) onto 2mm x 3mm filter paper until the bromocresol green embedded methylated gelatin hydrogel is completely immersed, irradiating 30 min by using a 365 nm ultraviolet lamp, and transferring to an oven until the bromocresol green embedded methylated gelatin hydrogel (GelMA-BCG) indicator tag is completely dried;
Detection of fish freshness using bromocresol green embedded methylated gelatin hydrogel (GelMA-BCG) indicator tag:
40g of fish meat is placed in a culture dish of 90 mm, a methyl gelatin hydrogel (GelMA-BCG) indicating label embedded with bromocresol green is stuck on the inner side of a culture dish cover by using an adhesive tape, the culture dish is covered, the culture dish is sealed, and the culture dish is placed in a refrigerator at 4 ℃. As shown in fig. 1, bromocresol green embedded methylated gelatin hydrogel (GelMA-BCG) indicates that the tag is color responsive to changes in ammonia concentration in the environment and thus can be used to detect freshness of meat quality. After storage for different times, the methylated gelatin hydrogel (GelMA-BCG) embedded with bromocresol green indicates that the tag shows different colors along with the change of the freshness of the fish meat, yellow indicates that the fish meat is fresh, green indicates that the fish meat is fresher, and blue indicates that the fish meat has degenerated. The indicator label took 1-2 minutes to develop color and developed less color than example 1.
Example 2 construction of meat freshness Intelligent detection System
The utility model provides a visual intelligent detection meat freshness's detection APP based on hydrogel material lies in extracting the colour difference value delta E of a large amount of different meat freshness colour labels through the deep learning model, after constantly iterating training model, detects meat freshness through the label colour of cell-phone scanning meat that awaits measuring.
The intelligent detection system APP is constructed by the following steps:
S1, data acquisition: after label color acquisition for meat samples of different freshness using the application method of example 1, each image of the color label was matched to its potential class according to training factors and the features were collected for classification. The acquired images are classified into three categories according to the volatile nitrogen value: fresh (< 15 mg/100 g), less fresh (15-30 mg/100 g) and spoilage (> 30 mg/100 g);
s2, label scanning and developing: according to the characteristics of the experimental image in S1, a color label is segmented from the whole image by using a watershed algorithm based on a mark in an Open CV library;
s3, establishing a deep learning model: designing a three-class image classification network with VGG-16, including input, convolution, full Connection (FC) and output layers, using a rectifying linear unit (ReLU) function as an activation function for each convolution layer;
S4, APP development: the color indicator tag is combined with a marker-based watershed algorithm for image segmentation and the VGG 16 algorithm for deep learning is integrated therewith to form a mobile application to provide automatic recognition of freshness.
The specific method for detecting the intelligent detection system (mobile phone APP) comprises the following steps: in the process of producing and selling meat products, the methylated gelatin embedded bromocresol green hydrogel (GelMA-BCG) indication tag and meat are packaged, transported and stored together, and the color change of the indication tag accurately, quickly and timely reflects the freshness of the meat within 30 seconds by using a smart phone APP to scan the indication tag. Using the detection system shown in fig. 3 and the operation flow shown in fig. 4, the color change of the tag is shot by the smart phone APP to obtain the freshness, less freshness and spoilage information of the meat quality.
While the invention has been described with reference to the preferred embodiments, it is not limited thereto, and various changes and modifications can be made therein by those skilled in the art without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (4)
1. The preparation method of the methylated gelatin embedded bromocresol green hydrogel indication tag for visually and intelligently detecting the freshness of meat is characterized by comprising the following steps of:
S1, dissolving gelatin in a phosphate buffer solution, and heating to dissolve to obtain gelatin solution with the concentration of 5-20wt%; adding methacrylic anhydride into the gelatin solution, wherein the volume fraction of the methacrylic anhydride relative to the gelatin solution is 0.1% -2%, uniformly mixing for reaction, transferring to a dialysis bag for dialysis after finishing reaction, and then drying to obtain methylated gelatin GelMA with the substitution degree of 90.9%;
S2, adding bromocresol green BCG and a photoinitiator into water, and uniformly mixing to obtain a BCG solution, wherein the concentration of the photoinitiator is 0.3-0.8wt%, and the concentration of bromocresol green is 0.05-2 mg/mL; then adding the methylated gelatin GelMA obtained in the step S1 into a BCG solution, wherein the mass ratio of the BCG to the GelMA is 1:80, dissolving and mixing uniformly, and irradiating by an ultraviolet lamp to initiate a reaction, so as to obtain the methylated gelatin hydrogel GelMA-BCG embedded with bromocresol green after the reaction is finished;
S3, adjusting the pH value of the bromocresol green embedded methylated gelatin hydrogel GelMA-BCG obtained in the step S2 to 3-5 by using acid, then dripping the bromocresol green embedded methylated gelatin hydrogel GelMA-BCG onto filter paper until the bromocresol green embedded methylated gelatin hydrogel is completely immersed, irradiating by using an ultraviolet lamp, and drying to obtain the bromocresol green embedded methylated gelatin hydrogel indication label.
