CN111665215A - Apple maturity detection system and method based on embedded mode - Google Patents
Apple maturity detection system and method based on embedded mode Download PDFInfo
- Publication number
- CN111665215A CN111665215A CN202010452754.6A CN202010452754A CN111665215A CN 111665215 A CN111665215 A CN 111665215A CN 202010452754 A CN202010452754 A CN 202010452754A CN 111665215 A CN111665215 A CN 111665215A
- Authority
- CN
- China
- Prior art keywords
- apple
- maturity
- apple maturity
- data
- embedded
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 80
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000001228 spectrum Methods 0.000 claims abstract description 61
- 230000003595 spectral effect Effects 0.000 claims abstract description 60
- 238000013145 classification model Methods 0.000 claims abstract description 50
- 238000012706 support-vector machine Methods 0.000 claims abstract description 35
- 238000009659 non-destructive testing Methods 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 12
- 238000004458 analytical method Methods 0.000 claims abstract description 9
- 241000220225 Malus Species 0.000 claims description 238
- 238000004422 calculation algorithm Methods 0.000 claims description 60
- 230000002068 genetic effect Effects 0.000 claims description 47
- 239000000523 sample Substances 0.000 claims description 42
- 235000021016 apples Nutrition 0.000 claims description 23
- 238000000513 principal component analysis Methods 0.000 claims description 21
- 229910052736 halogen Inorganic materials 0.000 claims description 17
- 150000002367 halogens Chemical class 0.000 claims description 17
- 238000007635 classification algorithm Methods 0.000 claims description 11
- 238000005457 optimization Methods 0.000 claims description 10
- 239000013598 vector Substances 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 8
- 238000012795 verification Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 238000007667 floating Methods 0.000 claims description 5
- 238000002329 infrared spectrum Methods 0.000 claims description 5
- 230000003993 interaction Effects 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 4
- 238000007621 cluster analysis Methods 0.000 claims description 3
- 238000002474 experimental method Methods 0.000 claims description 3
- 230000035772 mutation Effects 0.000 claims description 3
- 108090000623 proteins and genes Proteins 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 238000000547 structure data Methods 0.000 claims description 3
- 230000001066 destructive effect Effects 0.000 claims 2
- 238000007689 inspection Methods 0.000 claims 2
- 230000006870 function Effects 0.000 description 32
- 238000010586 diagram Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 7
- 230000001976 improved effect Effects 0.000 description 6
- 235000013399 edible fruits Nutrition 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 244000134242 Malus prunifolia Species 0.000 description 2
- 235000005087 Malus prunifolia Nutrition 0.000 description 2
- 235000010724 Wisteria floribunda Nutrition 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 238000004040 coloring Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000000796 flavoring agent Substances 0.000 description 2
- 235000019634 flavors Nutrition 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000002633 protecting effect Effects 0.000 description 2
- 238000012827 research and development Methods 0.000 description 2
- 230000000087 stabilizing effect Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000008093 supporting effect Effects 0.000 description 2
- 238000010146 3D printing Methods 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 1
- 235000011034 Rubus glaucus Nutrition 0.000 description 1
- 244000235659 Rubus idaeus Species 0.000 description 1
- 235000009122 Rubus idaeus Nutrition 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 229910052744 lithium Inorganic materials 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000000275 quality assurance Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000000985 reflectance spectrum Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
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
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
-
- 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
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- 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
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/02—Food
- G01N33/025—Fruits or vegetables
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05B—ELECTRIC HEATING; ELECTRIC LIGHT SOURCES NOT OTHERWISE PROVIDED FOR; CIRCUIT ARRANGEMENTS FOR ELECTRIC LIGHT SOURCES, IN GENERAL
- H05B45/00—Circuit arrangements for operating light-emitting diodes [LED]
- H05B45/30—Driver circuits
- H05B45/32—Pulse-control circuits
- H05B45/325—Pulse-width modulation [PWM]
-
- H—ELECTRICITY
- H05—ELECTRIC TECHNIQUES NOT OTHERWISE PROVIDED FOR
- H05B—ELECTRIC HEATING; ELECTRIC LIGHT SOURCES NOT OTHERWISE PROVIDED FOR; CIRCUIT ARRANGEMENTS FOR ELECTRIC LIGHT SOURCES, IN GENERAL
- H05B45/00—Circuit arrangements for operating light-emitting diodes [LED]
- H05B45/30—Driver circuits
- H05B45/345—Current stabilisation; Maintaining constant current
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2201/00—Features of devices classified in G01N21/00
- G01N2201/06—Illumination; Optics
- G01N2201/062—LED's
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Biophysics (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Food Science & Technology (AREA)
- Evolutionary Biology (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Medicinal Chemistry (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Genetics & Genomics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Physiology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention belongs to the technical field of nondestructive testing of agricultural products, and discloses an embedded apple maturity detection system and method, wherein new low-dimensional data is used for replacing original high-order data for spectral clustering analysis, and the characteristic wavelength of apple maturity is extracted; dividing a training set and a prediction set of a data sample to obtain a penalty parameter c and a kernel function parameter g in a support vector machine model; constructing a classification model of apple maturity; acquiring sample apple characteristic spectrum data, and constructing an apple maturity classification model; and taking the apple maturity classification model as a core, and compiling a control program fused with the apple maturity classification model to realize the lossless prediction of the apple maturity. The invention reduces the prediction of indirect quantity, reduces the working complexity and improves the working efficiency and precision; a miniaturized printed circuit board is designed, an embedded operating system is implanted, and small and portable apple maturity rapid classification equipment is designed and completed.
Description
Technical Field
The invention belongs to the technical field of nondestructive testing of agricultural products, and particularly relates to an apple maturity detection system and method based on an embedded system.
