CN113484250B - Method for manufacturing colorimetric card for evaluating color of potato skins and potato flesh and evaluation method - Google Patents
Method for manufacturing colorimetric card for evaluating color of potato skins and potato flesh and evaluation method Download PDFInfo
- Publication number
- CN113484250B CN113484250B CN202110182727.6A CN202110182727A CN113484250B CN 113484250 B CN113484250 B CN 113484250B CN 202110182727 A CN202110182727 A CN 202110182727A CN 113484250 B CN113484250 B CN 113484250B
- Authority
- CN
- China
- Prior art keywords
- color
- potato
- pixels
- cluster
- clustering
- 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
Images
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
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Spectrometry And Color Measurement (AREA)
Abstract
A color comparison card manufacturing method and an evaluation method for evaluating the color of potato peel and potato flesh are characterized in that sample preparation is carried out, then a picture with high reduction degree is taken, and white balance correction is carried out through an international standard color card Pantong color card; accurately extracting the potato block outline by a Canny edge detection algorithm, summarizing the cluster colors of all potato skins and potato flesh, obtaining the color grade of the potato skins and the potato flesh, and printing the color grade on a waterproof, wear-resistant and corrosion-resistant material to prepare a color card. The color card is applied to the color classification of the potato skin and the potato pulp, has simple operation and high recognition speed, can realize the rapid, scientific and standard classification, and is a necessary tool for the standardized classification of the commercial potatoes.
Description
Technical Field
The invention relates to the field of potato quality evaluation, in particular to a method for manufacturing a color comparison card for evaluating the color of potato skin and potato flesh and an evaluation method.
Background
In china, potato is the fourth largest food crop following corn, rice and wheat. Since 1995, the potato planting area and the total yield of China are in the 1 st position of the world. The planting area is more than 7500 ten thousand mu throughout the year, the yield is more than 8500 ten thousand tons, and the specific gravity of the potato planting area and the yield in the world are respectively 29.7 percent and 24.2 percent. Wherein the ratio of potatoes used for fresh eating is about 85 percent, and the ratio of other potatoes used for processing, seeds, feed and the like is lower.
The grade standards of fresh food and processed potatoes have national standards and local standards, cover the block weight, the shape, the defect rate and the impurity rate of the potatoes, but lack the standards on the color of the potatoes. In actual commercial potato circulation, potatoes for fresh eating and processing pay attention to the color of potato skin and potato pulp, the color is a necessary basis for judging the grade of the potatoes, and the importance degree of the potatoes is prior to the block weight, the defect rate and the like. The market of each consumption area has different preferences for the color of the potato skin and the potato meat, and different types of consumer enterprises also have different color preferences. 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 if the color is measured by a precise instrument, the problems of overhigh cost and overlow efficiency are caused.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides a quick, scientific and standard color comparison card manufacturing method and an evaluation method for evaluating the color of potato skins and potato flesh.
(II) technical scheme
In order to achieve the purpose, the invention provides the following technical scheme: a method for manufacturing a color comparison card for evaluating the color of potato skin and potato flesh comprises the following steps:
step 1, potato block sample collection:
extracting a plurality of potato blocks of the first 30 main planting varieties from a plurality of planting lands, wherein the potato blocks are complete, uniform and flawless, 1-3 potato blocks are taken from each land, and collected potato block samples are stored in a dark place and in a windproof manner;
step 2, image acquisition
Collecting the obtained potato block samples, placing the potato block samples on object placing tables in a darkroom one by one, arranging 3 light supplementing light sources with the color reduction degree of more than 95% around the object placing tables, irradiating the object placing tables downwards by 45 degrees from the left and the right respectively, and irradiating the object placing tables downwards by one table at the top; the color temperature is kept to 5500K; carrying out white balance correction by a camera through an international standard color card, and then shooting photos of original potato skins, cleaned and dried potato skins and slit potato meat;
step 3, image preprocessing
Accurately extracting the potato block outline by the collected potato chip photo through a Canny edge detection algorithm and an outline extraction algorithm, removing the interference of non-potato block parts in the image, and reserving a required image area;
step 4, manufacturing a color comparison card
Step 4-1, performing DBSCAN clustering on the required pixels of each image preprocessed in the step 3 in a three-dimensional color space, and recording the center color of each cluster of each image and the percentage of the number of the pixels contained in the cluster to the total number of the pixels;
step 4-2, constructing 1024 pixels according to the percentage of the pixels of each cluster in the same proportion for the cluster color of each image, wherein the 6000 images account for 6144000 (6000 pixels 1024), carrying out DBSCAN clustering and K-means + + clustering on the pixel set in the three-dimensional color space again, wherein the clustering standard is the same as that of the pixels of the single image, and finally obtaining 64 clusters and 64 central colors thereof, namely obtaining a standard color sequence for manufacturing the color card;
and 4-3, printing the sequence colors on a waterproof, wear-resistant and corrosion-resistant material to prepare a color comparison card for grading the colors of the potato skin and the potato meat.
In the step 4-1, the three-dimensional color space is a Lab three-dimensional color space, DBSCAN clustering is performed in the Lab three-dimensional color space, CIELab color difference is taken as distance measurement, epsilon is set to be 3, minpts is set to be 5% of pixel number, and when the maximum distance between two points in a cluster does not exceed 6, the clustering result of the DBSCAN is directly obtained; otherwise, performing K-means + + clustering on the pixels in the cluster again until the inter-class distance is less than 4 or the intra-class distance is less than 6, and recording the center color of each cluster of each image and the percentage of the number of the pixels contained in the cluster to the total number of the pixels;
and 4-2, constructing 1024 pixels according to the percentage of the pixels of each cluster for the cluster color of each image in the same proportion, wherein the total of 6000 images is 6144000 pixels, carrying out DBSCAN clustering and K-means + + clustering on the pixel set in a Lab three-dimensional color space again, wherein the clustering standard is the same as that of the pixels of the single image, and finally obtaining 64 clusters and 64 central colors thereof, namely obtaining a standard color sequence for manufacturing the color card.
The improvement of the invention is that in the step 4-1, the three-dimensional color space is an RGB three-dimensional color space, when DBSCAN clustering is carried out in the RGB three-dimensional color space, an Euclidean distance is adopted as distance measurement, epsilon is set to be 3, minPts is set to be 5% of pixel number, and when the maximum distance between two points in a cluster does not exceed 6, the clustering result of the DBSCAN is directly obtained; otherwise, performing K-means + + clustering on the pixels in the cluster again until the inter-class distance is less than 4 or the intra-class distance is less than 6, and recording the center color of each cluster of each image and the percentage of the number of the pixels contained in the cluster to the total number of the pixels;
and 4-2, constructing 1024 pixels according to the percentage of the pixels of each cluster in the same proportion for the cluster color of each image, wherein the total of 6000 images is 6144000 pixels, carrying out DBSCAN clustering and K-means + + clustering on the pixel set in the RGB three-dimensional color space again, wherein the clustering standard is the same as that of the pixels of the single image, and finally obtaining 64 clusters and 64 central colors thereof, namely obtaining a standard color sequence for manufacturing the color card.
In the improvement of the invention, in the step 1, the variety is determined by gene sequencing.
The invention has the improvement that the quantitative standard is made for the reflecting rate of a darkroom.
The improvement of the invention comprises the step 4-4, numbering JY-P21-01 to JY-P21-64 for each color according to the sequence from light to dark from the color sequence obtained in the step 4-2, printing each color block on a color comparison card from top to bottom, and marking the number of the color block at the lower left corner of the color block to represent the color grade.
The improvement of the invention is that the total number of samples in the step 1 is not less than 2000, and 1000 different plots of 30 main stream varieties are required.
The invention improves that at least three pictures are taken for each sample, including original potato skins, dried potato skins after washing and potato meat after longitudinal cutting.
The improvement of the invention is that the environment for shooting the sample in the step 2 must meet the requirements of a darkroom, the color reduction degree of a light supplement light source is not less than 95 percent, and the light temperature is kept between 5400K and 5600K.
The invention further provides a method for evaluating the color of potato skins and potato flesh, which is characterized in that the color grade of a sample to be tested is judged by comparing the sample to be tested with the color card of any one of claims 1-10.
(III) advantageous effects
Compared with the prior art, the invention provides the colorimetric card manufacturing method and the evaluation method for evaluating the color of the potato skin and the potato pulp, and the colorimetric card manufacturing method and the evaluation method have the following beneficial effects:
the color comparison card is simple to manufacture and operate, the color comparison card is preprocessed after the sample images of different varieties are collected, and the color comparison card is manufactured based on a CIELab color difference distance clustering algorithm, so that the accuracy rate is high, and the speed is high; the manufactured color comparison card has good feasibility and stability, the identification accuracy of the color comparison card is high, and the color grade of the potato skin and the potato flesh can be scientifically and quickly identified; can provide basis for the standardization of the commercial potatoes, has important practical significance for promoting the standardization and normalization of the commercial potato circulation field, and also can provide reference basis for the relevant color identification research of other products.
Drawings
FIG. 1 is a schematic representation of an original potato skin image of the present invention;
FIG. 2 is a schematic representation of a slit potato meat image of the present invention;
FIG. 3 is a diagram illustrating the image preprocessing result according to embodiment 1 of the present invention;
FIG. 4 is a schematic diagram of a process for making a color chart according to embodiment 1 of the present invention;
FIG. 5 is a schematic view of a numbered color chart according to example 1 of the present invention;
FIG. 6 is a schematic representation of a color chart prepared according to example 1 of the present invention;
fig. 7 is a schematic diagram of an RGB color chart prepared in example 2 of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
Referring to fig. 1-4 and fig. 5-6, a method for making a color chart for evaluating the color of potato skin and meat comprises the following steps:
step 1, potato block sample collection:
in 2020, from 1 day in 9 months to 15 days in 9 months, the total number of the potato blocks of the first 30 main planting varieties is 1000, the potato blocks are complete, uniform and flawless (no diseases, insect pests, blue heads, mechanical injuries and the like), the number proportion of the potato blocks of each variety is the same as the proportion of the planting area of the potato blocks, and the variety selection is ensured to be correct by inquiring features such as planting households, flower shape, flower color and leaflet number. And taking 1000 cellaring potatoes in the same batch for 10 months, 15-10 months and 30 days. The harvested potato varieties are shown in table 1.
TABLE 1 sample overlay of potato varieties
And (4) keeping the collected potato blocks in dark and wind.
Step 2, image acquisition
Collecting the obtained potato block samples, placing the potato block samples on object placing tables in a darkroom one by one, arranging 3 light supplementing light sources with the color reduction degree of more than 95% around the object placing tables, irradiating the object placing tables downwards by 45 degrees from the left and the right respectively, and irradiating the object placing tables downwards by one table at the top; the color temperature is kept to 5500K; and (3) carrying out white balance correction by using a single lens reflex through an international standard color card Pantong color card, and then shooting photos of original potato skins, cleaned and dried potato skins and longitudinally cut potato pulp. The total number of images was 6000 (2000 blocks by 3).
Step 3, image preprocessing
And accurately extracting the potato block outline from each collected image through a Canny edge detection algorithm and an outline extraction algorithm, and removing irrelevant interference. Only the pixels inside the outline of the potato in the image are retained, the pixels being represented in Lab color space. Since the RGB color space is not a uniform color space, and the color difference obtained according to the RGB space distance does not completely conform to the visual color difference of human, the Lab color space of CIE (International Commission on illumination) is used to represent the pixels and calculate the color difference.
Step 4, manufacturing a color comparison card
Step 4-1, performing DBSCAN clustering on the required pixels of each image preprocessed in the step 3 in Lab three-dimensional color space, and taking CIELab color difference as
Measuring the distance, wherein epsilon is set to be 3, minPts is set to be 5% of pixel number, and when the maximum distance between two points in a cluster does not exceed 6, directly taking the clustering result of DBSCAN; otherwise, performing K-means + + clustering on the pixels in the cluster again until the inter-class distances are all lower than 4 or the intra-class distances are all lower than 6. The center color of each cluster of each image and the percentage of the number of pixels contained in the cluster to the total number of pixels are recorded.
And 4-2, constructing 1024 pixels according to the percentage of the pixels of each cluster for the cluster color of each image, wherein the 6000 images account for 6144000 (6000 pixels 1024), carrying out DBSCAN clustering and K-means + + clustering on the pixel set in the Lab three-dimensional color space again, wherein the clustering standard is the same as that of the pixels of the single image, and finally obtaining 64 clusters and 64 central colors thereof, namely obtaining the standard color sequence for manufacturing the color card.
And 4-3, printing the sequence colors on a waterproof, wear-resistant and corrosion-resistant material to prepare a color comparison card for grading the colors of the potato skin and the potato meat.
Further, the method also comprises a step 4-4 of numbering JY-P21-01 to JY-P21-64 colors from light to dark in the color sequence obtained in the step 4-2, printing each color block on a color comparison card from top to bottom, and marking the number of the color block at the lower left corner of the color block to represent the color grade.
The invention also provides aEvaluation ofThe method for determining the color grade of the potato skin and the potato flesh comprises the steps of comparing a potato sample to be determined with the color comparison card, and judging the color grade of the sample to be determined, wherein for example, the color grade of the potato sample is JY-P21-03 when the color grade of the potato sample is the same as the color grade of JY-P21-03 of the color comparison card.
Example 2
With reference to the attached figures 1-7
The difference from the example 1 lies in the step 4, which is specifically as follows:
step 4-1, the clustering algorithm is based on the RGB color space when the color comparison card is manufactured, and the Euclidean distance is adopted when DBSCAN clustering is carried out in the RGB color space
For distance measurement, epsilon is set to be 3, minPts is set to be 5% of pixel number, and when the maximum distance between two points in a cluster does not exceed 6, the clustering result of DBSCAN is directly obtained; otherwise, performing K-means + + clustering on the pixels in the cluster again until the inter-class distances are all lower than 4 or the intra-class distances are all lower than 6. The center color of each cluster of each image and the percentage of the number of pixels contained in the cluster to the total number of pixels are recorded. And then, constructing 1024 pixels according to the percentage of the pixels of each cluster in the same proportion for the cluster color of each image, wherein the 6000 images account for 6144000 (6000 x 1024) pixels in total, carrying out DBSCAN clustering and K-means + + clustering on the pixel set in an RGB three-dimensional color space again, wherein the clustering standard is the same as that of the pixels of the single image, and finally obtaining 64 clusters and 64 central colors thereof, namely obtaining a standard color sequence for manufacturing the color card.
The accuracy of the colorimetric card is verified by combining an RGB color space with a sensory experiment:
(1) Algorithm validation
Because the color card using scene depends on the human eye to observe the approximation degree of the colors of the color blocks of the contrast sample and the color card, the identification degree of the colors by the human eye vision is used as a comparison standard, namely the CIELab color difference is used as a comparison standard. And clustering the obtained 64 colors, and calculating the CIELab color difference between each color and the adjacent color. For a color sequence obtained based on an RGB color space, RGB needs to be converted into an approximate Lab value with the color temperature of 5000K-5500K, and then the color difference is calculated. Comparing the color difference value between each adjacent color of the Lab color space clustering result with the color difference value between each adjacent color of the RGB color space clustering result, wherein the color difference value between each adjacent color of the Lab color space clustering result is more than 4 by 100 percent, namely, the difference between the two colors can be identified by human eyes; and 62.5% of color difference values between adjacent colors of the RGB color space clustering result are less than 4, namely, the difference between two colors is difficult to be identified by human vision. As a color chart for comparison based on human visual sense, 62.5% of the clustering results of the RGB color space are highly likely to cause color level misjudgment. See table 2, the color sequence obtained with the two color spaces, each color being contrasted with the color difference of the previous one.
TABLE 2 color difference between Lab and the first 16 adjacent colors of a color chart made from RGB color space
(2) Comparison of sensory tests
5 persons of professional potato collection and storage agencies and merchants are selected, the working years are not less than 6 years, the color is colorless and blind, the variety and the color of the potatoes are rich in experience, and the qualified products can be effectively selected for potato demand parties. Then, randomly extracting 50 potato tuber samples from each group, and extracting 3 groups for color grading test, wherein the 3 groups are respectively an original potato skin color group, a washed potato skin color group and a potato pulp color group, each sample is provided with a number when being photographed, and the corresponding preferred Lab and RGB color values of the samples are also corresponding to the same number. The test person first evaluated the color grade of potato using Lab color card for 3 groups of potato tubers, and after 10 minutes, evaluated the color grade of potato again using RGB color card for 3 groups of potatoes in a disordered order. The result of the accuracy sensory verification is that the judgment accuracy of the Lab colorimetric card is 98 percent, and the judgment accuracy of the RGB colorimetric card is 62 percent.
(3) Discussion of results
After the color comparison cards manufactured based on the Lab color space and the RGB color space are subjected to algorithm verification and sensory verification, the adjacent color identification degree and the human eye identification accuracy of the color comparison cards are obviously higher than those of the color comparison cards manufactured based on the RGB color space, so that the color comparison cards manufactured based on the Lab color space have good stability and feasibility, and are more suitable for quickly distinguishing the colors of potatoes.
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.
Claims (9)
1. A method for manufacturing a color comparison card for evaluating the color of potato skins and potato flesh is characterized by comprising the following steps:
step 1, potato block sample collection:
extracting more than 30 main planting varieties of potato blocks from a plurality of planting lands, wherein the potato blocks are complete, uniform and flawless, 1-3 potato blocks are taken from each land, and collected potato block samples are kept in a dark place and protected from wind;
step 2, image acquisition
Collecting potato block samples, placing the potato block samples on object placing tables in a darkroom one by one, arranging 3 light supplementing light sources with color reduction degree of more than 95% around the object placing tables, irradiating the object placing tables downwards at 45 degrees from left to right, and irradiating the object placing tables downwards at the top; the color temperature is kept to 5500K; carrying out white balance correction by a camera through a Pantong standard color card, and then shooting photos of original potato skins, cleaned and dried potato skins and slit potato meat;
step 3, image preprocessing
Accurately extracting potato block outlines from the acquired potato chip photos through a Canny edge detection algorithm and an outline extraction algorithm, removing interference of non-potato block parts in images, and reserving required image areas;
step 4, manufacturing a color comparison card
Step 4-1, performing DBSCAN clustering on the required pixels of each image preprocessed in the step 3 in a three-dimensional color space, performing K-means + + clustering again in the clusters as required, and recording the center color of each cluster of each image and the percentage of the number of pixels contained in the cluster to the total number of pixels;
step 4-2, constructing 1024 pixels according to the percentage of the pixels of each cluster in the same proportion for the cluster color of each image, wherein the 6000 images account for 6144000 (6000 pixels 1024), carrying out DBSCAN clustering and K-means + + clustering on the pixel set in the three-dimensional color space again, wherein the clustering standard is the same as that of the pixels of the single image, and finally obtaining 64 clusters and 64 central colors thereof, namely obtaining a standard color sequence for manufacturing the color card;
4-3, printing the sequence colors on a waterproof, wear-resistant and corrosion-resistant material to prepare a color comparison card for grading the colors of the potato skin and the potato meat;
in the step 4-1, the three-dimensional color space is a Lab three-dimensional color space, DBSCAN clustering is performed in the Lab three-dimensional color space, and CIELab color difference is used as
Measuring the distance, wherein epsilon is set to be 3, minPts is set to be 5% of pixel number, and when the maximum distance between two points in a cluster does not exceed 6, directly taking the clustering result of DBSCAN; otherwise, performing K-means + + clustering on the pixels in the cluster again until the inter-class distance is less than 4 or the intra-class distance is less than 6, and recording the center color of each cluster of each image and the percentage of the number of the pixels contained in the cluster to the total number of the pixels;
and 4-2, constructing 1024 pixels according to the same proportion of the percentage of the pixels of each cluster for the cluster color of each image, wherein the total of 6000 images is 6144000 pixels, carrying out DBSCAN clustering and K-means + + clustering on the pixel set in a Lab three-dimensional color space again, wherein the clustering standard is the same as that of the pixels of the single image, and finally obtaining 64 clusters and 64 central colors thereof, namely obtaining a standard color sequence for manufacturing the color card.
2. The method for making a color chart for evaluating the color of potato skin and potato flesh of claim 1, wherein in step 4-1, the three-dimensional color space is RGB three-dimensional color space, and the euclidean distance is used for DBSCAN clustering in RGB three-dimensional color space
For distance measurement, epsilon is set to be 3, minPts is set to be 5% of pixel number, and when the maximum distance between two points in a cluster does not exceed 6, the clustering result of DBSCAN is directly taken; otherwise, performing K-means + + clustering on the pixels in the cluster again until the inter-class distance is less than 4 or the intra-class distance is less than 6, and recording the center color of each cluster of each image and the percentage of the number of the pixels contained in the cluster to the total number of the pixels;
and 4-2, constructing 1024 pixels according to the percentage of the pixels of each cluster in the same proportion for the cluster color of each image, wherein the total of 6000 images is 6144000 pixels, carrying out DBSCAN clustering and K-means + + clustering on the pixel set in the RGB three-dimensional color space again, wherein the clustering standard is the same as that of the pixels of the single image, and finally obtaining 64 clusters and 64 central colors thereof, namely obtaining a standard color sequence for manufacturing the color card.
3. The method for making the color chart for evaluating the color of the potato skin and the potato pulp as claimed in claim 1, wherein in the step 1, the variety is determined by gene sequencing.
4. The method for making the color comparison card used for evaluating the color of the potato skin and the potato flesh as claimed in claim 1, wherein a quantitative standard is made for the light reflectance in a dark room.
5. The method for manufacturing the colorimetric card for evaluating the color of potato skins and potato flesh according to claim 1, further comprising a step 4-4 of numbering JY-P21-01 to JY-P21-64 of each color block from top to bottom according to the color sequence obtained in the step 4-2 from light to dark, printing each color block on the colorimetric card from top to bottom, and marking the number on the lower left corner of each color block to represent the color grade.
6. The method of claim 1, wherein the total number of samples in step 1 is not less than 2000, and the samples must be from 1000 different plots of 30 major varieties.
7. The method for making the color shade card for evaluating the color of potato skins and potato pulp as claimed in claim 1, wherein at least three photographs are taken of each sample, comprising raw potato skins, dried potato skins after washing, and slit potato pulp.
8. The method for making the colorimetric card for evaluating the color of the potato peels and the potato pulp as claimed in claim 1, wherein the environment for shooting the sample in the step 2 must meet the requirements of a dark room, a light supplement light source color reduction degree of not less than 95% and a light temperature of 5400K-5600K.
9. A method for evaluating the color of potato skins and potatoes, characterized in that the color grade of a sample to be tested is judged by comparing the sample to be tested with a color chart according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110182727.6A CN113484250B (en) | 2021-02-10 | 2021-02-10 | Method for manufacturing colorimetric card for evaluating color of potato skins and potato flesh and evaluation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110182727.6A CN113484250B (en) | 2021-02-10 | 2021-02-10 | Method for manufacturing colorimetric card for evaluating color of potato skins and potato flesh and evaluation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113484250A CN113484250A (en) | 2021-10-08 |
| CN113484250B true CN113484250B (en) | 2023-01-31 |
Family
ID=77933319
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110182727.6A Active CN113484250B (en) | 2021-02-10 | 2021-02-10 | Method for manufacturing colorimetric card for evaluating color of potato skins and potato flesh and evaluation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113484250B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114166761A (en) * | 2021-12-03 | 2022-03-11 | 郑其向 | Colorimetric card for preventing and controlling plant diseases and predicting plant diseases |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102353632A (en) * | 2011-06-28 | 2012-02-15 | 上海谷绿旺农业投资管理有限公司 | Color atla for determining pork freshness and manufacturing method thereof |
| CN103394472A (en) * | 2013-07-04 | 2013-11-20 | 中国农业大学 | Method for detecting and grading greening potatoes based on machine vision |
| CN106228612A (en) * | 2016-07-11 | 2016-12-14 | 浙江大学 | Utilize the method and apparatus that System of Rotating about Fixed Axis profile diagram rebuilds Rhizoma Solani tuber osi three-dimensional surface |
| CN106296696A (en) * | 2016-08-12 | 2017-01-04 | 深圳市中识创新科技有限公司 | The conforming processing method of color of image and image capture device |
| CN208922290U (en) * | 2018-08-03 | 2019-05-31 | 中国农业大学 | Potato image collecting device based on RGB-D camera |
| CN110646416A (en) * | 2019-09-27 | 2020-01-03 | 渤海大学 | Colorimetric card for evaluating smoked chicken quality and application |
| CN111272682A (en) * | 2020-03-03 | 2020-06-12 | 渤海大学 | Color comparison card for evaluating freshness of sugar-smoked meat product and preparation method and application thereof |
| CN111537450A (en) * | 2020-06-18 | 2020-08-14 | 中国农业科学院蔬菜花卉研究所 | Method for identifying browning resistance of potato resources |
| CN111798526A (en) * | 2020-01-10 | 2020-10-20 | 中国人民解放军国防科技大学 | Method and system for rapidly extracting dominant colors of color images based on clustering space mapping |
-
2021
- 2021-02-10 CN CN202110182727.6A patent/CN113484250B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102353632A (en) * | 2011-06-28 | 2012-02-15 | 上海谷绿旺农业投资管理有限公司 | Color atla for determining pork freshness and manufacturing method thereof |
| CN103394472A (en) * | 2013-07-04 | 2013-11-20 | 中国农业大学 | Method for detecting and grading greening potatoes based on machine vision |
| CN106228612A (en) * | 2016-07-11 | 2016-12-14 | 浙江大学 | Utilize the method and apparatus that System of Rotating about Fixed Axis profile diagram rebuilds Rhizoma Solani tuber osi three-dimensional surface |
| CN106296696A (en) * | 2016-08-12 | 2017-01-04 | 深圳市中识创新科技有限公司 | The conforming processing method of color of image and image capture device |
| CN208922290U (en) * | 2018-08-03 | 2019-05-31 | 中国农业大学 | Potato image collecting device based on RGB-D camera |
| CN110646416A (en) * | 2019-09-27 | 2020-01-03 | 渤海大学 | Colorimetric card for evaluating smoked chicken quality and application |
| CN111798526A (en) * | 2020-01-10 | 2020-10-20 | 中国人民解放军国防科技大学 | Method and system for rapidly extracting dominant colors of color images based on clustering space mapping |
| CN111272682A (en) * | 2020-03-03 | 2020-06-12 | 渤海大学 | Color comparison card for evaluating freshness of sugar-smoked meat product and preparation method and application thereof |
| CN111537450A (en) * | 2020-06-18 | 2020-08-14 | 中国农业科学院蔬菜花卉研究所 | Method for identifying browning resistance of potato resources |
Non-Patent Citations (6)
| Title |
|---|
| 10个马铃薯品种在川中丘陵区冬作的品质综合评价与分类;高佳等;《食品工业科技》;20191017(第07期);全文 * |
| Image Segmentation Using K-Means Color Quantization and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) for Hotspot Detection in Photovoltaic Modules;Genevieve C. Ngo and Erees Queen B. Macabebe，;《2016 IEEE Region 10 Conference (TENCON) — Proceedings of the International Conference》;20170209;全文 * |
| Real-Time Superpixel Segmentation by DBSCAN Clustering Algorithm;Jianbing Shen, Xiaopeng Hao, Zhiyuan Liang,Yu Liu;《IEEE TRANSACTIONS ON IMAGE PROCESSING》;20161231;第25卷(第12期);全文 * |
| Towards A Hybrid Approach of K-means and Density-Based Spatial Clustering of Applications with Noise for Image Segmentation;Chun Guan、Kevin Kam Fung Yuen、Qi Chen;《Conference on Internet of Things and IEEE Green Computing and Communications and IEEE Cyber, Physical and Social Computing and IEEE Smart Data》;20180201;第396页第07段、第397页第01-04段 * |
| 基于改进k-means算法的猕猴桃叶部病斑分割方法;张会敏等;《电脑知识与技术》;20200905(第25期);全文 * |
| 基于色度域划分的马铃薯绿皮检测方法;虞晓娟等;《农业工程学报》;20090930;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113484250A (en) | 2021-10-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Momin et al. | Geometry-based mass grading of mango fruits using image processing | |
| Mahendran et al. | Application of computer vision technique on sorting and grading of fruits and vegetables | |
| CN109001407B (en) | Lake water quality analysis system | |
| CN106525732B (en) | Rapid nondestructive detection method for internal and external quality of apple based on hyperspectral imaging technology | |
| CN103076288B (en) | A kind of flesh of fish self-grading device based on computer vision and method | |
| Ishak et al. | Image based modeling for oil palm fruit maturity prediction | |
| WO2009045035A1 (en) | White and brown rice appearance characteristics measurement system and method | |
| WO2007068056A1 (en) | Stain assessment for cereal grains | |
| CN103808263A (en) | High-throughput detection method for grain form parameters | |
| CN108613989A (en) | A kind of detection method of paddy unsound grain | |
| CN113484250B (en) | Method for manufacturing colorimetric card for evaluating color of potato skins and potato flesh and evaluation method | |
| Yin et al. | Detection of early bruises on loquat using hyperspectral imaging technology coupled with band ratio and improved Otsu method | |
| Singh et al. | Image analysis methods for real-time color grading of stonefruit | |
| Torres et al. | Setting up a methodology to distinguish between green oranges and leaves using hyperspectral imaging | |
| Motonaga et al. | A method of making digital fruit color charts for cultivation management and quality control | |
| Bindlish et al. | Assessment of peanut pod maturity | |
| Fu et al. | Color based classification for berries of Japanese Blue Honeysuckle | |
| Puchalski et al. | Image analysis for apple defect detection | |
| CN112837301A (en) | Method for judging color and color impurity degree of dry tea leaves | |
| Yumang et al. | Computer vision-based non-invasive sweetness assessment of mangifera indica l. fruit using k-means clustering and cnn | |
| Mohamed et al. | Strawberry ripeness calibrated 2D colour lookup table for field-deployable computer vision | |
| Wongruen | Comparative study estimating and detecting chalkiness of Thai hom Mali Brown rice grains using image analysis and four segmentation techniques | |
| Hasankhani et al. | Qualitative sorting of potatoes by color analysis in machine vision system | |
| Mendoza et al. | Predicting ripening stages of bananas (Musa cavendish) by computer vision | |
| Jian et al. | Identification and grading of tea using computer vision |
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 |