CN112082913A - Grain grade detection method and system, handheld detector and server - Google Patents
Grain grade detection method and system, handheld detector and server Download PDFInfo
- Publication number
- CN112082913A CN112082913A CN202011011837.8A CN202011011837A CN112082913A CN 112082913 A CN112082913 A CN 112082913A CN 202011011837 A CN202011011837 A CN 202011011837A CN 112082913 A CN112082913 A CN 112082913A
- Authority
- CN
- China
- Prior art keywords
- light
- sample
- grain
- server
- detected
- 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 63
- 239000002245 particle Substances 0.000 claims abstract description 22
- 238000000034 method Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 18
- 230000003595 spectral effect Effects 0.000 claims abstract description 10
- 238000001914 filtration Methods 0.000 claims description 24
- 230000003287 optical effect Effects 0.000 claims description 21
- 239000012535 impurity Substances 0.000 claims description 14
- 238000012360 testing method Methods 0.000 claims description 13
- 230000002194 synthesizing effect Effects 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 5
- 235000013305 food Nutrition 0.000 claims description 4
- 238000009434 installation Methods 0.000 claims description 2
- 235000013339 cereals Nutrition 0.000 description 98
- 238000005516 engineering process Methods 0.000 description 15
- 238000004891 communication Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 240000007594 Oryza sativa Species 0.000 description 6
- 235000007164 Oryza sativa Nutrition 0.000 description 6
- 238000007689 inspection Methods 0.000 description 6
- 235000009566 rice Nutrition 0.000 description 6
- 240000002582 Oryza sativa Indica Group Species 0.000 description 5
- 240000008467 Oryza sativa Japonica Group Species 0.000 description 5
- 240000008042 Zea mays Species 0.000 description 3
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 3
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 3
- 235000005822 corn Nutrition 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000003801 milling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 230000037380 skin damage Effects 0.000 description 1
- 238000004611 spectroscopical analysis Methods 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
- G01N15/02—Investigating particle size or size distribution
- G01N15/0205—Investigating particle size or size distribution by optical means
Landscapes
- Chemical & Material Sciences (AREA)
- Dispersion Chemistry (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a grain grade detection method, a grain grade detection system, a handheld detector and a server, aiming at clearly distinguishing index particles to be detected so as to conveniently judge the grain grade, different characteristic wavelengths are selected according to different grains, a plurality of sample images under the irradiation of light with a plurality of characteristic wavelengths corresponding to a sample to be detected are obtained, the plurality of sample images are synthesized, the spectral data and the image data are processed to obtain the ratio of the index particles to be detected, and the ratio is compared with the preset grain grade ratio to judge the grain grade. After the sample image is shot, all procedures are automatically completed by a machine without manual operation, and compared with a hyperspectral image, only a plurality of important wavelength images are detected, so that the data processing amount and the acquisition cost are reduced, and the relatively low cost is realized.
Description
Technical Field
The invention relates to the technical field of grain detection, in particular to a grain grade detection method and system, a handheld detector and a server.
Background
During the circulation and storage of the grains, the grain grade needs to be measured for classified sale and subsequent treatment. At present, the mainstream grain grade assessment method only uses the experience of grain detection related personnel to judge through the modes of naked eyes, hand feeling and the like, and the method has certain subjectivity and is easy to misjudge.
The hyperspectral technology is one of the technologies which are developed rapidly in recent years, and has a very good development prospect in the field of food safety. However, the existing hyperspectral image acquisition technology has high cost and needs a precise light splitting instrument, which greatly limits the large-scale practicability of the hyperspectral technology in the field of grain grade determination.
Disclosure of Invention
The invention mainly aims to provide a grain grade detection method, a grain grade detection system, a handheld detector and a server, aiming at realizing grain grade detection by applying a multispectral technology, easily realizing low cost and miniaturization, avoiding artificial interference and reducing the requirement of professional skills of grade detection personnel.
The invention provides a grain grade detection method, which is used for a server or a handheld detector and comprises the following steps:
obtaining a plurality of sample images under the irradiation of light with a plurality of characteristic wavelengths corresponding to a sample to be detected;
synthesizing a plurality of sample images, and processing spectral data and image data to obtain the ratio of the index particles to be measured;
and comparing the ratio with a preset grain grade ratio to judge the grain grade.