Background
At present, apples are rich in variety and wide in planting, are the first fruit in China, and the planting area and the yield of the apples all account for about 50% of the world. The yield of Chinese apples is huge, but the quality of the Chinese apples is different from that of foreign apples by a certain distance, and the reason is that the picking time of the apples with different purposes is unreasonable, in short, the apples are not ripe and picked in advance, so that the quality of the apples is influenced, and the apple waste is also caused. The apple maturity can determine the picking time of the fruits and evaluate the quality of the harvested fruits, and is one of important indexes for evaluating the quality of the apples. The harvest maturity is a key factor for determining the taste and flavor of the apples, and directly influences the quality grade and the economic benefit of the apples. Maturity is generally classified into collectable maturity, edible maturity, and physiological maturity. Insufficient ripeness causes problems such as low sugar content, poor coloring degree, poor taste, susceptibility to diseases, etc., while too high a ripeness causes problems such as soft texture, poor taste and flavor, poor storage stability, etc. Therefore, the judgment of the maturity is of great significance to the storage and quality assurance of the picked apples.
At present, the apple maturity is mainly determined by fruit growers according to the blooming period, the determination needs certain experience and is blind, and the maturity is not uniform due to the influence of regional climate, growth difference and other factors on different fruit trees. Meanwhile, the method for detecting the physical and chemical properties is complex and time-consuming, is not suitable for large-scale detection and needs to damage apples. However, at present, relatively few researches on the evaluation index analysis, the evaluation of physicochemical quality and the comprehensive evaluation model of the apple maturity at home and abroad are carried out, the selected evaluation standards are different, the whole system is imperfect, but according to the researches of Zhao political Yang, Zhang military and the like, indexes such as sugar degree, acidity, hardness, coloring and the like are found to be different along with the apple maturity, index parameters are greatly changed, and the method is an important judgment basis for the apple maturity.
In summary, the problems of the prior art are as follows:
(1) at present, the apple maturity is judged by predicting an apple quality index factor through a spectrum and judging the apple maturity by using the index factor, the process is complicated, and the prediction accuracy is reduced by performing multiple predictions in order to predict the maturity.
(2) The existing prediction method adopts full spectrum to establish a maturity prediction model, contains more redundant and miscellaneous information, has low operation speed and is not easy to popularize.
(3) The existing maturity detection equipment is large in size, high in requirements for detection environment and long in detection period.
The difficulty of solving the technical problems is as follows: the method has many advantages of establishing an apple maturity classification model by using the characteristic spectrum, but the selection of the characteristic wave band is a difficult point, the characteristic wave band needs to contain most of the content of the full wave band, and simultaneously redundant information is removed, and the characteristic wave band is not a thousand-dimensional array but a vector of only dozens of elements; how to create the model based on the support vector machine depends on the input parameters to a great extent, and the result obtained by the difference of the input parameters is quite different, so how to select the proper input parameters is another difficulty.
The significance of solving the technical problems is as follows: the mode of directly predicting the maturity of the apples by using the spectrum solves the defects of non-uniform and inaccurate apple maturity judgment standards, reduces the complexity of the apple maturity judgment process, and improves the efficiency of apple maturity grading; based on the characteristic spectrum, the optimal decision hyperplane and classification model of Fuji apple maturity classification is obtained by utilizing a support vector machine algorithm optimized by a genetic algorithm, so that the complexity of spectral operation is reduced, the interference of useless spectra is eliminated, and the transportability of the model is improved; the embedded apple maturity detection method and system are applied to small-sized portable detection equipment, complexity of a detection device can be reduced, operability of the device is improved, technology is combined with products, and research and development of an apple maturity judging method are promoted.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides an apple maturity detection system and method based on an embedded mode.
The invention is realized in such a way that an embedded apple maturity detection method comprises the following steps:
firstly, an apple diffuse reflection laboratory platform performs spectral clustering analysis through principal component analysis to replace original high-order data with new low-order data, and extracts the characteristic wavelength of apple maturity by combining an x-load coefficient method based on the spectral data of the principal component analysis;
dividing a training set and a prediction set of the data sample based on a sample of the apple maturity characteristic spectrum, and optimizing by using a genetic algorithm to obtain a punishment parameter c and a kernel function parameter g in the support vector machine model; constructing a classification model of apple maturity by taking a Gaussian kernel function as a kernel function of a support vector machine;
step three, based on the diffuse reflection mode of the interaction of the near infrared light and the apples; the method comprises the steps that a drive circuit and a control circuit of a halogen light source and a printed circuit board of an external trigger circuit are adopted to match a main controller, sample apple characteristic spectrum data are obtained, and an apple maturity classification model is constructed; and taking the apple maturity classification model as a core, and compiling a control program fused with the apple maturity classification model to realize the lossless prediction of the apple maturity.
Further, the apple maturity classification method based on the embedded apple maturity detection method and the support vector machine optimized based on the genetic algorithm comprises the following steps:
firstly, extracting spectral characteristic wavelengths of apple maturity classification, constructing an apple maturity diffuse reflection experiment platform based on a visible/near infrared spectrum, and acquiring a spectral curve graph of an apple by using a surface feature spectrometer; based on the sample of the apple diffuse reflection, performing cluster analysis on spectral data by means of principal component analysis to obtain a cluster map of a first principal component and a second principal component; extracting characteristic wavelength of a spectrum based on an x-load coefficient, wherein the x-load coefficient method is based on a principal component factor coefficient matrix of spectral data obtained by principal component analysis, and a load coefficient graph of the first three principal components is drawn by taking a wavelength vector of the spectral data as a horizontal axis of the load coefficient graph and taking the principal component factor coefficient matrix as a response value of a vertical coordinate; the x-load coefficient method can obtain the load coefficient corresponding to each wavelength point under each hidden variable, and the spectral characteristic wavelength which has clustering effect on the spectral data sample is screened; according to the local maximum value of the load coefficient, the spectral characteristic wavelength for apple maturity classification is screened out;
and secondly, constructing a classification model of apple maturity, comprising the following steps of: establishing an apple maturity classification model by using a genetic algorithm as an optimization mode and a support vector machine classification algorithm; the classification model takes a spectral characteristic waveband extracted by an x-load coefficient algorithm as input, sets an optimal punishment parameter c and a kernel function parameter g obtained by a genetic algorithm, and adopts a kernel function as a Gaussian kernel function to realize rapid lossless prediction of apple maturity information;
according to the extracted spectral characteristic wave bands, dividing an experimental sample, dividing the experimental sample into a training set and a verification set, firstly training an apple maturity prediction model according to a support vector machine algorithm based on genetic algorithm optimization, verifying the model based on the verification set sample, and finally storing the model.
