CN112818810A - Kumquat intelligent sorting method and device based on big data - Google Patents
Kumquat intelligent sorting method and device based on big data Download PDFInfo
- Publication number
- CN112818810A CN112818810A CN202110110742.XA CN202110110742A CN112818810A CN 112818810 A CN112818810 A CN 112818810A CN 202110110742 A CN202110110742 A CN 202110110742A CN 112818810 A CN112818810 A CN 112818810A
- Authority
- CN
- China
- Prior art keywords
- kumquat
- information
- obtaining
- kumquats
- image information
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method and a device for intelligently sorting kumquats based on big data, wherein the method comprises the following steps: obtaining damage degree information of the first kumquat according to the first image information; obtaining color difference information of the first kumquat and the Nth kumquat according to the first image information and the second image information; inputting the damage degree information and the color difference information of the first kumquat into a kumquat sorting model to obtain first output information; obtaining the size information of the first kumquat according to the first image information and the second image information; judging whether the size information of the first kumquat is within the preset size threshold value or not, and obtaining a first judgment result; and determining whether to continuously sort the first output information according to the first judgment result. The technical problem of prior art exist kumquat letter sorting inefficiency, the error is big and lack the specialty, lead to letter sorting quality unqualified is solved.
Description
Technical Field
The invention relates to the field of sorting identification, in particular to a kumquat intelligent sorting method and device based on big data.
Background
Kumquat is golden in skin color, thin in skin, tender in meat, fragrant and sweet in juice, and is characterized in that peel and pulp can be eaten together, kumquat contains special volatile oil, kumquat glycoside and other special substances, has pleasant fragrance, is a distinctive fruit with high nutritional value, and currently, kumquat sorting is mainly carried out by naked eyes of people or manual weighing and weight sensing.
However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the inventors of the present application find that the above-mentioned technology has at least the following technical problems:
the technical problems that in the prior art, kumquat sorting efficiency is low, errors are large, and the specialty is lacked, so that sorting quality is unqualified are solved.
Disclosure of Invention
The embodiment of the application provides an intelligent kumquat sorting method and device based on big data, solves the technical problems that in the prior art, kumquats are low in sorting efficiency, large in error and lack of specialty, so that sorting quality is unqualified, achieves the effect of shortening sorting time, improves sorting efficiency, and further enables kumquats to be sorted more conveniently and quickly, and the quality of the kumquats reaches the standard.
In view of the above problems, the present application provides an intelligent kumquat sorting method and apparatus based on big data.
In a first aspect, an embodiment of the present application provides a kumquat intelligent sorting method based on big data, where the method includes: obtaining first image information through the first image acquisition device, wherein the first image information comprises image information of a first kumquat; obtaining second image information through the second image acquisition device, wherein the second image information comprises image information of a first amount of kumquats, and the first amount of kumquats comprises the first kumquats and the Nth kumquats; obtaining damage degree information of the first kumquat according to the first image information; obtaining color difference information of the first kumquat and the Nth kumquat according to the first image information and the second image information; inputting the damage information of the first kumquat and the color difference information of the first kumquat and the Nth kumquat into a kumquat sorting model to obtain first output information, wherein the first output information comprises a first result and a second result, the first result is that the first kumquat is removed from the first amount of kumquats, and the second result is that the first kumquats are kept in the first amount of kumquats; obtaining the size information of the first kumquat according to the first image information and the second image information; obtaining a predetermined size threshold; judging whether the size information of the first kumquat is within the preset size threshold value or not, and obtaining a first judgment result; and determining whether to continuously sort the first output information according to the first judgment result.
On the other hand, this application still provides a kumquat intelligence sorting device based on big data, the device includes: the image processing device comprises a first obtaining unit, a second obtaining unit and a processing unit, wherein the first obtaining unit is used for obtaining first image information through a first image acquisition device, and the first image information comprises image information of a first kumquat; a second obtaining unit, configured to obtain second image information through a second image acquisition device, where the second image information includes image information of a first amount of kumquats, and the first amount of kumquats includes the first kumquat and an nth kumquat; a third obtaining unit, configured to obtain damage information of the first kumquat according to the first image information; a fourth obtaining unit, configured to obtain color difference information of the first kumquat and the nth kumquat according to the first image information and the second image information; a first input unit, configured to input information on a breakage degree of the first kumquat and information on a color difference between the first kumquat and the nth kumquat into a kumquat sorting model to obtain first output information, where the first output information includes a first result and a second result, the first result is to remove the first kumquat from the first amount of kumquats, and the second result is to retain the first kumquat in the first amount of kumquats; a fifth obtaining unit, configured to obtain size information of the first kumquat according to the first image information and the second image information; a sixth obtaining unit configured to obtain a predetermined size threshold; the first judgment unit is used for judging whether the size information of the first kumquat is within the preset size threshold value or not to obtain a first judgment result; a first determining unit, configured to determine whether to continue sorting the first output information according to the first determination result.
In a third aspect, the present invention provides a big data-based intelligent kumquat sorting apparatus, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method according to the first aspect when executing the program.