Optionally, before the step of obtaining the sample image of the sample to be detected under the irradiation of a certain characteristic wavelength, the method includes:
and acquiring related information of the sample to be detected, and storing the related information, wherein the related information comprises the sample type.
Optionally, in the step of synthesizing a plurality of sample images, processing the spectral data and the image data to obtain the ratio of the indexes of the particles to be measured,
the index particles to be measured include impurities and the like.
The invention also provides a hand-held detector, comprising:
a detector body;
the image acquisition device is positioned at the front end of the detector body and is used for acquiring a sample image of a sample to be detected under the irradiation of light with characteristic wavelength; and the number of the first and second groups,
and the control device is arranged on the detector body and is electrically connected with the image acquisition device.
Optionally, the hand-held test meter further includes:
the light source assembly is arranged at the front end of the detector body and used for providing a plurality of light sources; and the number of the first and second groups,
the light filtering component is positioned at the front side of the light source component and is used for filtering the light sources to obtain light with characteristic wavelength;
wherein, the control device is electrically connected with the light source component and the light filtering component.
Optionally, the filtering assembly includes:
the annular mounting plate is sleeved at the front end of the detector body and provided with a light transmission hole; and the number of the first and second groups,
the optical filter structure is rotatably installed on the annular installation plate along the front-back axis and comprises a plurality of optical filters which are sequentially arranged, and each optical filter can rotate to cover the light holes.
Optionally, the light filtering component further comprises an end cover, the end cover is detachably mounted on the annular mounting plate, and the end cover corresponds to the light holes and is provided with through holes.
Optionally, the handheld detector further comprises a display screen arranged on the outer surface of the detector body, and the display screen is electrically connected with the image acquisition assembly and the control device.
Optionally, the handheld detector further includes a power supply assembly, the power supply assembly is located at the rear end of the detector body, and is electrically connected to the light source assembly, the light filtering assembly, the image collecting assembly, and the control assembly.
Optionally, the light source assembly has two light sources arranged oppositely, and two light holes are correspondingly arranged;
the light filter structure comprises two light filter segments which are arranged in a central symmetry manner, each light filter segment is provided with a plurality of light filters which are arranged in sequence, and the two light filters which are arranged oppositely can rotate to cover to form corresponding light holes.
Optionally, the control device includes a memory, a processor, and a detection program for detecting the grain level, which is stored in the memory and can be run on the processor, and the detection program for detecting the grain level is configured to implement the steps of the grain level detection method.
The invention also provides a server, which comprises a memory, a processor and a detection program for detecting the grain level, wherein the detection program is stored on the memory and can be operated on the processor, and the detection program for detecting the grain level is configured to realize the steps of the grain level detection method.
The invention also provides a grain grade detection system, which comprises a server and at least one handheld detector, wherein each handheld detector is in communication connection with the server;
the hand-held test meter comprises:
a detector body;
the image acquisition device is positioned at the front end of the detector body and is used for acquiring a sample image of a sample to be detected under the irradiation of light with characteristic wavelength; and the number of the first and second groups,
and the control device is arranged on the detector body and is electrically connected with the image acquisition device.
Optionally, the hand-held test meter further includes:
the light source assembly is arranged at the front end of the detector body and used for providing a plurality of light sources; and the number of the first and second groups,
the light filtering component is positioned at the front side of the light source component and is used for filtering the light sources to obtain light with characteristic wavelength;
the server comprises a memory, a processor and a detection program for detecting the grain level, wherein the detection program is stored on the memory and can run on the processor, and the detection program for detecting the grain level is configured to realize the steps of the grain level detection method.