Further, the construction of the apple maturity classification model in the second step specifically comprises:
(1) encoding the extracted spectral characteristic wavelength, expressing the solution space variable as gene string structure data of genetic space, using the accuracy function of a support vector machine model as the fitness function of a genetic algorithm, and using a roulette method as the fitness functionThe probability of each individual being selected is in direct proportion to the fitness of the individual through a selection operator of the genetic algorithm, the formula is shown as the following formula, the population scale is n, and the fitness of an individual i is fiThen i is selected with probability Pi：
In the formula (f)iFitness of individual i, PiIs the probability of being selected;
(2) selecting an operation method of the genetic algorithm for both crossing and mutation operations in the genetic algorithm, and running the genetic algorithm for multiple times to obtain an optimal punishment parameter c and a kernel function parameter g;
(3) the support vector machine algorithm takes the characteristic wavelength of an apple sample spectrum and the actual maturity condition of an apple as input, the penalty parameter c and the kernel function parameter g select the optimal value obtained by the genetic algorithm, the kernel function is a Gaussian kernel function, and the formula is as follows:
in the formula, XpIs the kernel function center, X is the input vector, | X-Xp||2Is the squared euclidean distance between the two feature vectors.
Further, the nondestructive testing method based on the embedded apple maturity detection method based on the apple maturity classification algorithm comprises the following steps: the spectrum acquisition module is mainly used for acquiring characteristic spectrum data, one spectrum data is a 23-bit binary data pair, and the binary data is converted into decimal floating point numbers through IEEE standard, namely the real values of the characteristic spectrum; an embedded apple maturity detection model is embedded in the controller module, spectral characteristic data is input through a model network interface, and the result of apple maturity is output; the trigger module adopts hardware anti-shake; the display screen communicates with the controller through the SPI bus to realize real-time display of the apple detection result.
Further, the nondestructive testing method based on the embedded apple maturity detection method based on the apple maturity classification algorithm further comprises the following steps: fusing an apple maturity classification model, carrying out initialization operation after equipment loading is finished, then carrying out light source correction, and storing the optimal duty ratio by the equipment after the correction is finished; the duty ratio is always used to ensure the consistency of the light intensity of the light source, after the interface is loaded successfully, the equipment waits for an external trigger signal circularly, once the falling edge trigger signal is detected, the equipment generates pulses to control the light source driving board to drive halogen and the like to light, the controller starts to read the spectrum data in the sensor register, and the integrity of the data is judged; based on the acquired characteristic spectrum data, the maturity information of the apples is acquired by using an apple maturity classification model, and the apple maturity is classified.
It is another object of the present invention to provide a program storage medium for receiving user input, the stored computer program causing an electronic device to perform the steps comprising:
firstly, an apple diffuse reflection laboratory platform performs spectral clustering analysis through principal component analysis to replace original high-order data with new low-order data, and extracts the characteristic wavelength of apple maturity by combining an x-load coefficient method based on the spectral data of the principal component analysis;
secondly, dividing a training set and a prediction set of the data sample based on a sample of the apple maturity characteristic spectrum, and optimizing by using a genetic algorithm to obtain a punishment parameter c and a kernel function parameter g in a support vector machine model; constructing a classification model of apple maturity by taking a Gaussian kernel function as a kernel function of a support vector machine;
thirdly, based on the diffuse reflection mode of the interaction of the near infrared light and the apple; the method comprises the steps that a drive circuit and a control circuit of a halogen light source and a printed circuit board of an external trigger circuit are adopted to match a main controller, sample apple characteristic spectrum data are obtained, and an apple maturity classification model is constructed; and taking the apple maturity classification model as a core, and compiling a control program fused with the apple maturity classification model to realize the lossless prediction of the apple maturity.
It is another object of the present invention to provide a computer program product stored on a computer readable medium, comprising a computer readable program for providing a user input interface to implement the embedded apple maturity detection method when executed on an electronic device.
Another object of the present invention is to provide an embedded apple maturity detection system for implementing the embedded apple maturity detection method, wherein the embedded apple maturity detection system comprises:
the apple diffuse reflection laboratory platform is used for carrying out spectral clustering analysis through principal component analysis to replace original high-order data with new low-order data, and extracting the characteristic wavelength of apple maturity by combining an x-load coefficient method based on the spectral data of the principal component analysis;
the portable nondestructive testing equipment is used for constructing an apple maturity classification model based on the acquired sample apple characteristic spectrum data; and taking the apple maturity classification model as a core, and compiling a control program fused with the apple maturity classification model to realize the lossless prediction of the apple maturity.
Further, the apple diffuse reflection laboratory platform adopts a surface spectrograph to obtain a spectrum curve graph of the apple.