One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:
the damage degree information of the first kumquat is obtained according to the first image information; obtaining color difference information of the first kumquat and the Nth kumquat according to the first image information and the second image information; inputting the damage degree information and the color difference information of the first kumquat into a kumquat sorting model to obtain first output information; obtaining the size information of the first kumquat according to the first image information and the second image information; judging whether the size information of the first kumquat is within the preset size threshold value or not, and obtaining a first judgment result; and determining whether to continuously sort the first output information according to the first judgment result so as to reduce sorting time, improve sorting efficiency and further achieve the technical effects of more convenient and faster kumquat sorting and standard quality.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
Fig. 1 is a schematic flow chart of an intelligent kumquat sorting method based on big data according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of an intelligent kumquat sorting device based on big data according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.
Description of reference numerals: a first obtaining unit 11, a second obtaining unit 12, a third obtaining unit 13, a fourth obtaining unit 14, a first input unit 15, a fifth obtaining unit 16, a sixth obtaining unit 17, a first judging unit 18, a first determining unit 19, a bus 300, a receiver 301, a processor 302, a transmitter 303, a memory 304, and a bus interface 306.
Detailed Description
The embodiment of the application provides an intelligent kumquat sorting method and device based on big data, solves the technical problems that in the prior art, kumquats are low in sorting efficiency, large in error and lack of specialty, so that sorting quality is unqualified, achieves the effect of shortening sorting time, improves sorting efficiency, and further enables kumquats to be sorted more conveniently and quickly, and the quality of the kumquats reaches the standard. Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are merely some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein.
Summary of the application
Kumquat is golden in skin color, thin in skin, tender in meat, fragrant and sweet in juice, and is characterized in that peel and pulp can be eaten together, kumquat contains special volatile oil, kumquat glycoside and other special substances, has pleasant fragrance, is a distinctive fruit with high nutritional value, and currently, kumquat sorting is mainly carried out by naked eyes of people or manual weighing and weight sensing. However, the prior art has the technical problems that kumquat sorting efficiency is low, errors are large, and the specialty is lacked, so that sorting quality is unqualified.
In view of the above technical problems, the technical solution provided by the present application has the following general idea:
the embodiment of the application provides a kumquat intelligent sorting method based on big data, which comprises the following steps: obtaining first image information through the first image acquisition device, wherein the first image information comprises image information of a first kumquat; obtaining second image information through the second image acquisition device, wherein the second image information comprises image information of a first amount of kumquats, and the first amount of kumquats comprises the first kumquats and the Nth kumquats; obtaining damage degree information of the first kumquat according to the first image information; obtaining color difference information of the first kumquat and the Nth kumquat according to the first image information and the second image information; inputting the damage information of the first kumquat and the color difference information of the first kumquat and the Nth kumquat into a kumquat sorting model to obtain first output information, wherein the first output information comprises a first result and a second result, the first result is that the first kumquat is removed from the first amount of kumquats, and the second result is that the first kumquats are kept in the first amount of kumquats; obtaining the size information of the first kumquat according to the first image information and the second image information; obtaining a predetermined size threshold; judging whether the size information of the first kumquat is within the preset size threshold value or not, and obtaining a first judgment result; and determining whether to continuously sort the first output information according to the first judgment result.
Having thus described the general principles of the present application, various non-limiting embodiments thereof will now be described in detail with reference to the accompanying drawings.
Example one
As shown in fig. 1, an embodiment of the present application provides a kumquat intelligent sorting method based on big data, where the method includes:
step S100: obtaining first image information through the first image acquisition device, wherein the first image information comprises image information of a first kumquat;
step S200: obtaining second image information through the second image acquisition device, wherein the second image information comprises image information of a first amount of kumquats, and the first amount of kumquats comprises the first kumquats and the Nth kumquats;
specifically, the first kumquat is a target sorting object needing to be intelligently sorted, the first image information is the appearance image information of the first kumquat obtained by the first image acquisition device, and includes the image information of the shape, size, color and the like of the first kumquat, the second image information is the appearance image information of the first kumquat obtained by the second image acquisition device, and the first kumquat includes the first kumquat and the nth kumquat, which are the same batch of kumquats.
Step S300: obtaining damage degree information of the first kumquat according to the first image information;
specifically, the information of the damage degree of the first kumquat is information of the damage and rot degree of the first kumquat caused by external factors such as temperature and impact, for example, the surface of the first kumquat is softened and darkened due to collision during picking, storage and transportation of the first kumquat, or the kumquat is damaged due to frostbite caused by temperature.
Step S400: obtaining color difference information of the first kumquat and the Nth kumquat according to the first image information and the second image information;
further, in step S400 of the embodiment of the present application, where the color difference information between the first kumquat and the nth kumquat is obtained according to the first image information and the second image information, the method further includes:
step S410: inputting the first image information and the second image information into a color difference estimation model, wherein the color difference estimation model is obtained by training a plurality of sets of training data, and each set of the plurality of sets of training data comprises: the first image information and the second image information and identification information identifying a color difference between the first kumquat and the Nth kumquat;
step S420: and obtaining a first output result of the color difference estimation model, wherein the first output result comprises the color difference between the first kumquat and the Nth kumquat.