In the technical scheme provided by the invention, in order to clearly distinguish the index particles to be detected so as to conveniently judge the grade of the grain, different characteristic wavelengths are selected correspondingly to different grains, a plurality of sample images under the irradiation of light with a plurality of characteristic wavelengths corresponding to a sample to be detected are obtained, the plurality of sample images are synthesized, the spectrum data and the image data are processed, the ratio of the index particles to be detected is obtained, and the grain grade is judged by comparing the ratio with the preset grain grade ratio. After the sample image is shot, all procedures are automatically completed by a machine without manual operation, and compared with a hyperspectral image, only a plurality of important wavelength images are detected, so that the data processing amount and the acquisition cost are reduced, and the relatively low cost is realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the structures shown in the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a grain grade detection method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a control system of a hardware operating environment according to the embodiment of FIG. 1;
FIG. 3 is a schematic view of a grain level detection system according to an embodiment of the present invention;
FIG. 4 is a schematic view of the hand-held test meter of FIG. 3;
FIG. 5 is a schematic diagram of the filter structure shown in FIG. 4;
FIG. 6 is a schematic view of the annular mounting plate of FIG. 4.
The reference numbers illustrate:
| reference numerals | Name (R) | Reference numerals | Name (R) |
| 1000 | Grain |
5 | |
| 100 | Hand-held |
51 | |
| 1 | |
511 | |
| 2 | |
521 | |
| 3 | |
5211 | Optical filter |
| 4 | |
200 | Server |
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that, if directional indications (such as up, down, left, right, front, and back … …) are involved in the embodiment of the present invention, the directional indications are only used to explain the relative positional relationship between the components, the movement situation, and the like in a specific posture (as shown in the drawing), and if the specific posture is changed, the directional indications are changed accordingly.
In addition, if there is a description of "first", "second", etc. in an embodiment of the present invention, the description of "first", "second", etc. is for descriptive purposes only and is not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
China is a big population country, and the problem of food safety is always the first major thing of China. In recent years, the yield of grains in China breaks through 6 hundred million kilograms, the production time and the production place of the grains are different, and the varieties and the quality of the grains are also different. Therefore, during the distribution and storage of the grains, the grain grade needs to be accurately, rapidly and inexpensively determined so as to be classified and sold and processed later. At present, the mainstream grain grade assessment method only uses the experience of grain detection related personnel to judge through the modes of naked eyes, hand feeling and the like, and the method has certain subjectivity and is easy to misjudge. In some places where grains are concentrated, such as large-scale dealers, grain depots and the like, a relatively accurate grain grade detection system is also provided, the system adopts various sensors of different types to respectively detect the moisture and impurity content of the grains, and a small rice milling system is also needed to be equipped for measuring the rice yield and other indexes after the rice is milled into rice. The detection methods have the disadvantages of more required equipment and processes and higher detection cost. On the other hand, because the detection equipment is not networked, after the detection result is obtained, the detection result needs to be manually input into a database of a large-scale dealer or a grain depot, the workload is large, and errors are easy to occur.
The hyperspectral technology is one of the technologies which are developed rapidly in recent years, combines the advantages of the spectrum technology and the digital image processing technology, can clearly identify information which cannot be distinguished by human eyes, and has a very good development prospect in the field of food safety. However, the existing hyperspectral image acquisition technology has high cost and needs a precise light splitting instrument, which greatly limits the large-scale practicability of the hyperspectral technology in the field of grain grade determination. In fact, a large amount of information in the hyperspectral image is redundant, a plurality of wave bands which are most critical to the level detection result can be found through a reasonable mathematical method, accurate detection of the grain level can be realized only by collecting data of the wave bands, and the hyperspectral image is called as a multispectral technology to be different from the existing hyperspectral technology.
Referring to fig. 3, the present invention provides a grain grade detection system 1000, where the grain grade detection system 1000 includes at least one handheld detector 100 and a server 200, each handheld detector 100 is in communication connection with the server 200, the grain sample to be detected is tested by the handheld detector 100, a plurality of obtained sample images under irradiation of a plurality of characteristic wave lights are uploaded to the server 200, a detection result of the grade of the sample to be detected is obtained by image processing and spectral analysis of the server 200, and the result is transmitted to the handheld detector 100 for information feedback. The test is convenient, and the miniaturization is easy to realize.
It should be noted that, with the continuous development of network information transmission, the signal transmission between the handheld detector 100 and the server 200 can be completed through a 5G technology, and the data transmission speed of a 5G network is faster, so as to better satisfy the situation that a plurality of handheld detectors 100 access one server 200.
The server 200 includes a memory, a processor, and a detection program for grain level detection stored in the memory and operable on the processor.