Furthermore, the portable nondestructive testing equipment comprises a shell, a testing probe, a control module, a light source driving module and a data acquisition module;
the control module includes: the system comprises a spectrum acquisition module, a controller module, a light source driving module, a trigger module and a power supply module;
the spectrum acquisition module is used for acquiring characteristic spectrum data, one spectrum data is a binary data pair of 23 bits, and the binary data pair is converted into decimal floating point number by IEEE standard, namely the real value of the characteristic spectrum;
the controller module is embedded with an embedded apple maturity detection model, and spectral characteristic data is input through a model network interface and used for outputting apple maturity results;
the trigger module adopts hardware anti-shake to ensure that the system cannot be triggered for many times, and is connected with a large capacitor of 0.1 mu F in parallel to reduce the shake of keys; a key indicator lamp is added in the trigger module, so that a user is prevented from triggering keys for many times in a short time;
the power module reasonably distributes the 12V voltage provided by the lithium battery into 7V and 5V voltages through the printed circuit board and provides sufficient current;
the light source driving module is characterized in that a driving chip of the light source driving module is BP1361, the packaging mode is an SOT23-5 mode, the light source driving module is a common voltage reduction constant current driving chip, and a pin VIM can input voltage from 5V to 30V; when the controller works, the BP1361, an inductor (L1) and a current sampling resistor (R1) form a self-oscillating voltage-reducing constant current LED controller in a continuous inductor current mode, and current is output between leads AD1 and AD 2;
the module is a light source driving module which can adjust the light intensity of the LED by using PWM, a pin DIM in the module can receive PWM with a wide frequency range of 0.5-2.5V, when the voltage of the DIM is lower than 0.3V, a power switch is turned off, a driving chip enters a standby state with extremely low working current, the PWM required by the pin of the DIM can be generated by a software program, the light source driving module can generate current with constant power by combining with a PWM control program, and the light intensity generated by the halogen light source each time is ensured to be consistent;
the shell of the portable nondestructive testing equipment mainly has the functions of protection, support and heat dissipation and is designed according to the hardware structure of the equipment; the equipment detection probe is one of the most important parts of the equipment and provides guarantee for the equipment detection precision.
The display screen is communicated with the controller through the SPI bus to achieve real-time display of apple detection results.
In summary, the advantages and positive effects of the invention are: aiming at the problems of complex mode, high requirement on environment and the like of the existing lossless prediction of apple maturity, a diffuse reflection light detection light path (probe) is designed, spectral characteristic wavelength is used as input, and classification of apple maturity is directly realized by adopting a support vector machine apple maturity classification model fused with a genetic algorithm; compared with the traditional mode for predicting the apple maturity, the method reduces the prediction of indirect quantity (the national and chemical indexes of the apples), reduces the work complexity and improves the work efficiency and precision. Based on the apple maturity intelligent classification algorithm, a miniaturized printed circuit board is designed, an embedded operating system is implanted, and a small portable apple maturity rapid classification device is designed.
The method adopts a new maturity discrimination algorithm, a support vector machine maturity classification algorithm based on characteristic spectrum wavelength and genetic algorithm optimization to realize rapid classification of apple maturity; the detection spectrum is optimized, a light source correction system is added, and the adaptability of the equipment to the environment is improved; the printed circuit board is designed in an integrated mode, the size of the equipment is reduced, and the equipment is convenient to carry.
The invention comprises an apple maturity classification method and portable apple maturity rapid nondestructive testing equipment which integrate a genetic algorithm and a support vector machine algorithm; the rapid nondestructive detection equipment for the apple maturity specifically comprises a shell for stabilizing, supporting and protecting the equipment, a detection light path designed according to the diffuse reflection principle of light and a halogen light source, a light intensity correction unit for ensuring the light intensity stability of the equipment, a drive control unit of the halogen light source, a trigger unit and a data acquisition module; the support vector machine algorithm for apple maturity grading adopts a Gaussian kernel function, wherein a penalty parameter c and a kernel function parameter g are obtained by optimizing a genetic algorithm; the drive control unit of the halogen light source specifically comprises a constant voltage and constant current drive module and a pulse width modulation control module. The embedded apple maturity detection system is simple in structure, convenient to apply and carry, capable of efficiently and quickly distinguishing apple maturity and promoting digital and intelligent development of the apple industry.
According to the invention, the detection light path (probe) is designed according to the characteristics of spectrum diffuse reflection and the actual situation of the halogen light source, so that the practicability of the equipment is effectively improved; the design mode of an integrated circuit is adopted, a basic control driving circuit and a control circuit are closely combined together, and the research and development cost of equipment is reduced; the embedded apple maturity judging model based on the genetic algorithm and the support vector machine algorithm endows the detection equipment with real practical significance; the rapid apple maturity detection system and method promote the intellectualization and digitization of the apple industry, promote the realization of agricultural Internet of things, and accelerate the progress of visible/near infrared nondestructive apple detection technology toward actual production.
Drawings
Fig. 1 is a flowchart of an embedded apple maturity detection method according to an embodiment of the present invention.
Fig. 2 is a graph of apple diffuse reflectance spectrum provided by the embodiment of the present invention.
FIG. 3 is a diagram of apple spectral clustering provided by the embodiment of the present invention
FIG. 4 is a graph of apple spectrum x-loading coefficient based on principal component analysis according to an embodiment of the present invention.
FIG. 5 is a flowchart of a support vector machine algorithm based on genetic algorithm optimization according to an embodiment of the present invention.
Fig. 6 is a schematic diagram of an optical path of an embedded apple maturity detection apparatus according to an embodiment of the present invention.
Fig. 7 is a light path object diagram of an embedded apple maturity detection device according to an embodiment of the present invention.
Fig. 8 is a system control diagram of an embedded apple maturity detection device according to an embodiment of the present invention.
Fig. 9 is a schematic diagram of a driving circuit of an apple detection light source according to an embodiment of the present invention.
FIG. 10 is a flowchart of a process provided by an embodiment of the present invention.
FIG. 11 is a flowchart illustrating a light source calibration process according to an embodiment of the present invention.
FIG. 12 is a diagram illustrating the classification effect of samples according to an embodiment of the present invention.
Fig. 13 is a diagram showing an apparatus housing according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Aiming at the problems in the prior art, the invention provides an apple maturity detection system and method based on an embedded mode, and the invention is described in detail with reference to the attached drawings.
As shown in fig. 1, the method for detecting apple maturity based on the embedded system according to the embodiment of the present invention includes the following steps:
s101: constructing an apple diffuse reflection laboratory platform based on visible/near infrared spectrum; and (3) performing spectral clustering analysis through principal component analysis to replace original high-order data with new low-order data, and extracting the characteristic wavelength of apple maturity by combining an x-load coefficient method based on the spectral data of the principal component analysis.
S102: dividing a training set and a prediction set of a data sample based on a sample of an apple maturity characteristic spectrum, and optimizing by using a genetic algorithm to obtain a penalty parameter c and a kernel function parameter g in a support vector machine model; and (5) constructing a classification model of apple maturity by taking the Gaussian kernel function as the kernel function of the support vector machine.
S103: three-dimensional printing can be used for a detection light path (probe) on portable equipment based on a diffuse reflection mode of interaction of near infrared light and apples; drawing a drive circuit and a control circuit of the halogen light source, processing a printed circuit board by an external trigger circuit, and forming a hardware platform of the equipment by matching with a main controller.
S104: acquiring sample apple characteristic spectrum data based on a special detection probe and a hardware platform, and constructing an apple maturity classification model by combining an S102 method; and then, taking the apple maturity classification model as a core, and compiling a control program fused with the apple maturity classification model to realize the lossless prediction of the apple maturity.
The technical solution of the present invention is further described below with reference to the accompanying drawings.
The apple maturity detection method based on the embedded mode provided by the embodiment of the invention comprises the following steps:
(1) apple maturity classification method based on genetic algorithm optimization and using support vector machine
The first step is as follows: and extracting spectral characteristic wavelengths for apple maturity classification. An apple maturity diffuse reflection experiment platform based on a visible/near infrared spectrum is built, a spectral curve graph of an apple is obtained by adopting a terrestrial object spectrometer (OFS-1100, Ocean Optics, USA), as shown in figure 2, a wavelength with a spectral wavelength range of 398-1045 nm is selected as an effective sample, the spectral resolution is 0.46nm, and 1432 sample attributes are total; based on the sample of the apple diffuse reflection, the spectral data is subjected to cluster analysis by means of principal component analysis to obtain a cluster diagram of a first principal component and a second principal component as shown in fig. 3, and the spectral data can be seen to be roughly divided into three types, which indicates that spectral curves of apples with different ripeness degrees are different; extracting characteristic wavelength of spectrum based on x-load coefficient, wherein the x-load coefficient method is based on principal component factor coefficient matrix of spectrum data obtained by principal component analysis, and the load coefficient diagram of the first three principal components is drawn by taking wavelength vector of the spectrum data as the horizontal axis of the load coefficient diagram and taking the principal component factor coefficient matrix as the response value of the vertical coordinate (as shown in FIG. 4); the x-load coefficient method can obtain the load coefficient corresponding to each wavelength point under each hidden variable, and further screens the spectral characteristic wavelength which has clustering effect on the spectral data sample; and screening out spectral characteristic wavelengths which can be used for apple maturity classification according to the local maximum value of the load coefficient.
The second step is that: and (5) constructing a classification model of apple maturity. The apple maturity rapid classification algorithm specifically comprises the following steps: establishing an apple maturity classification model by using a genetic algorithm as an optimization mode and a support vector machine classification algorithm; the classification model takes the spectral characteristic wave band extracted by the x-load coefficient algorithm as input, sets the optimal punishment parameter c and the kernel function parameter g obtained by the genetic algorithm, and adopts the kernel function as the Gaussian kernel function to realize the rapid lossless prediction of the apple maturity information.
When the genetic algorithm is carried out, firstly, the extracted spectral characteristic wavelength needs to be coded, a solution space variable is expressed into gene string structure data of the genetic space, an accuracy function of a support vector machine model is used as a fitness function of the genetic algorithm, a roulette method is used as a selection operator of the genetic algorithm, in the method, the probability of each individual to be selected is in direct proportion to the fitness of the individual, a formula is shown as the following formula, the group scale is set as n, and the fitness of an individual i is fiThen i is selected with probability Pi：
In the formula (f)iFitness of individual i, PiIs the probability of being selected;
and (4) selecting an operation method of the genetic algorithm for both crossing and mutation operations in the genetic algorithm, and running the genetic algorithm for multiple times to obtain the optimal penalty parameter c and the kernel function parameter g.
The support vector machine algorithm takes the characteristic wavelength of an apple sample spectrum and the actual maturity condition of an apple as input, a penalty parameter c and a kernel function parameter g select the optimal value obtained by the genetic algorithm, the kernel function is a Gaussian kernel function, and the formula is as follows:
in the formula, XpIs the kernel function center, X is the input vector, | X-Xp||2Is the squared euclidean distance between the two eigenvectors;
according to the spectral characteristic wave bands extracted by the hardware platform of the device, dividing the experimental samples into a training set and a verification set, firstly training an apple maturity prediction model according to a support vector machine algorithm flow chart based on genetic algorithm optimization as shown in figure 5, then verifying the model based on the verification set samples, and finally storing the model.
(2) Portable nondestructive testing equipment based on apple maturity classification algorithm
The first step is as follows: the establishment of the hardware equipment of the apple maturity rapid detection system comprises a shell, a detection probe, a control module, a light source driving module and a data acquisition module. The shell of the equipment mainly plays a role in supporting, protecting and stabilizing, and the existence of the shell of the equipment increases the stability of the equipment; the tilt angle of the halogen light source and the distance from the light source to the apple surface are calculated according to the characteristics of diffuse reflection of the visible/near infrared spectrum and the characteristics of the halogen light source and the actual external environment, as shown in fig. 6, and finally, the diffuse reflection light path of the usable device designed as the drawing is obtained, as shown in fig. 7.
The second step is that: the device uses a raspberry pie as a central processing unit to coordinate the work of all modules, the system block diagram of the rapid nondestructive testing device for apple maturity is shown in fig. 8, and the whole hardware control system comprises 6 modules which are mainly a spectrum acquisition module, a controller module, a light source driving module, a triggering module and a power supply module. The spectrum acquisition module is mainly used for acquiring characteristic spectrum data, one spectrum data is a 23-bit binary data pair, and the binary data is converted into decimal floating point numbers through IEEE standard, namely the real values of the characteristic spectrum; an embedded apple maturity detection model is embedded in the controller module, spectral characteristic data is input through a model network interface, and the result of apple maturity is output; the trigger module adopts a hardware anti-shake technology, so that the condition of multiple triggers is greatly reduced, and the stability of the equipment is improved; the display screen communicates with the controller through the SPI bus to realize real-time display of the apple detection result. Because the lighting of the halogen light source needs a large current (not less than 0.9A), the light source driving module is designed as shown in FIG. 9, and meanwhile, the pulse can be used for regulating the light intensity of the halogen light source, so that the universality of the equipment is improved.