Specifically, the color difference estimation model is a Neural network model, i.e., a Neural network model in machine learning, and a Neural Network (NN) is a complex Neural network system formed by widely connecting a large number of simple processing units (called neurons), which reflects many basic features of human brain functions, and is a highly complex nonlinear dynamical learning system. Neural network models are described based on mathematical models of neurons. Artificial Neural Networks (ANN), is a description of the first-order properties of the human brain system. Briefly, it is a mathematical model. And through training of a large amount of training data, inputting the first image information and the second image information into a neural network model, and outputting the color difference information of the first kumquat and the Nth kumquat.
More specifically, the training process is substantially a supervised learning process, each group of supervised data includes the first image information and the second image information, and identification information identifying a color difference between the first kumquat and the nth kumquat, the first image information and the second image information are input into a neural network model, the neural network model performs continuous self-correction and adjustment according to the identification information for identifying the color difference between the first kumquat and the nth kumquat, and the neural network model finishes the group of supervised learning until an obtained first output result is consistent with the identification information, and then performs the next group of supervised learning; and when the output information of the neural network model reaches the preset accuracy rate/reaches the convergence state, finishing the supervised learning process. Through the supervised learning of the neural network model, the neural network model can process the input information more accurately, so that the output kumquat color difference information is more reasonable and accurate, and the kumquat color difference can be accurately and efficiently analyzed, so that the kumquat color difference model can be established more finely and accurately.
Step S500: inputting the damage information of the first kumquat and the color difference information of the first kumquat and the Nth kumquat into a kumquat sorting model to obtain first output information, wherein the first output information comprises a first result and a second result, the first result is that the first kumquat is removed from the first amount of kumquats, and the second result is that the first kumquats are kept in the first amount of kumquats;
further, in step S500 of this embodiment of the present invention, the step of inputting the damage information of the first kumquat and the color difference information between the first kumquat and the nth kumquat into a kumquat sorting model to obtain first output information further includes:
step S510: taking the damage degree information of the first kumquats as an abscissa;
step S520: constructing a two-dimensional rectangular coordinate system by taking the color difference information of the first kumquat and the Nth kumquat as longitudinal coordinates;
step S530: and constructing a logistic regression line in the two-dimensional rectangular coordinate system according to a logistic regression model, wherein one side of the logistic regression line represents the first result, the other side of the logistic regression line represents the second result, the first result is that the first kumquats are removed from the first amount of kumquats, and the second result is that the first kumquats are kept in the first amount of kumquats.
Specifically, the cumquat sorting model is a logistic regression model, the logistic regression model is a sorting model in machine learning, a coordinate system is constructed by taking the damage information of the first cumquat as an abscissa and the color difference information of the first cumquat and the nth cumquat as an ordinate, a logistic regression line is obtained in the coordinate system based on the logistic regression model, one side of the logistic regression line represents the first result, the first result is that the first cumquat is removed from the first amount of cumquats, the other side of the logistic regression line represents the second result, the second result is that the first cumquat is retained in the first amount of cumquats, the logistic regression line is controlled by a first position and a first angle, and the first position and the first angle of the logistic line can be adjusted according to the damage information of the first cumquat and the color difference information of the first cumquat and the nth cumquat, and then make the logistic regression line is more accurate, and then makes the output result that obtains more accurate, and then reaches and combines kumquat damaged condition and colour difference information, thereby the improvement kumquat of intelligence specialty letter sorting efficiency makes the kumquat letter sorting convenient and fast's technological effect more.
Step S600: obtaining the size information of the first kumquat according to the first image information and the second image information;
further, in an embodiment of the present application, the obtaining the size information of the first kumquat according to the first image information and the second image information, step S600 further includes:
step S610: obtaining first size information of the first kumquat according to the first image information;
step S620: obtaining second size information of the first kumquat and size ratio information of the first kumquat and the Nth kumquat according to the second image information;
step S630: obtaining third size information according to the first size information and the size ratio information;
step S640: obtaining fourth size information according to the second size information and the size ratio information;
step S650: and obtaining the size information of the first kumquat according to the third size information and the fourth size information.
Specifically, the first size information of the first kumquat is the size information of the first kumquat obtained by the first image information, the second size information of the first kumquat is the size information of the first kumquat obtained by the second image information, the size ratio information of the first kumquat to the nth kumquat is the size ratio information of the first kumquat size to the N nth kumquat size in the first batch of kumquats obtained by the second image information, the actual size of the first kumquat needs to be calculated due to different acquisition ratios of the images, the third size information is the actual size of the kumquat of the first image information calculated according to the first size information and the size ratio information, and the fourth size information is the actual size of the kumquat of the second image information calculated according to the second size information and the size ratio information, the actual size information of the first kumquats is obtained through comprehensive analysis of the third size information and the fourth size information, so that the technical effects of calculating the actual size of the kumquats in proportion and improving the identification accuracy of the kumquats are achieved.
Step S700: obtaining a predetermined size threshold;
step S800: judging whether the size information of the first kumquat is within the preset size threshold value or not, and obtaining a first judgment result;
specifically, the predetermined size threshold is a size of a pre-set up standard size range of the first kumquat, and the first determination result is to determine whether the calculated size information of the first kumquat is within the predetermined size threshold, that is, the size of the first kumquat satisfies the predetermined kumquat standard size.
Step S900: and determining whether to continuously sort the first output information according to the first judgment result.
Further, in step S900 according to the embodiment of the present application, determining whether to continue to sort the first output information according to the first determination result, further includes:
step S910: if the first judgment result is that the size information of the first kumquats is within the preset size threshold, keeping the first kumquats in the first amount of kumquats;
step S920: and if the first judgment result is that the size information of the first kumquats is not within the preset size threshold, removing the first kumquats from the first batch of kumquats.
Specifically, if the size of the first kumquat meets the preset kumquat standard size, the first kumquat is kept in the first batch of kumquats, and if the size of the first kumquat does not meet the preset kumquat standard size, the first kumquat is removed from the first batch of kumquats, namely, the kumquats with unqualified sizes are screened out, so that the kumquats with unqualified quality can be intelligently and quickly sorted out in combination with the size of the kumquats, and the technical effect of sorting efficiency of the kumquats is improved.
Further, the embodiment of the present application further includes:
step S1010: obtaining the producing area information of the first kumquat;
step S1020: obtaining historical kumquat quality information of the place of production information through big data statistics, wherein the historical kumquat quality information comprises kumquat size, kumquat color, kumquat sweetness and kumquat water content;
step S1030: obtaining a first characteristic label of the producing area according to the size, color, sweetness and water content of the kumquats;
step S1040: obtaining a first additional sorting criterion according to the first characteristic label;
step S1050: and marking and screening the first amount of kumquats according to the first accessory sorting standard.
Specifically, the information of the production place of the first kumquat is the information of the production place of the first kumquat, for example, the kumquat is mainly produced in the Yangtze river valley and the southern province in China, wherein Fujian Youyxi, Guangxi Wei' an, Jiangxi Tuochuan and Hunan Liuyang are four major production places of the kumquat in China, the planting history of the kumquat in the regions is long, the climate is warm and humid, the soil is fertile, the produced kumquat is golden in color and full in pulp, and the kumquat is very popular both in China and abroad. The big data statistical method is a method for uniformly managing and centrally storing big data resources, meeting the requirements of high concurrency and mass data on high-performance computing capacity and high-capacity storage capacity, providing a large amount of open capacities of data acquisition, data calculation, data storage, data analysis, data visualization and the like, ensuring interconnection and sharing of data among systems, providing a basis for full-chain transparency of data and high intelligence of operation decision, and obtaining historical kumquat quality information of production place information through big data statistics, wherein the historical kumquat quality information comprises kumquat size, kumquat color and luster, kumquat sweetness and kumquat water content. The first specialty label of the place of origin is a kumquat specialty obtained from the kumquat size, kumquat color, kumquat sweetness and kumquat moisture content, such as fujianyuyi: the Youxian kumquat is beautiful and fresh in color, succulent and tender, sweet, sour and delicious, and particularly has the best production quality in the splayed bridge 'three floods', namely the Hongbu brand, the Hongkun and the Hongtian village; guangxi melt an: the Huaian kumquats have the characteristics of multiple tastes and sweetness, crisp mouthfeel and no glycerin taste; jiangxi Tunica: the tunnel cumquats are famous for golden color, thin and sweet big peel, and good in color, fragrance, taste and shape, the fresh fruits are golden color, the shapes are oval or oval like pigeon eggs, and the area, yield and fruit quality of the tunnel cumquats are the first of four golden orange producing places all across the country. The first additional sorting standard is used for sorting out the kumquats with elliptical appearances according to the characteristic sorting standard added to the kumquats by the first characteristic label, and the kumquats with the first batch are marked and screened according to the first additional sorting standard, so that the kumquats which do not meet the characteristic standard are removed, the kumquats with regional characteristics are highlighted, and the technical effect of screening regional special products is maintained.
Further, the embodiment of the present application further includes:
step S1110: obtaining the water content information of the first kumquat;
step S1120: acquiring elastic information of the first kumquat;
step S1130: determining freshness information of the first kumquat according to the water content information and the elasticity information;
step S1140: determining the freshness grade of the first kumquat according to the freshness information;
step S1150: obtaining a first oscillation intensity according to the freshness grade;
step S1160: obtaining a first control instruction according to the first oscillation intensity;
step S1170: and controlling the oscillation intensity of the intelligent kumquat sorting device to be kept at the first oscillation intensity through the first control instruction.
Specifically, the water content information of the first kumquat is the water content in the first kumquat, the water content is fruit weight × water content ratio%, if the water content ratio of the kumquat is 84.7% on average as measured by a reduced pressure drying method according to national standards, then the water content of 100g kumquat is 100 × 84.7% or 84.7g, the water content can be directly detected by a water content meter, the elastic information of the first kumquat is the property that the first kumquat can recover the original size and shape after being deformed, the elastic quantity of the first kumquat can be rapidly measured by an indentation test method, the freshness information of the first kumquat represents the freshness of the first kumquat according to the water content information and the elastic information, the freshness grade of the first kumquat is a freshness range grade divided according to the freshness of the kumquat, and according to the freshness information of the first kumquat, the method comprises the steps of determining the freshness grade of a first kumquat, wherein the first oscillation intensity is according to the freshness grade to the oscillation amplitude of kumquat sorting, the first control instruction is to adopt the kumquat to control sorting, and the oscillation intensity of the intelligent kumquat sorting device is controlled to be kept to be the first oscillation intensity through the first control instruction so as to carry out oscillation sorting on the kumquat, so that the sorting oscillation amplitude is controlled according to the freshness degree of the kumquat in the sorting process, and the breakage rate of the kumquat is further reduced.
Further, in step S300 according to the present application, the obtaining of the breakage information of the first kumquat according to the first image information further includes:
step S310: acquiring the information of the defective area of the first kumquat through the first image information;
step S320: obtaining the appearance information of the first kumquat through the first image information;
step S330: inputting the information of the defect area of the first kumquat and the information of the appearance of the first kumquat into a damage degree estimation model, wherein the damage degree estimation model is obtained by training a plurality of groups of training data, and each group of the plurality of groups of training data comprises: the information of the defect area of the first kumquat, the information of the appearance of the first kumquat and the identification information for identifying the damage degree of the first kumquat;
step S340: obtaining a first output result of the damage estimation model, wherein the first output result comprises the damage of the first kumquat.
Specifically, the information of the defect area of the first kumquat is the size of the skin defect area of the first kumquat caused by mechanical damage, temperature damage and the like, and the information of the shape of the first kumquat is the information of the shape of the first kumquat, and if the shape of the first kumquat is a circle or an ellipse, the shape of the kumquat is squashed due to external factors. The damage degree estimation model is a neural network model, and through training of a large amount of training data, the damaged area information of the first kumquat and the appearance information of the first kumquat are input into the neural network model, so that the damage degree of the first kumquat is output, and through supervision and learning of the neural network model, the neural network model is enabled to process the input information more accurately, so that the damage degree of the first kumquat is output more reasonably and accurately, and further the damage degree identification of the kumquat is enabled to be more accurate, and further the sorting of the kumquats is enabled to be more professional and efficient.
In summary, the method and the device for intelligently sorting kumquats based on big data provided by the embodiment of the application have the following technical effects:
1. the damage degree information of the first kumquat is obtained according to the first image information; obtaining color difference information of the first kumquat and the Nth kumquat according to the first image information and the second image information; inputting the damage degree information and the color difference information of the first kumquat into a kumquat sorting model to obtain first output information; obtaining the size information of the first kumquat according to the first image information and the second image information; judging whether the size information of the first kumquat is within the preset size threshold value or not, and obtaining a first judgment result; and determining whether to continuously sort the first output information according to the first judgment result so as to reduce sorting time, improve sorting efficiency and further achieve the technical effects of more convenient and faster kumquat sorting and standard quality.
2. Because the mode of inputting the first image information and the second image information into the neural network model is adopted, the output kumquat color difference information is more reasonable and accurate, the kumquat color difference is accurately and efficiently analyzed, and the kumquat color difference model is established more finely and accurately.
3. Due to the adoption of the mode of constructing the logistic regression model through the damage degree information of the first kumquats and the color difference information of the first kumquats and the Nth kumquats, the technical effects of combining the logistic regression model and improving the sorting efficiency of the kumquats in an intelligent and professional way so as to enable the kumquats to be sorted more conveniently and quickly are achieved.
Example two
Based on the same inventive concept as the kumquat intelligent sorting method based on big data in the foregoing embodiment, the present invention further provides a kumquat intelligent sorting apparatus based on big data, as shown in fig. 2, the system includes:
a first obtaining unit 11, where the first obtaining unit 11 is configured to obtain first image information through a first image acquisition device, where the first image information includes image information of a first kumquat;
a second obtaining unit 12, where the second obtaining unit 12 is configured to obtain second image information through a second image acquisition device, where the second image information includes image information of a first quantity of kumquats, and the first quantity of kumquats includes the first kumquat and an nth kumquat;
a third obtaining unit 13, where the third obtaining unit 13 is configured to obtain damage information of the first kumquat according to the first image information;
a fourth obtaining unit 14, where the fourth obtaining unit 14 is configured to obtain color difference information of the first kumquat and the nth kumquat according to the first image information and the second image information;
a first input unit 15, where the first input unit 15 is configured to input the information of the damage degree of the first kumquat and the information of the color difference between the first kumquat and the nth kumquat into a kumquat sorting model to obtain first output information, where the first output information includes a first result and a second result, the first result is to remove the first kumquat from the first amount of kumquats, and the second result is to keep the first kumquats in the first amount of kumquats;
a fifth obtaining unit 16, where the fifth obtaining unit 16 is configured to obtain size information of the first kumquat according to the first image information and the second image information;
a sixth obtaining unit 17, the sixth obtaining unit 17 being configured to obtain a predetermined size threshold;
a first judging unit 18, where the first judging unit 18 is configured to judge whether the size information of the first kumquat is within the predetermined size threshold, and obtain a first judgment result;
a first determining unit 19, wherein the first determining unit 19 is configured to determine whether to continue sorting the first output information according to the first judgment result.
Further, the system further comprises:
a second input unit, configured to input the first image information and the second image information into a color difference estimation model, where the color difference estimation model is obtained by training multiple sets of training data, and each of the multiple sets of training data includes: the first image information and the second image information and identification information identifying a color difference between the first kumquat and the Nth kumquat;
a seventh obtaining unit, configured to obtain a first output result of the color difference estimation model, where the first output result includes a color difference between the first kumquat and the nth kumquat.
Further, the system further comprises:
a first determination unit configured to determine damage information of the first kumquat as an abscissa;
a second serving unit, configured to construct a two-dimensional rectangular coordinate system using the color difference information of the first kumquat and the nth kumquat as a vertical coordinate;
a first constructing unit, configured to construct a logistic regression line in the two-dimensional rectangular coordinate system according to a logistic regression model, where one side of the logistic regression line represents the first result, and the other side of the logistic regression line represents the second result, the first result is that the first kumquat is removed from the first amount of kumquats, and the second result is that the first kumquat is retained in the first amount of kumquats.
Further, the system further comprises:
an eighth obtaining unit, configured to obtain first size information of the first kumquat according to the first image information;
a ninth obtaining unit, configured to obtain, according to the second image information, second size information of the first kumquat and size ratio information of the first kumquat and the nth kumquat;
a tenth obtaining unit configured to obtain third size information from the first size information and the size ratio information;
an eleventh obtaining unit configured to obtain fourth size information from the second size information and the size ratio information;
a twelfth obtaining unit, configured to obtain size information of the first kumquat according to the third size information and the fourth size information.
Further, the system further comprises:
a first retaining unit, configured to retain the first kumquat in the first amount of kumquats if the first determination result is that the size information of the first kumquat is within the predetermined size threshold;
a first removing unit, configured to remove the first kumquat from the first amount of kumquats if the first determination result is that the size information of the first kumquat is not within the predetermined size threshold.
Further, the system further comprises:
a thirteenth obtaining unit, configured to obtain information of a place of production of the first kumquat;
a fourteenth obtaining unit, configured to obtain historical kumquat quality information of the place of production information through big data statistics, where the historical kumquat quality information includes kumquat size, kumquat color, kumquat sweetness and kumquat moisture content;
a fifteenth obtaining unit, configured to obtain a first specialty label for the place of production based on the kumquat size, kumquat color, kumquat sweetness and kumquat moisture content;
a sixteenth obtaining unit, configured to obtain a first additional sorting criterion according to the first feature tag;
and the first screening unit is used for performing marking screening on the first amount of kumquats according to the first additional sorting standard.
Further, the system further comprises:
a seventeenth obtaining unit for obtaining water content information of the first kumquat;
an eighteenth obtaining unit configured to obtain a second adjustment parameter when the motion information exceeds the predetermined motion speed threshold;
a second determining unit, configured to determine freshness information of the first kumquat according to the water content information and the elasticity information;
a third determining unit, configured to determine a freshness level of the first kumquat according to the freshness information;
a nineteenth obtaining unit configured to obtain a first oscillation intensity according to the freshness degree level;
a twentieth obtaining unit, configured to obtain a first control instruction according to the first oscillation intensity;
and the first control unit is used for controlling the oscillation intensity of the intelligent kumquat sorting device to be kept at the first oscillation intensity through the first control instruction.
Various changes and specific examples of the kumquat intelligent sorting method based on big data in the first embodiment of fig. 1 are also applicable to the kumquat intelligent sorting device based on big data in the present embodiment, and through the foregoing detailed description of the kumquat intelligent sorting method based on big data, those skilled in the art can clearly know the implementation method of the kumquat intelligent sorting device based on big data in the present embodiment, so for the brevity of the description, detailed descriptions are omitted here.
Exemplary electronic device
The electronic device of the embodiment of the present application is described below with reference to fig. 3.
Fig. 3 illustrates a schematic structural diagram of an electronic device according to an embodiment of the present application.
Based on the inventive concept of the intelligent sorting method for kumquats based on big data in the foregoing embodiments, the present invention further provides an intelligent sorting apparatus for kumquats based on big data, wherein the apparatus has a computer program stored thereon, and the computer program, when executed by a processor, implements the steps of any one of the foregoing intelligent sorting methods for kumquats based on big data.
Where in fig. 3 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 306 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other systems over a transmission medium.
The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
The embodiment of the invention provides a kumquat intelligent sorting method based on big data, which comprises the following steps: obtaining first image information through the first image acquisition device, wherein the first image information comprises image information of a first kumquat; obtaining second image information through the second image acquisition device, wherein the second image information comprises image information of a first amount of kumquats, and the first amount of kumquats comprises the first kumquats and the Nth kumquats; obtaining damage degree information of the first kumquat according to the first image information; obtaining color difference information of the first kumquat and the Nth kumquat according to the first image information and the second image information; inputting the damage information of the first kumquat and the color difference information of the first kumquat and the Nth kumquat into a kumquat sorting model to obtain first output information, wherein the first output information comprises a first result and a second result, the first result is that the first kumquat is removed from the first amount of kumquats, and the second result is that the first kumquats are kept in the first amount of kumquats; obtaining the size information of the first kumquat according to the first image information and the second image information; obtaining a predetermined size threshold; judging whether the size information of the first kumquat is within the preset size threshold value or not, and obtaining a first judgment result; and determining whether to continuously sort the first output information according to the first judgment result. The technical problem of prior art exist kumquat letter sorting inefficiency, the error is big and lack the specialty, lead to sorting unqualified quality is solved, reach and reduce letter sorting time, improve letter sorting efficiency and then make kumquat letter sorting convenient and fast more and quality up to standard's technological effect.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a system for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction system which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (9)
1. The method is applied to an intelligent kumquat sorting device, wherein the device comprises a first image acquisition device and a second image acquisition device, and the method comprises the following steps:
obtaining first image information through the first image acquisition device, wherein the first image information comprises image information of a first kumquat;
obtaining second image information through the second image acquisition device, wherein the second image information comprises image information of a first amount of kumquats, and the first amount of kumquats comprises the first kumquats and the Nth kumquats;
obtaining damage degree information of the first kumquat according to the first image information;
obtaining color difference information of the first kumquat and the Nth kumquat according to the first image information and the second image information;
inputting the damage information of the first kumquat and the color difference information of the first kumquat and the Nth kumquat into a kumquat sorting model to obtain first output information, wherein the first output information comprises a first result and a second result, the first result is that the first kumquat is removed from the first amount of kumquats, and the second result is that the first kumquats are kept in the first amount of kumquats;
obtaining the size information of the first kumquat according to the first image information and the second image information;
obtaining a predetermined size threshold;
judging whether the size information of the first kumquat is within the preset size threshold value or not, and obtaining a first judgment result;
and determining whether to continuously sort the first output information according to the first judgment result.
2. The method of claim 1, wherein the obtaining color difference information for the first kumquat and the Nth kumquat from the first image information and the second image information comprises:
inputting the first image information and the second image information into a color difference estimation model, wherein the color difference estimation model is obtained by training a plurality of sets of training data, and each set of the plurality of sets of training data comprises: the first image information and the second image information and identification information identifying a color difference between the first kumquat and the Nth kumquat;
and obtaining a first output result of the color difference estimation model, wherein the first output result comprises the color difference between the first kumquat and the Nth kumquat.
3. The method of claim 1, wherein the inputting the information about the damage of the first kumquat and the information about the color difference between the first kumquat and the Nth kumquat into a kumquat sorting model to obtain first output information comprises:
taking the damage degree information of the first kumquats as an abscissa;
constructing a two-dimensional rectangular coordinate system by taking the color difference information of the first kumquat and the Nth kumquat as longitudinal coordinates;
and constructing a logistic regression line in the two-dimensional rectangular coordinate system according to a logistic regression model, wherein one side of the logistic regression line represents the first result, the other side of the logistic regression line represents the second result, the first result is that the first kumquats are removed from the first amount of kumquats, and the second result is that the first kumquats are kept in the first amount of kumquats.
4. The method of claim 1, wherein the obtaining the size information of the first kumquat from the first image information and the second image information comprises:
obtaining first size information of the first kumquat according to the first image information;
obtaining second size information of the first kumquat and size ratio information of the first kumquat and the Nth kumquat according to the second image information;
obtaining third size information according to the first size information and the size ratio information;
obtaining fourth size information according to the second size information and the size ratio information;
and obtaining the size information of the first kumquat according to the third size information and the fourth size information.
5. The method of claim 1, wherein the determining whether to continue sorting the first output information according to the first determination comprises:
if the first judgment result is that the size information of the first kumquats is within the preset size threshold, keeping the first kumquats in the first amount of kumquats;
and if the first judgment result is that the size information of the first kumquats is not within the preset size threshold, removing the first kumquats from the first batch of kumquats.
6. The method of claim 1, wherein the method comprises:
obtaining the producing area information of the first kumquat;
obtaining historical kumquat quality information of the place of production information through big data statistics, wherein the historical kumquat quality information comprises kumquat size, kumquat color, kumquat sweetness and kumquat water content;
obtaining a first characteristic label of the producing area according to the size, color, sweetness and water content of the kumquats;
obtaining a first additional sorting criterion according to the first characteristic label;
and performing marking and screening on the first amount of kumquats through the first additional sorting standard.
7. The method of claim 1, wherein the method comprises:
obtaining the water content information of the first kumquat;
acquiring elastic information of the first kumquat;
determining freshness information of the first kumquat according to the water content information and the elasticity information;
determining the freshness grade of the first kumquat according to the freshness information;
obtaining a first oscillation intensity according to the freshness grade;
obtaining a first control instruction according to the first oscillation intensity;
and controlling the oscillation intensity of the intelligent kumquat sorting device to be kept at the first oscillation intensity through the first control instruction.
8. An intelligent kumquat sorting device based on big data, wherein the device comprises:
the image processing device comprises a first obtaining unit, a second obtaining unit and a processing unit, wherein the first obtaining unit is used for obtaining first image information through a first image acquisition device, and the first image information comprises image information of a first kumquat;
a second obtaining unit, configured to obtain second image information through a second image acquisition device, where the second image information includes image information of a first amount of kumquats, and the first amount of kumquats includes the first kumquat and an nth kumquat;
a third obtaining unit, configured to obtain damage information of the first kumquat according to the first image information;
a fourth obtaining unit, configured to obtain color difference information of the first kumquat and the nth kumquat according to the first image information and the second image information;
a first input unit, configured to input information on a breakage degree of the first kumquat and information on a color difference between the first kumquat and the nth kumquat into a kumquat sorting model to obtain first output information, where the first output information includes a first result and a second result, the first result is to remove the first kumquat from the first amount of kumquats, and the second result is to retain the first kumquat in the first amount of kumquats;
a fifth obtaining unit, configured to obtain size information of the first kumquat according to the first image information and the second image information;
a sixth obtaining unit configured to obtain a predetermined size threshold;
the first judgment unit is used for judging whether the size information of the first kumquat is within the preset size threshold value or not to obtain a first judgment result;
a first determining unit, configured to determine whether to continue sorting the first output information according to the first determination result.