2. The methylated gelatin-embedded bromocresol green hydrogel indicator tag for visually and intelligently detecting meat freshness prepared by the method of claim 1.
3. Use of a methylated gelatin-embedded bromocresol green hydrogel indicator tag for visually and intelligently detecting meat freshness according to claim 2 in detecting fish freshness.
4. A detection system APP based on the methylated gelatin embedded bromocresol green hydrogel indication tag for visually and intelligently detecting meat freshness according to claim 2, wherein the color characteristics of a large number of indication tags after detection of different meat freshness are extracted through a deep learning model, and after the training model is continuously iterated, the tag colors of meat to be detected are scanned through a mobile phone to detect meat freshness.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211141185.9A CN115561233B (en) | 2022-09-20 | 2022-09-20 | Method for visually and intelligently detecting freshness of meat based on hydrogel material |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211141185.9A CN115561233B (en) | 2022-09-20 | 2022-09-20 | Method for visually and intelligently detecting freshness of meat based on hydrogel material |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115561233A CN115561233A (en) | 2023-01-03 |
| CN115561233B true CN115561233B (en) | 2024-10-18 |
Family
ID=84741596
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211141185.9A Active CN115561233B (en) | 2022-09-20 | 2022-09-20 | Method for visually and intelligently detecting freshness of meat based on hydrogel material |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115561233B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107290335A (en) * | 2017-04-07 | 2017-10-24 | 广东海洋大学 | A kind of intelligent label for indicating aquatic products freshness and preparation method thereof |
| CN114414566A (en) * | 2021-12-20 | 2022-04-29 | 北京市农林科学院信息技术研究中心 | Nondestructive testing method and device for freshness of fishes |
| CN114814084A (en) * | 2022-03-24 | 2022-07-29 | 武汉大学 | Method for detecting pH by using microneedle |
Family Cites Families (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101910014B1 (en) * | 2016-10-05 | 2018-10-19 | 연세대학교 원주산학협력단 | Indicator for sensing freshness of food and preparation method thereof, method for monitoring freshness od food using the same |
| CN109575317A (en) * | 2017-09-29 | 2019-04-05 | 天津大学 | A kind of high intensity hydrogel and preparation method thereof with pH response |
| CN109089992A (en) * | 2018-06-04 | 2018-12-28 | 浙江海洋大学 | A kind of classification method and system of the Estimation of The Fish Freshness based on machine vision |
| CN109115758B (en) * | 2018-08-22 | 2021-04-06 | 广西大学 | Preparation method and application of freshness indication type intelligent label |
| US11698344B2 (en) * | 2018-09-05 | 2023-07-11 | University Of South Carolina | PH indicator swabs for biomonitoring and diagnostics |
| CN110327056B (en) * | 2019-05-24 | 2021-01-01 | 武汉大学 | Intelligent hydrogel for visual blood glucose detection and preparation method thereof |
| CN110618116B (en) * | 2019-08-28 | 2022-01-11 | 江苏大学 | Preparation method and application of intelligent indication label for visually detecting freshness of meat |
| TWI729684B (en) * | 2020-01-21 | 2021-06-01 | 台灣奈米碳素股份有限公司 | A system and method for managing and trading fresh foods according to the flavor thereof |
| CN113549226B (en) * | 2020-04-24 | 2022-11-01 | 华中科技大学 | Photonic crystal hydrogel for visual bacterial detection and preparation and application thereof |
| CN112465094B (en) * | 2020-11-23 | 2022-08-16 | 武汉大学 | Dynamic two-dimensional code intelligent sensing label system for monitoring food freshness in real time |
| CN113279287A (en) * | 2021-05-08 | 2021-08-20 | 荆楚理工学院 | Preparation method of visual freshness label based on lycium ruthenicum anthocyanin |
| CN113402734B (en) * | 2021-06-17 | 2023-04-18 | 东北农业大学 | Preparation method and application of hydrogel for indicating freshness of chilled meat |
| CN113651748B (en) * | 2021-07-19 | 2023-05-23 | 华南理工大学 | Volatile basic nitrogen response type compound, portable detection test paper, preparation method and application |
| CN113563609A (en) * | 2021-07-28 | 2021-10-29 | 华南理工大学 | Nano composite porous hydrogel and preparation and application thereof |
| CN113674265B (en) * | 2021-08-27 | 2024-05-14 | 石河子大学 | Meat quality qualitative detection method based on thermal imaging and visual imaging fusion in time sequence temperature changing process |