The third step: writing a software program fusing apple maturity classification models, wherein a flow chart is shown in fig. 10, after equipment loading is finished, firstly, initializing operation is carried out, then, a method for carrying out light source correction specifically is shown in fig. 11, after correction is finished, the equipment stores an optimal duty ratio, in the using process of the following equipment, the duty ratio is always used to ensure the consistency of light intensity of a light source, after a successful interface is loaded, the equipment circularly waits for an external trigger signal, once a falling edge trigger signal is detected, the equipment generates pulses to control a light source driving board to drive halogen and the like to be lightened, a controller starts to read spectral data in a sensor register, and the integrity of the data is judged; based on the acquired characteristic spectrum data, the maturity information of the apples is acquired by using an apple maturity classification model, and the apple maturity is classified.
The apple maturity classification method of the support vector machine integrating the genetic algorithm can be directly applied to the detection equipment. The method comprises the steps of inputting a plurality of characteristic spectrums with the maximum correlation with apple maturity to obtain apple maturity information, reducing the influence of environment on a detection result by a detection light path of nondestructive detection equipment included in the system, and providing a hardware environment for the operation of an algorithm by a designed and manufactured printed circuit board. In conclusion, the apple nondestructive testing method provides a new idea for researches on apple maturity and the like; the rapid apple maturity detection equipment constructed by combining the nondestructive detection method provided by the invention promotes the rapid development of the nondestructive apple maturity detection equipment in China, and accelerates the process of combining intelligent data and agricultural products.
(3) Experimental verification
As shown in fig. 13, the portable apple maturity detection device built based on the embedded apple maturity detection method and system and the computer program according to the embodiment verifies the detection method and system of the embodiment by using the built nondestructive detection device; the experimental samples are 60 Fuji apples with different ripeness degrees, the classification precision reaches 83.33%, and the condition that the non (over) ripeness apples are classified into the non (over) ripeness apples does not exist, as shown in FIG. 12, the apple ripeness detection method and the apple ripeness detection system are feasible; some errors are also not negligible in the prediction of the system, and the reason for generating the errors may be that external natural light interferes the detection process, so the light shading performance of the system still needs to be deeply researched.
It should be noted that the embodiments of the present invention can be realized by hardware, software, or a combination of software and hardware. The hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the apparatus and methods described above may be implemented using computer executable instructions and/or embodied in processor control code, such code being provided on a carrier medium such as a disk, CD-or DVD-ROM, programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier, for example. The apparatus and its modules of the present invention may be implemented by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., or by software executed by various types of processors, or by a combination of hardware circuits and software, e.g., firmware.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. An embedded apple maturity detection method is characterized by comprising the following steps:
firstly, an apple diffuse reflection laboratory platform performs spectral clustering analysis through principal component analysis to replace original high-order data with new low-order data, and extracts the characteristic wavelength of apple maturity by combining an x-load coefficient method based on the spectral data of the principal component analysis;
dividing a training set and a prediction set of the data sample based on a sample of the apple maturity characteristic spectrum, and optimizing by using a genetic algorithm to obtain a punishment parameter c and a kernel function parameter g in the support vector machine model; constructing a classification model of apple maturity by taking a Gaussian kernel function as a kernel function of a support vector machine;
step three, based on the diffuse reflection mode of the interaction of the near infrared light and the apples; the method comprises the steps that a drive circuit and a control circuit of a halogen light source and a printed circuit board of an external trigger circuit are adopted to match a main controller, sample apple characteristic spectrum data are obtained, and an apple maturity classification model is constructed; and taking the apple maturity classification model as a core, and compiling a control program fused with the apple maturity classification model to realize the lossless prediction of the apple maturity.
2. The embedded apple maturity detection method of claim 1 wherein the support vector machine apple maturity classification method based on genetic algorithm optimization comprises:
firstly, extracting spectral characteristic wavelengths of apple maturity classification, constructing an apple maturity diffuse reflection experiment platform based on a visible/near infrared spectrum, and acquiring a spectral curve graph of an apple by using a surface feature spectrometer; based on the sample of the apple diffuse reflection, performing cluster analysis on spectral data by means of principal component analysis to obtain a cluster map of a first principal component and a second principal component; extracting characteristic wavelength of a spectrum based on an x-load coefficient, wherein the x-load coefficient method is based on a principal component factor coefficient matrix of spectral data obtained by principal component analysis, and a load coefficient graph of the first three principal components is drawn by taking a wavelength vector of the spectral data as a horizontal axis of the load coefficient graph and taking the principal component factor coefficient matrix as a response value of a vertical coordinate; the x-load coefficient method can obtain the load coefficient corresponding to each wavelength point under each hidden variable, and the spectral characteristic wavelength which has clustering effect on the spectral data sample is screened; according to the local maximum value of the load coefficient, the spectral characteristic wavelength for apple maturity classification is screened out;
and secondly, constructing a classification model of apple maturity, comprising the following steps of: establishing an apple maturity classification model by using a genetic algorithm as an optimization mode and a support vector machine classification algorithm; the classification model takes a spectral characteristic waveband extracted by an x-load coefficient algorithm as input, sets an optimal punishment parameter c and a kernel function parameter g obtained by a genetic algorithm, and adopts a kernel function as a Gaussian kernel function to realize rapid lossless prediction of apple maturity information;
according to the extracted spectral characteristic wave bands, dividing an experimental sample, dividing the experimental sample into a training set and a verification set, firstly training an apple maturity prediction model according to a support vector machine algorithm based on genetic algorithm optimization, verifying the model based on the verification set sample, and finally storing the model.