9. An intelligent sorting apparatus for kumquats based on big data, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1-7 when executing the program.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110110742.XA CN112818810A (en) | 2021-01-27 | 2021-01-27 | Kumquat intelligent sorting method and device based on big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110110742.XA CN112818810A (en) | 2021-01-27 | 2021-01-27 | Kumquat intelligent sorting method and device based on big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112818810A true CN112818810A (en) | 2021-05-18 |
Family
ID=75859644
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110110742.XA Pending CN112818810A (en) | 2021-01-27 | 2021-01-27 | Kumquat intelligent sorting method and device based on big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112818810A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113680711A (en) * | 2021-10-27 | 2021-11-23 | 南通瑞隆农产品开发有限公司 | Agricultural product sorting method and system based on color gradation display card |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110352660A (en) * | 2019-07-12 | 2019-10-22 | 塔里木大学 | A kind of ginning cotton seed vigor Fast nondestructive evaluation information processing method and device |
CN110490862A (en) * | 2019-08-22 | 2019-11-22 | 联峰钢铁(张家港)有限公司 | A kind of method and device improving continuous casting flaw detection qualification rate |
CN110533032A (en) * | 2019-08-22 | 2019-12-03 | 江苏联峰实业有限公司 | A kind of method and apparatus obtaining high-purity cryogenic steel |
CN110627182A (en) * | 2019-09-24 | 2019-12-31 | 康玄谷(北京)国际生物科技有限公司 | Method and device for obtaining mineral water |
CN112101149A (en) * | 2020-08-31 | 2020-12-18 | 江苏工程职业技术学院 | Building waste classification method and system |
-
2021
- 2021-01-27 CN CN202110110742.XA patent/CN112818810A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110352660A (en) * | 2019-07-12 | 2019-10-22 | 塔里木大学 | A kind of ginning cotton seed vigor Fast nondestructive evaluation information processing method and device |
CN110490862A (en) * | 2019-08-22 | 2019-11-22 | 联峰钢铁(张家港)有限公司 | A kind of method and device improving continuous casting flaw detection qualification rate |
CN110533032A (en) * | 2019-08-22 | 2019-12-03 | 江苏联峰实业有限公司 | A kind of method and apparatus obtaining high-purity cryogenic steel |
CN110627182A (en) * | 2019-09-24 | 2019-12-31 | 康玄谷(北京)国际生物科技有限公司 | Method and device for obtaining mineral water |
CN112101149A (en) * | 2020-08-31 | 2020-12-18 | 江苏工程职业技术学院 | Building waste classification method and system |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113680711A (en) * | 2021-10-27 | 2021-11-23 | 南通瑞隆农产品开发有限公司 | Agricultural product sorting method and system based on color gradation display card |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110352660B (en) | Method and device for processing information of rapid nondestructive testing of vitality of delinted cotton seeds | |
CN107590460B (en) | Face classification method, apparatus and intelligent terminal | |
CN108090508A (en) | A kind of classification based training method, apparatus and storage medium | |
CN108615071A (en) | The method and device of model measurement | |
CN108133391A (en) | Method for Sales Forecast method and server | |
CN103971176B (en) | A kind of citrusfruit high quality harvests the method and system of decision-making | |
CN110472611A (en) | Method, apparatus, electronic equipment and the readable storage medium storing program for executing of character attribute identification | |
CN109800795A (en) | A kind of fruit and vegetable recognition method and system | |
CN112396131A (en) | Papaya shred quality monitoring method and device | |
CN110232445A (en) | A kind of historical relic authenticity identification method of knowledge based distillation | |
CN106778791A (en) | A kind of timber visual identity method based on multiple perceptron | |
CN112818810A (en) | Kumquat intelligent sorting method and device based on big data | |
Herdiyeni et al. | Chilli quality classification using deep learning | |
CN107742132A (en) | Potato detection method of surface flaw based on convolutional neural networks | |
CN113359628B (en) | Control method and device for green tea processing process | |
CN110287207A (en) | A kind of quality of food estimating and measuring method based on density meter | |
CN109711590B (en) | Fishery water quality analysis monitoring method, device and system | |
CN112760756A (en) | Textile process self-adaptive cotton cleaning system based on artificial intelligence | |
CN115330759B (en) | Method and device for calculating distance loss based on Hausdorff distance | |
CN111062511A (en) | Aquaculture disease prediction method and system based on decision tree and neural network | |
CN110580495A (en) | automatic analysis method for leaf area and leaf surface anthracnose lesion number of pear | |
CN106444578B (en) | A kind of fault detection method based on isomery geodesic curve distance SVDD | |
CN113670917B (en) | Analysis method and system for green tea quality | |
CN114972292A (en) | Banana growing period identification method and system based on deep learning | |
CN115330721A (en) | Banana fruit comb plumpness detection method and system based on shape and color information |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210518 |