| CN114047184B (en) * | 2021-09-23 | 2023-12-05 | 河北科技师范学院 | Preparation method and application of intelligent indication tag for identifying freshness of meat |
| CN114349990B (en) * | 2022-01-18 | 2023-10-10 | 苏州大学 | Hydrogel with adjustable dynamic characteristics and preparation method and application thereof |
| CN114456404B (en) * | 2022-01-24 | 2024-02-13 | 哈尔滨工业大学 | Liquid metal flexible wearable device and preparation method thereof |
| CN114409940B (en) * | 2022-03-01 | 2023-01-24 | 南京鼓楼医院 | Preparation method and application of fish gelatin hydrogel inverse opal film with pH responsiveness |
| CN114835844B (en) * | 2022-05-26 | 2023-10-27 | 仲恺农业工程学院 | Intelligent packaging hydrogel material with carbon dioxide response performance of fruit and vegetable metabolic gas product and application thereof |
-
2022
- 2022-09-20 CN CN202211141185.9A patent/CN115561233B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107290335A (en) * | 2017-04-07 | 2017-10-24 | 广东海洋大学 | A kind of intelligent label for indicating aquatic products freshness and preparation method thereof |
| CN114414566A (en) * | 2021-12-20 | 2022-04-29 | 北京市农林科学院信息技术研究中心 | Nondestructive testing method and device for freshness of fishes |
| CN114814084A (en) * | 2022-03-24 | 2022-07-29 | 武汉大学 | Method for detecting pH by using microneedle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115561233A (en) | 2023-01-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wells et al. | Colourimetric plastic film indicator for the detection of the volatile basic nitrogen compounds associated with fish spoilage | |
| CN109115758B (en) | Preparation method and application of freshness indication type intelligent label | |
| CN103267843B (en) | Colloidal gold test paper card, corresponding collaurum analyser and method of testing | |
| CN104198695B (en) | A kind of method for the interpretation of result that developed the color to colloidal gold strip | |
| Salinas et al. | Monitoring of chicken meat freshness by means of a colorimetric sensor array | |
| CN105181912B (en) | A kind of Noninvasive Measuring Method of Freshness in rice storage | |
| AU2012225196B2 (en) | Method and software for analysing microbial growth | |
| CN110618116A (en) | Preparation method and application of intelligent indication label for visually detecting freshness of meat | |
| CN112020738B (en) | Method and apparatus for product monitoring | |
| Munekata et al. | Applications of electronic nose, electronic eye and electronic tongue in quality, safety and shelf life of meat and meat products: a review | |
| Lin et al. | A pH-Responsive colourimetric sensor array based on machine learning for real-time monitoring of beef freshness | |
| US11366067B2 (en) | System and method for evaluating flavor of food based on gas | |
| CN115561233B (en) | Method for visually and intelligently detecting freshness of meat based on hydrogel material | |
| Moon et al. | Application of colorimetric indicators to predict the fermentation stage of kimchi | |
| Shen et al. | Consumer-oriented smart dynamic detection of fresh food quality: recent advances and future prospects | |
| Lin et al. | Fast real-time monitoring of meat freshness based on fluorescent sensing array and deep learning: From development to deployment | |
| CN110322434A (en) | A kind of squid freshness identification method based on color notation conversion space and pixel cluster | |
| CN114656440B (en) | Near infrared emission fluorescent probe for indicating freshness of sea water fish meat, dual-channel indicating card prepared by same and application of dual-channel indicating card | |
| CN115876734A (en) | Intelligent meat freshness detection method, system and medium based on fluorescent sensing array | |
| Zaragozá et al. | Proof of concept of using chromogenic arrays as a tool to identify blue cheese varieties | |
| CN111239119A (en) | System and method for colorimetric detection of mercury ions based on App | |
| CN114397281B (en) | Visual fluorescent sensor and application thereof | |
| CN112730392B (en) | Test strip for rapidly detecting acid value of salad dressing, preparation method and test method | |
| Nami et al. | Recent Progress in Intelligent Packaging for Seafood and Meat Quality Monitoring | |
| CN110084409B (en) | Preparation method of intelligent indication label, and remaining shelf life prediction method and device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |