CN111401350A - Colorimetric card for evaluating repeated freezing and thawing times of meat and preparation method and application thereof - Google Patents
Colorimetric card for evaluating repeated freezing and thawing times of meat and preparation method and application thereof Download PDFInfo
- Publication number
- CN111401350A CN111401350A CN202010141637.8A CN202010141637A CN111401350A CN 111401350 A CN111401350 A CN 111401350A CN 202010141637 A CN202010141637 A CN 202010141637A CN 111401350 A CN111401350 A CN 111401350A
- Authority
- CN
- China
- Prior art keywords
- thawing
- freezing
- meat
- sample
- color
- 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
Links
- 238000010257 thawing Methods 0.000 title claims abstract description 87
- 238000007710 freezing Methods 0.000 title claims abstract description 83
- 230000008014 freezing Effects 0.000 title claims abstract description 83
- 235000013372 meat Nutrition 0.000 title claims abstract description 60
- 238000002360 preparation method Methods 0.000 title description 5
- 238000000034 method Methods 0.000 claims abstract description 17
- 238000004519 manufacturing process Methods 0.000 claims abstract description 11
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 3
- 230000001131 transforming effect Effects 0.000 claims description 2
- 238000003384 imaging method Methods 0.000 claims 1
- 238000002372 labelling Methods 0.000 claims 1
- 235000015277 pork Nutrition 0.000 abstract description 27
- 239000003086 colorant Substances 0.000 abstract description 4
- 230000001953 sensory effect Effects 0.000 description 10
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000002474 experimental method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000012795 verification Methods 0.000 description 5
- 235000013622 meat product Nutrition 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000000052 comparative effect Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000012425 Freezing-thawing process Methods 0.000 description 2
- 239000013078 crystal Substances 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 239000004519 grease Substances 0.000 description 2
- 230000008018 melting Effects 0.000 description 2
- 238000002844 melting Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 102000004190 Enzymes Human genes 0.000 description 1
- 108090000790 Enzymes Proteins 0.000 description 1
- 239000004698 Polyethylene Substances 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 210000000170 cell membrane Anatomy 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 210000003195 fascia Anatomy 0.000 description 1
- 235000011389 fruit/vegetable juice Nutrition 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000000265 homogenisation Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 244000144972 livestock Species 0.000 description 1
- 244000005700 microbiome Species 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 210000001087 myotubule Anatomy 0.000 description 1
- 230000003647 oxidation Effects 0.000 description 1
- 238000007254 oxidation reaction Methods 0.000 description 1
- -1 polyethylene Polymers 0.000 description 1
- 229920000573 polyethylene Polymers 0.000 description 1
- 244000144977 poultry Species 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000010561 standard procedure Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 210000001519 tissue Anatomy 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/147—Details of sensors, e.g. sensor lenses
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J3/00—Spectrometry; Spectrophotometry; Monochromators; Measuring colours
- G01J3/46—Measurement of colour; Colour measuring devices, e.g. colorimeters
- G01J3/52—Measurement of colour; Colour measuring devices, e.g. colorimeters using colour charts
- G01J3/522—Measurement of colour; Colour measuring devices, e.g. colorimeters using colour charts circular colour charts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Vascular Medicine (AREA)
- Multimedia (AREA)
- Probability & Statistics with Applications (AREA)
- Spectrometry And Color Measurement (AREA)
Abstract
A method for manufacturing a colorimetric card for evaluating the repeated freezing and thawing times of meat. The method for manufacturing the color comparison card comprises the following steps: preparing a meat sample, under the condition of the same freezing time and thawing temperature, taking the number of times of freezing and thawing as a variable, respectively thawing the meat sample every 24 hours within the range of 0-7 times of freezing and thawing, collecting sample images, and storing the images with different freezing and thawing times in a classified manner; preprocessing the collected image data, and then manufacturing a color comparison card by using a K-Means algorithm. The prepared colorimetric card comprises color blocks corresponding to the colors of meat samples under different freezing and thawing times, and the freezing and thawing times of the samples are marked under the color blocks. The colorimetric card is applied to evaluating the freezing and thawing times of meat, and has the advantages that: the color comparison card is simple to operate and high in identification speed; the prepared colorimetric card has good feasibility and stability, the identification accuracy of the colorimetric card is high, and the rapid, scientific and standard identification of the repeated freezing and thawing times of the pork can be realized.
Description
Technical Field
The invention relates to the field of meat quality evaluation, in particular to a colorimetric card for evaluating the repeated freezing and thawing times of meat and a preparation method and application thereof.
Background
In the modern meat product industry, the livestock and poultry frozen meat is an important product for regulating the meat food market in China and is also a main form of circulation and import and export trade of meat products in domestic regions. Compared with fresh meat, the low-temperature condition of frozen meat can inhibit the growth and reproduction of most microorganisms, reduce enzyme activity, prolong the shelf life of products and increase the mobility and dominance of meat product consumption, but ice crystals with different sizes are generated in the freezing process of meat, the formation of the ice crystals can not only destroy cell membranes and damage the tissue structure of the meat, but also cause the loss of a large amount of juice in the thawed meat, and simultaneously cause the oxidation of protein and fat in the meat product, thereby changing the color of the meat. For consumers, the color is more intuitive when the meat is purchased, and in a non-contact state, the color is an important basis for the consumers to judge the product quality and is also the most leading sensory factor for judging the freezing and thawing times and freshness of the meat. However, the color is judged only by naked eyes, so that the conditions of misjudgment and missed judgment are easily caused by strong subjectivity, low repeatability and the like, and the problems of overhigh cost, overlow efficiency or sample pollution are caused if the color is measured by a precise instrument.
Disclosure of Invention
In order to solve the technical problems in the prior art, the invention provides a rapid, scientific and standard method for manufacturing a color comparison card for evaluating the number of times of repeated freezing and thawing of meat.
The technical scheme of the invention is as follows:
the invention aims to provide a method for manufacturing a colorimetric card for evaluating the freezing and thawing times of meat, which comprises the following steps:
1) samples were collected for different freeze-thaw times:
taking a meat sample, taking the freezing and thawing times as variables, and obtaining samples with different freezing and thawing times under the condition that the freezing temperature and the freezing time are the same after thawing each time;
2) image acquisition:
step 1) after thawing the samples collected and obtained in different freezing and thawing times, respectively shooting collected images by using a camera, keeping the illumination intensity in the field of view of the camera stable, keeping the brightness of the shot light the same, and ensuring that the shot images are clear, preferably, the number of the shot samples is not less than 3, wiping water stains and oil stains on the shot parts by using oil absorption paper before shooting, avoiding reflecting points generated by mirror reflection caused by grease on the surface of pork or water generated by melting, and storing the images in a classified manner according to different freezing and thawing times;
3) image preprocessing:
preprocessing each image acquired in the step 2) by adopting the following 3 modes respectively: 1. randomly rotating; 2. randomly overturning; 3. stretching and transforming; the number of samples is further increased so as to increase the accuracy of the test result;
4) color comparison card made by using K-Means algorithm
Converting the image information preprocessed in the step 3) into parameters which can be recognized by a computer by adopting an image processing program TensorFlow:
firstly, extracting not less than 10 4 × 4 pixel blocks from each image preprocessed in the step 3), respectively traversing each 4 × 4 pixel block by using a slider with the size of 2 × 2 and the step length of 1, and classifying the traversal results according to different freezing and thawing times to obtain R, G, B values contained in all 4 × 4 pixel blocks of each freezing and thawing time sample image, wherein R, G, B values are Red (Red), Green (Green) and Blue (Blue) correspondingly;
secondly, clustering the R, G, B value traversal results contained in all 4 × 4 pixel blocks of the obtained sample images of each freeze-thaw frequency by using a K-Means algorithm, calculating the distance between each clustering point through Euclidean distance, finally determining the cluster center point of each clustering point, respectively extracting R, G, B values corresponding to the center point in each category, and carrying out mean value processing to obtain the average R, G, B value of the sample images of each freeze-thaw frequency;
and then, printing average R, G, B information of each freezing and thawing frequency into color blocks, wherein the color blocks are sample colors with different freezing and thawing frequencies, arranging the color blocks in sequence according to the freezing and thawing frequencies, and drawing to obtain the colorimetric card for evaluating the freezing and thawing frequencies of the meat.
Further, the step 1) is specifically that the meat sample is sampled once when not frozen, then the meat sample is frozen and then thawed once every 24 hours, and then the meat sample is sampled, wherein the freezing and thawing times are not less than 7. In a particular embodiment, the freezing conditions are (-18 ± 2) ° c.
Further, in the step 1), the unfreezing is to unfreeze the sample until the central temperature reaches 0-2 ℃.
In a special embodiment, the thawing mode is that the meat sample is thawed by running water at room temperature until the central temperature of the meat sample reaches 0-2 ℃.
Further, in the step 2), the number of the shot pictures of each sample is not less than 3,
further, the specific operation is as follows: placing the sample on a sample plate, and keeping a camera above the sample to shoot vertically overlooking;
furthermore, the camera and the sample are placed in the same closed environment system for shooting;
further, the vertical distance between the camera of the camera and the sample photographing part is 20 cm.
Further, the step 4) further comprises marking the number of times of freezing and thawing on each corresponding color block of the colorimetric card.
The second purpose of the invention is to provide the colorimetric card prepared by the preparation method.
In a specific embodiment, the meat sample is frozen and thawed 7 times, and the prepared colorimetric card comprises 8 color blocks with the color gradually changed from light pink to water red, wherein the color blocks represent pork colors with the freezing and thawing times of 0-7 times respectively, and the freezing and thawing times are marked under each color block and are 0, 1, 2, 3, 4, 5, 6 and 7 times from left to right.
The third purpose of the invention is to provide the application of the colorimetric card in the evaluation of the freezing and thawing times of meat.
Further, comparing the meat sample to be detected with the color block on the color comparison card, wherein the freezing and thawing times corresponding to the color block with the same color as the meat sample to be detected are the freezing and thawing times of the meat sample to be detected.
Furthermore, the type, freezing condition and thawing condition of the meat sample to be detected and the meat sample used for preparing the colorimetric card are the same.
The invention has the beneficial effects that:
the colorimetric card is simple to manufacture and operate, sample images under different freezing and thawing times are collected and then preprocessed, and the colorimetric card is manufactured based on the Euclidean distance clustering algorithm, so that the accuracy rate is high, and the speed is high; the prepared colorimetric card has good feasibility and stability, the identification accuracy of the colorimetric card is high, and the identification of the repeated freezing and thawing times of meat can be realized; the method can provide scientific and accurate guide basis for the purchase of the meat of the consumer, provide guide basis for monitoring the processing and storage process of the meat of the enterprise, and also provide reference basis for the identification research of the related colors of other products.
Drawings
FIG. 1 is a diagram illustrating the result of image preprocessing according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a process of producing a color chart according to the K-Means algorithm of the embodiment of the present invention;
FIG. 3 is a schematic diagram of a process for making a color chart according to the comparative example mean algorithm of the present invention;
fig. 4 is a schematic diagram of a color chart prepared according to an embodiment of the invention.
FIG. 5 is a graph showing RGB value changes of K-Means algorithm at 0-7 times of freezing and thawing according to an embodiment of the present invention
FIG. 6 is a graph showing the RGB value variation of the mean value algorithm for 0-7 freeze-thaw cycles of comparative examples of the present invention
Detailed Description
Example 1 evaluation of the number of Freeze-thawing of pork samples
1) Collecting pork samples of different freezing and thawing times:
taking pork samples, taking the number of times of freezing and thawing as a variable, and obtaining samples with different numbers of times of freezing and thawing within the range of 0-7 times of freezing and thawing respectively under the condition that the freezing temperature (-18 +/-2 ℃) and the freezing time (24h) are the same after thawing.
The preparation method of the freeze-thawed pork sample comprises the following steps:
taking the longissimus dorsi of a 24-hour slaughtered pig, removing fascia, cutting the longissimus dorsi into 5cm × 5cm × 3cm meat blocks which are 12 blocks in total along the direction perpendicular to muscle fibers, collecting a first image (freezing and thawing for 0 time) according to the operation of the step 2), then, using a polyethylene bag to package all samples, freezing and storing the samples at (-18 +/-2) DEG C for 24 hours, taking out the samples, thawing the samples in running water at room temperature, completing the 1 st freezing-thawing process when the central temperature of the meat sample reaches 0-2 ℃, placing 12 pork samples back to the (-18 +/-2) DEG C for freezing and storing the samples at (-18 +/-2) DEG C after the image collecting step is completed, taking out the samples after 24 hours, thawing in running water at room temperature, completing the 2 nd freezing-thawing process when the central temperature of the meat sample reaches 0-2 ℃, and so on.
2) Image acquisition
Unfreezing every 24h to collect pork images, and storing the images in different time periods in a classified manner;
step 1) thawing the pork samples collected and obtained in different freezing and thawing times, and shooting and sampling in a closed black box body by using a type camera, wherein the specific collection process is as follows: pork is placed on a matte black sample plate in a black box body, the vertical distance between a camera of the camera and a pork shooting part is 20cm, the shooting part is wiped by filter paper before shooting, and a reflection point generated by mirror reflection due to the fact that grease on the surface of the pork or water generated by melting is avoided. The number of the pictures taken on each pork is 3, the total amount of image data is 288 (12 blocks of 3 blocks of 8 times of freezing and thawing), and the pork outer spine meat is selected for shooting in the embodiment;
3) image pre-processing
The shape and the number of the samples can influence the accuracy of the shooting result in the process of collecting the images; the problems of poor quality and unbalanced samples of partial pork images caused by the reasons of irregular pork shapes, slight difference of placing positions, uneven fat and thin and the like further influence the accuracy of experimental results, and the workload of manually screening photos is large and the standard is difficult to control; for the number of samples, the abundant training set and the prediction set can ensure that the experimental result has better accuracy, but due to the reasons of higher pork cost and the like, the cost performance of the scheme for acquiring a large number of samples is not high. Therefore, each image acquired in step 2) is preprocessed in the following 3 ways: 1. randomly rotating; 2. randomly overturning; 3. a stretch transformation (fig. 1);
4) manufacture of color comparison card
Converting the image information preprocessed in the step 3) into parameters which can be recognized by a computer by adopting an image processing program TensorFlow:
as shown in fig. 2, firstly, 10 pixel blocks of 4 × 4 are extracted from each image preprocessed in step 3), a slider with the size of 2 × 2 and the step length of 1 is used for traversing each pixel block of 4 × 4, the traversal results are classified according to different freezing and thawing times, and R, G, B values contained in all the pixel blocks of 4 × 4 of each freezing and thawing time sample image are obtained, wherein R, G, B values correspond to Red (Red), Green (Green) and Blue (Blue);
secondly, clustering the R, G, B value traversal results contained in all 4 × 4 pixel blocks of the obtained sample images of each freeze-thaw frequency by using a K-Means algorithm, calculating the distance between each clustering point through Euclidean distance, finally determining the cluster center point of each clustering point, respectively extracting R, G, B values corresponding to the center point in each category, and carrying out mean value processing to obtain the average R, G, B value of the sample images of each freeze-thaw frequency;
and then, printing average R, G, B information of each freezing and thawing frequency into color blocks, sequentially arranging the color blocks according to the freezing and thawing frequency, and drawing to obtain the colorimetric card for evaluating the freezing and thawing frequency of the meat.
As shown in fig. 4, the colorimetric card includes 8 color blocks with a color gradient from light pink to water red, and the subscripts of the color blocks are labeled with corresponding times of freezing and thawing, which are 0, 1, 2, 3, 4, 5, 6, and 7 times, respectively, and each color number has a corresponding color region.
And carrying out color comparison on the pork sample to be tested by using the color comparison card for evaluating the repeated freezing and thawing times of the pork, wherein the repeated freezing and thawing times of the pork are known according to the freezing and thawing times corresponding to the color block of the pork to be tested and the color block of the color comparison card, for example, the color of the pork is the same as the color number 0 of the color comparison card, and the repeated freezing and thawing times of the pork are 0.
Comparative example
The main process of making the color card by the homogenization algorithm is shown in fig. 3, firstly, a 24 × 24-sized slider is used to traverse the pork original image to obtain RGB mean pixel blocks in a 24 × 24 region, then the RGB mean pixel blocks in the region are gradually increased to 9 × 9 → 5 × 5 → 3 × 3, the number of the pixel blocks is gradually decreased with the gradual increase of the slider, finally, the local RGB mean value is gradually changed to the global RGB mean value, the dominant hue of the image is obtained by the global RGB mean pixel blocks, and so on, all the images are traversed to obtain the dominant hue of the sample image in 8 time periods of repeated freezing and thawing for 0-7 times, the dominant hue of the image of each repeated freezing and thawing pork is sequentially arranged according to the number of repeated freezing and thawing, and the obtained dominant hue sequence diagram is the color card made by the mean algorithm (fig. 3).
The accuracy of the colorimetric card is verified by adopting a K-medoids algorithm and combining a sensory experiment:
(1) algorithm validation
The K-medoids algorithm is characterized in that each picture is divided into a plurality of areas by a sliding block with the size of 4 × 4, the RGB color of each area is subjected to mean processing, 8 points are randomly selected from total sample points to serve as center points (medoids), the selected medoids are randomly existing points (8 cluster groups in total) in the current cluster group, the algorithm requires that the medoids are the minimum sum of distances from all other points in the current cluster group to the medoids, all images are traversed, the point is finally determined, the RGB value of the point is taken as the RGB value of the cluster group, the RGB values of the 8 cluster groups are obtained by analogy, the RGB values of the 8 cluster groups are compared with the RGB values obtained by the mean algorithm and the K-Means algorithm to serve as the main basis for evaluating the accuracy of the color comparison card, and the accuracy verification results are respectively mean algorithm-88% and K-Means algorithm-92%.
(2) Comparison of sensory tests
Test samples were re-obtained from 0-7 repeated freeze-thaw cycles with the same treatment method, and a total of 8 trained sensory assessors, male: 2 for female: 6, the age is 20-26 years old, and the food is professional and good in health, colorless and blind, and can effectively distinguish color difference. The experimental procedure was as follows: (1) after 8 samples are pasted with the correct times of freeze thawing, the sequence is disordered and the samples are randomly arranged in two lines; (2) evaluating the freeze-thaw times of 8 samples by a sensory evaluator with reference to a color comparison card manufactured by a mean algorithm, starting a test with reference to the color comparison card manufactured by a K-Means algorithm at an interval of 10min after evaluation, and repeating the steps to obtain sensory experiment data corresponding to 2 color comparison cards; (3) and comparing the sensory experiment data with the real data to obtain the accuracy of the sensory experiments of the 2 kinds of color cards, and taking the accuracy as a judgment basis for evaluating the 2 kinds of color cards. The experiment was repeated 3 times, and the average of the accuracy was taken as the final experimental result. The result of the accuracy sensory verification is respectively 85 percent of the mean algorithm and 91 percent of the K-Means algorithm.
(3) Discussion of results
After the color comparison cards manufactured by the mean algorithm and the K-Means algorithm are subjected to algorithm verification and sensory verification, the accuracy rate of the color comparison cards manufactured by the mean algorithm and the K-Means algorithm is higher than that of the K-Means algorithm, and the verification accuracy rate of the K-Means algorithm is far higher than that of the mean algorithm, so that the color comparison cards manufactured by the K-Means algorithm have good stability and feasibility and are more suitable for rapidly identifying the repeated freezing and thawing times of pork.