3. The embedded apple maturity detection method based on claim 2, wherein the second step of constructing the apple maturity classification model specifically comprises:
(1) coding the extracted spectral characteristic wavelength, expressing a solution space variable into gene string structure data of a genetic space, using an accuracy function of a support vector machine model as a fitness function of a genetic algorithm, using a roulette method as a selection operator of the genetic algorithm, wherein the probability of each individual being selected is in direct proportion to the fitness of the individual, the formula is shown as the following formula, the population scale is n, wherein the fitness of an individual i is fiThen i is selected with probability Pi：
In the formula (f)iFitness of individual i, PiIs the probability of being selected;
(2) selecting an operation method of the genetic algorithm for both crossing and mutation operations in the genetic algorithm, and running the genetic algorithm for multiple times to obtain an optimal punishment parameter c and a kernel function parameter g;
(3) the support vector machine algorithm takes the characteristic wavelength of an apple sample spectrum and the actual maturity condition of an apple as input, the penalty parameter c and the kernel function parameter g select the optimal value obtained by the genetic algorithm, the kernel function is a Gaussian kernel function, and the formula is as follows:
in the formula, XpIs the kernel function center, X is the input vector, | X-Xp||2Is the squared euclidean distance between the two feature vectors.
4. The embedded apple maturity detection method of claim 1, wherein the embedded apple maturity detection method is a nondestructive detection method based on apple maturity classification algorithm, comprising: the spectrum acquisition module is mainly used for acquiring characteristic spectrum data, one spectrum data is a 23-bit binary data pair, and the binary data is converted into decimal floating point numbers through IEEE standard, namely the real values of the characteristic spectrum; an embedded apple maturity detection model is embedded in the controller module, spectral characteristic data is input through a model network interface, and the result of apple maturity is output; the trigger module adopts hardware anti-shake; the display screen communicates with the controller through the SPI bus to realize real-time display of the apple detection result.
5. The embedded apple maturity detection method of claim 1 wherein the apple maturity classification algorithm based non-destructive detection method further comprises: fusing an apple maturity classification model, carrying out initialization operation after equipment loading is finished, then carrying out light source correction, and storing the optimal duty ratio by the equipment after the correction is finished; the duty ratio is always used to ensure the consistency of the light intensity of the light source, after the interface is loaded successfully, the equipment waits for an external trigger signal circularly, once the falling edge trigger signal is detected, the equipment generates pulses to control the light source driving board to drive halogen and the like to light, the controller starts to read the spectrum data in the sensor register, and the integrity of the data is judged; based on the acquired characteristic spectrum data, the maturity information of the apples is acquired by using an apple maturity classification model, and the apple maturity is classified.
6. A program storage medium for receiving user input, the stored computer program causing an electronic device to perform the steps comprising:
firstly, an apple diffuse reflection laboratory platform performs spectral clustering analysis through principal component analysis to replace original high-order data with new low-order data, and extracts the characteristic wavelength of apple maturity by combining an x-load coefficient method based on the spectral data of the principal component analysis;
secondly, dividing a training set and a prediction set of the data sample based on a sample of the apple maturity characteristic spectrum, and optimizing by using a genetic algorithm to obtain a punishment parameter c and a kernel function parameter g in a support vector machine model; constructing a classification model of apple maturity by taking a Gaussian kernel function as a kernel function of a support vector machine;
thirdly, based on the diffuse reflection mode of the interaction of the near infrared light and the apple; the method comprises the steps that a drive circuit and a control circuit of a halogen light source and a printed circuit board of an external trigger circuit are adopted to match a main controller, sample apple characteristic spectrum data are obtained, and an apple maturity classification model is constructed; and taking the apple maturity classification model as a core, and compiling a control program fused with the apple maturity classification model to realize the lossless prediction of the apple maturity.
7. A computer program product stored on a computer readable medium, comprising a computer readable program for providing a user input interface for implementing an embedded apple maturity detection method according to any one of claims 1 to 5 when executed on an electronic device.
8. An embedded apple maturity detection system implementing the embedded apple maturity detection method of any one of claims 1 to 5, wherein the embedded apple maturity detection system comprises:
the apple diffuse reflection laboratory platform is used for carrying out spectral clustering analysis through principal component analysis to replace original high-order data with new low-order data, and extracting the characteristic wavelength of apple maturity by combining an x-load coefficient method based on the spectral data of the principal component analysis;
the portable nondestructive testing equipment is used for acquiring sample apple characteristic spectrum data and establishing an apple maturity classification model in a combined manner; and taking the apple maturity classification model as a core, and compiling a control program fused with the apple maturity classification model to realize the lossless prediction of the apple maturity.
9. The embedded apple maturity detection system of claim 8 wherein the apple diffuse reflectance laboratory platform uses a geophysical spectrometer to acquire a spectral profile of the apple.