The above description is only an example of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A colorimetric card manufacturing method for evaluating the freezing and thawing times of meat is characterized by comprising the following steps:
1) samples were collected for different freeze-thaw times:
taking a meat sample, and taking the freezing and thawing times as variables to obtain samples with different freezing and thawing times;
2) image acquisition:
step 1) after thawing the samples collected and obtained with different freezing and thawing times, respectively shooting collected images by using a camera, and storing the images in a classified manner according to the different freezing and thawing times;
3) image preprocessing:
preprocessing each image acquired in the step 2) by adopting the following 3 modes respectively: 1. randomly rotating; 2. randomly overturning; 3. stretching and transforming;
4) color comparison card made by using K-Means algorithm
Converting the image information preprocessed in the step 3) into parameters which can be recognized by a computer by adopting an image processing program TensorFlow:
firstly, extracting not less than 10 4 × 4 pixel blocks from each image preprocessed in the step 3), respectively traversing each 4 × 4 pixel block by using a slider with the size of 2 × 2 and the step length of 1, and classifying traversal results according to different freeze-thaw times to obtain R, G, B values contained in all 4 × 4 pixel blocks of each freeze-thaw time sample image;
secondly, clustering the R, G, B value traversal results contained in all 4 × 4 pixel blocks of the obtained sample images of each freeze-thaw frequency by using a K-Means algorithm, calculating the distance between each clustering point through Euclidean distance, finally determining the cluster center point of each clustering point, respectively extracting R, G, B values corresponding to the center point in each category, and carrying out mean value processing to obtain the average R, G, B value of the sample images of each freeze-thaw frequency;
and then, printing average R, G, B information of each freezing and thawing frequency into color blocks, sequentially arranging the color blocks according to the freezing and thawing frequency, and drawing to obtain the colorimetric card for evaluating the freezing and thawing frequency of the meat.
2. The method for preparing a color comparison card for evaluating the freezing and thawing times of meat according to claim 1, wherein the step 1) comprises sampling the meat sample once when the meat sample is not frozen, thawing the meat sample once every 24 hours after freezing the meat sample, and sampling, wherein the freezing and thawing times are not less than 7.
3. The method for manufacturing a color chart for evaluating the freezing and thawing times of meat according to claim 2, wherein in the thawing step 1), the sample is thawed until the central temperature reaches 0-2 ℃.
4. The method for preparing a color chart for evaluating the number of freezing and thawing of meat according to claim 1, wherein in the step 2), not less than 3 samples are photographed.
5. The method for making a color chart for evaluating the number of freezing and thawing of meat as claimed in claim 4, wherein said photographing of step 2) is specifically operated as: placing the sample on a sample plate, and keeping a camera above the sample to shoot vertically overlooking;
preferably, the camera and the sample are placed in the same closed environment system for shooting;
more preferably, the vertical distance between the camera of the camera and the sample imaging part is 20 cm.
6. The method for manufacturing a color comparison card for evaluating the freezing and thawing times of meat as claimed in claim 1, wherein said step 4) further comprises labeling the freezing and thawing times at the corresponding color blocks of the color comparison card.
7. The colorimetric card produced by the production method according to claim 1.
8. Use of the colorimetric card of claim 7 for assessing the number of freezing and thawing cycles of meat.
9. The application of claim 8, wherein the number of freeze-thaw times corresponding to the color block with the same color as the meat sample is determined by comparing the meat sample to be tested with the color block on the color chart.
10. The use according to claim 9, wherein the meat sample to be tested is the same as the meat sample used for preparing the colorimetric card in terms of the type, freezing and thawing conditions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010141637.8A CN111401350A (en) | 2020-03-03 | 2020-03-03 | Colorimetric card for evaluating repeated freezing and thawing times of meat and preparation method and application thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010141637.8A CN111401350A (en) | 2020-03-03 | 2020-03-03 | Colorimetric card for evaluating repeated freezing and thawing times of meat and preparation method and application thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111401350A true CN111401350A (en) | 2020-07-10 |
Family
ID=71430539
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010141637.8A Pending CN111401350A (en) | 2020-03-03 | 2020-03-03 | Colorimetric card for evaluating repeated freezing and thawing times of meat and preparation method and application thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111401350A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2019095384A (en) * | 2017-11-27 | 2019-06-20 | 株式会社リコー | Color evaluation device, method for evaluating color, and program |
| CN110646416A (en) * | 2019-09-27 | 2020-01-03 | 渤海大学 | Colorimetric card for evaluating smoked chicken quality and application |
| CN110675400A (en) * | 2019-11-15 | 2020-01-10 | 石河子大学 | Rapid and intelligent mutton quality index detection method based on mobile phone APP |
-
2020
- 2020-03-03 CN CN202010141637.8A patent/CN111401350A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2019095384A (en) * | 2017-11-27 | 2019-06-20 | 株式会社リコー | Color evaluation device, method for evaluating color, and program |
| CN110646416A (en) * | 2019-09-27 | 2020-01-03 | 渤海大学 | Colorimetric card for evaluating smoked chicken quality and application |
| CN110675400A (en) * | 2019-11-15 | 2020-01-10 | 石河子大学 | Rapid and intelligent mutton quality index detection method based on mobile phone APP |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102564964B (en) | Spectral image-based meat quality visual non-contact detection method | |
| CN104897581B (en) | The method and device of identification green meat, chilled meat and chilled meat based on EO-1 hyperion | |
| CN103076288B (en) | A kind of flesh of fish self-grading device based on computer vision and method | |
| EP1417632A1 (en) | Robust stain detection and quantification for histological specimens based on a physical model for stain absorption | |
| CN114169618B (en) | Kiwi fruit maturity nondestructive identification prediction method based on machine vision learning | |
| CN111652326A (en) | Improved fruit maturity identification method and identification system based on MobileNet v2 network | |
| CN110349153A (en) | The image method tobacco based on multi-feature fusion detection method of rate containing stalk | |
| CN111160451A (en) | Flexible material detection method and storage medium thereof | |
| CN110826552A (en) | Grape nondestructive automatic detection device and method based on deep learning | |
| CN114677671A (en) | Automatic identifying method for old ribs of preserved szechuan pickle based on multispectral image and deep learning | |
| CN109975292A (en) | A kind of atlantic salmon and rainbow trout method for quick identification based on machine vision | |
| CN107576660B (en) | A kind of double yellow duck egg Automatic Visual Inspection method based on apart from contour | |
| CN112560896A (en) | Fruit quality screening and classifying system based on image processing | |
| CN115330868A (en) | Grape picking method based on deep learning and depth information fusion | |
| Zuñiga et al. | Grape maturity estimation based on seed images and neural networks | |
| Asmara et al. | Chicken meat freshness identification using colors and textures feature | |
| Motonaga et al. | A method of making digital fruit color charts for cultivation management and quality control | |
| CN116309564B (en) | Method and system for detecting appearance defects of battery cells based on artificial intelligent image recognition | |
| CN111401350A (en) | Colorimetric card for evaluating repeated freezing and thawing times of meat and preparation method and application thereof | |
| CN112634274A (en) | Machine vision-based fattening pork quality evaluation method and system | |
| CN105447891B (en) | The appraisal procedure and system of chilled meat freshness | |
| Huang et al. | Mango surface defect detection based on HALCON | |
| CN113077420B (en) | Fish fiber evaluation method and system based on convolutional neural network | |
| CN110580495A (en) | automatic analysis method for leaf area and leaf surface anthracnose lesion number of pear | |
| CN114419359A (en) | Myofibroblast image classification and identification method and system based on ATP enzyme staining |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200710 |
|
| WD01 | Invention patent application deemed withdrawn after publication |