10. The embedded apple maturity detection system of claim 8 wherein said portable non-destructive inspection apparatus comprises a housing, an inspection probe, a control module, a light source driving module, a data acquisition module;
the control module includes: the system comprises a spectrum acquisition module, a controller module, a light source driving module, a trigger module and a power supply module;
the spectrum acquisition module is used for acquiring characteristic spectrum data, one spectrum data is a binary data pair of 23 bits, and the binary data pair is converted into decimal floating point number by IEEE standard, namely the real value of the characteristic spectrum;
the controller module is embedded with an embedded apple maturity detection model, and spectral characteristic data is input through a model network interface and used for outputting apple maturity results;
the trigger module adopts hardware anti-shake;
the display screen is communicated with the controller through the SPI bus to achieve real-time display of apple detection results.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010452754.6A CN111665215A (en) | 2020-05-26 | 2020-05-26 | Apple maturity detection system and method based on embedded mode |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010452754.6A CN111665215A (en) | 2020-05-26 | 2020-05-26 | Apple maturity detection system and method based on embedded mode |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111665215A true CN111665215A (en) | 2020-09-15 |
Family
ID=72384727
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010452754.6A Pending CN111665215A (en) | 2020-05-26 | 2020-05-26 | Apple maturity detection system and method based on embedded mode |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111665215A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112881323A (en) * | 2021-01-14 | 2021-06-01 | 云南中烟工业有限责任公司 | Quality evaluation method of cigarette mainstream smoke |
| CN117054354A (en) * | 2023-10-12 | 2023-11-14 | 云南省林业和草原科学院 | Portable seed maturity spectrum detection system and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103021379A (en) * | 2012-12-25 | 2013-04-03 | 广东威创视讯科技股份有限公司 | Method and system for color correction based on customized light source duty ratio |
| CN103462618A (en) * | 2013-09-04 | 2013-12-25 | 江苏大学 | Automobile driver fatigue detecting method based on steering wheel angle features |
| CN107202761A (en) * | 2017-06-09 | 2017-09-26 | 甘肃萃英大农科技有限公司 | The portable detection equipment and detection method of a kind of quick detection fruit internal quality |
| CN107247033A (en) * | 2017-06-02 | 2017-10-13 | 中国计量大学 | Differentiate the method for Huanghua Pear maturity based on rapid decay formula life cycle algorithm and PLSDA |
| CN111104972A (en) * | 2019-12-06 | 2020-05-05 | 南京工程学院 | Method for identifying low-voltage risk of distribution room based on genetic algorithm optimization support vector machine multi-classifier |
-
2020
- 2020-05-26 CN CN202010452754.6A patent/CN111665215A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103021379A (en) * | 2012-12-25 | 2013-04-03 | 广东威创视讯科技股份有限公司 | Method and system for color correction based on customized light source duty ratio |
| CN103462618A (en) * | 2013-09-04 | 2013-12-25 | 江苏大学 | Automobile driver fatigue detecting method based on steering wheel angle features |
| CN107247033A (en) * | 2017-06-02 | 2017-10-13 | 中国计量大学 | Differentiate the method for Huanghua Pear maturity based on rapid decay formula life cycle algorithm and PLSDA |
| CN107202761A (en) * | 2017-06-09 | 2017-09-26 | 甘肃萃英大农科技有限公司 | The portable detection equipment and detection method of a kind of quick detection fruit internal quality |
| CN111104972A (en) * | 2019-12-06 | 2020-05-05 | 南京工程学院 | Method for identifying low-voltage risk of distribution room based on genetic algorithm optimization support vector machine multi-classifier |
Non-Patent Citations (1)
| Title |
|---|
| 褚璇 等: "近红外光谱和特征光谱的山茶油掺假鉴别方法研究", 《光谱学与光谱分析》, 31 January 2017 (2017-01-31), pages 75 - 79 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112881323A (en) * | 2021-01-14 | 2021-06-01 | 云南中烟工业有限责任公司 | Quality evaluation method of cigarette mainstream smoke |
| CN112881323B (en) * | 2021-01-14 | 2022-03-08 | 云南中烟工业有限责任公司 | Quality evaluation method of cigarette mainstream smoke |
| CN117054354A (en) * | 2023-10-12 | 2023-11-14 | 云南省林业和草原科学院 | Portable seed maturity spectrum detection system and device |
| CN117054354B (en) * | 2023-10-12 | 2024-03-05 | 云南省林业和草原科学院 | Portable seed maturity spectrum detection system and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhang et al. | Nondestructive measurement of soluble solids content in apple using near infrared hyperspectral imaging coupled with wavelength selection algorithm | |
| Wang et al. | Application of long-wave near infrared hyperspectral imaging for determination of moisture content of single maize seed | |
| Li et al. | Comparative analysis of models for robust and accurate evaluation of soluble solids content in ‘Pinggu’peaches by hyperspectral imaging | |
| CN111665215A (en) | Apple maturity detection system and method based on embedded mode | |
| CN113049530A (en) | Single-seed corn seed moisture content detection method based on near-infrared hyperspectrum | |
| Wang et al. | The applications of hyperspectral imaging technology for agricultural products quality analysis: A review | |
| Gao et al. | Soluble solid content and firmness index assessment and maturity discrimination of Malus micromalus Makino based on near-infrared hyperspectral imaging | |
| CN106546541A (en) | A kind of identifying device and method based on EO-1 hyperion transgenic corns seed | |
| CN102564993A (en) | Method for identifying rice varieties by using Fourier transform infrared spectrum and application of method | |
| Wang et al. | Study on starch content detection and visualization of potato based on hyperspectral imaging | |
| CN104568824B (en) | Shrimps grade of freshness detection method and device based on Vis/NIR | |
| Yang et al. | Hyperspectral prediction of sugarbeet seed germination based on gauss kernel SVM | |
| Kim et al. | Application of ensemble neural-network method to integrated sugar content prediction model for citrus fruit using Vis/NIR spectroscopy. | |
| Gai et al. | Convolutional neural network for apple bruise detection based on hyperspectral | |
| Yuan et al. | A Novel strategy of clustering informative variables for quantitative analysis of potential toxics element in Tegillarca granosa using laser-induced breakdown spectroscopy | |
| CN111693487A (en) | Fruit sugar degree detection method and system based on genetic algorithm and extreme learning machine | |
| Zhao et al. | Hyperspectral imaging coupled with random frog and calibration models for assessment of total soluble solids in mulberries | |
| CN103278467A (en) | Rapid nondestructive high-accuracy method with for identifying abundance degree of nitrogen element in plant leaf | |
| Wu et al. | Variety identification of Chinese cabbage seeds using visible and near-infrared spectroscopy | |
| Xu et al. | Nondestructive detection of total soluble solids in grapes using VMD‐RC and hyperspectral imaging | |
| He et al. | Discriminant analysis of maize haploid seeds using near-infrared hyperspectral imaging integrated with multivariate methods | |
| Wang et al. | Intelligent detection of hard seeds of snap bean based on hyperspectral imaging | |
| Li et al. | Study on qualitative impact damage of yellow peaches using the combined hyperspectral and physicochemical indicators method | |
| CN113903407A (en) | Component identification method, component identification device, electronic equipment and storage medium | |
| Meghar et al. | Hyperspectral imaging for the determination of relevant cooking quality traits of boiled cassava |
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 |