The misting system 100 also includes a control system that includes a memory, a processor, and a misting program stored on the memory and operable on the processor to operate the misting system 100.
Specifically, the server 200 may include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a memory system separate from the processor 1001.
In the control system shown in fig. 2, a detection program for grain level detection stored in the memory 1005 is called by the processor 1001, and performs the following operations:
obtaining a plurality of sample images under the irradiation of light with a plurality of characteristic wavelengths corresponding to a sample to be detected;
synthesizing a plurality of sample images, and processing spectral data and image data to obtain the ratio of the index particles to be measured;
and comparing the ratio with a preset grain grade ratio to judge the grain grade.
Further, the processor 1001 may call a detection program for grain level detection stored in the memory 1005, and also perform the following operations:
before the step of obtaining the sample image of the sample to be detected under the irradiation of a certain characteristic wavelength, the method comprises the following steps:
and acquiring related information of the sample to be detected, and storing the related information, wherein the related information comprises the sample type.
Further, the processor 1001 may call a detection program for grain level detection stored in the memory 1005, and also perform the following operations:
synthesizing a plurality of sample images, processing spectral data and image data to obtain the ratio of the indexes of the particles to be measured,
the index particles to be measured include impurities and the like.
Based on the hardware structure, the invention provides a grain grade detection method, which realizes grain grade detection by applying a multispectral technology, is easy to realize low cost and miniaturization, avoids artificial interference and reduces the requirement of professional skills of grade detection personnel.
Fig. 1 is a schematic flow chart of a grain grade detection method according to an embodiment of the present invention.
In this embodiment, the grain grade detection method includes the following steps:
s10, obtaining a plurality of sample images under the irradiation of light with a plurality of characteristic wavelengths corresponding to a sample to be detected;
s20, synthesizing a plurality of sample images, and processing spectral data and image data to obtain the ratio of the index particles to be measured;
and step S30, comparing the ratio with a preset grain grade ratio to judge the grain grade.
In order to clearly distinguish the index particles to be detected so as to judge the grain grade, different characteristic wavelengths are selected correspondingly according to different grains, a plurality of sample images under the irradiation of light of a plurality of characteristic wavelengths corresponding to the sample to be detected are obtained, the plurality of sample images are synthesized, spectral data and image data are processed, the ratio of the index particles to be detected is obtained, and the grain grade is judged by comparing the ratio with the preset grain grade ratio. After the sample image is shot, all procedures are automatically completed by a machine without manual operation, and compared with a hyperspectral image, only a plurality of important wavelength images are detected, so that the data processing amount and the acquisition cost are reduced, and the relatively low cost is realized.
For example, the characteristic wavelengths of japonica rice are 703, 811, 939, etc., the characteristic wavelengths of indica rice are 652, 733, 811, etc., the characteristic wavelengths of corn are different, and the corresponding characteristic wavelengths are different and the number is also different for different grains, specifically, taking the impurity rate as an example, the sample to be detected includes impurity particles of grains and non-grains, such as sand, rice stalks, etc., the sample to be detected doped with the impurity particles and the grain particles is subjected to information acquisition, the sample image under the illumination of all the characteristic wavelengths of the sample to be detected is acquired, so that the grains or the impurities have obvious difference information under the illumination of the characteristic wavelengths, the images of a plurality of samples are subjected to synthesis processing to obtain two-dimensional image information, the synthesized image information is digitized, the shooting background is firstly removed, only the pixel information of the grain particles and the impurity particles is left, and each pixel point has intensity values under the information of a plurality of characteristic wavelengths, and (2) making a light wave-intensity curve, wherein the abscissa is characteristic spectrum information, the ordinate is intensity information, grains and impurities can be distinguished according to the trend of the curve, a ratio is obtained for pixel points of the impurities relative to the pixel points, the impurity rate in grain grade judgment is a percentage range, for example, is less than 5%, the ratio is compared with the percentage range, and the corresponding impurity rate grade is obtained by obtaining the specific range within which the ratio falls.
Multispectral data is a three-dimensional data source, grain images under a plurality of specific wavelengths are obtained, and the grain images contain more information than common visible light images, so that the method for providing grain grade related indexes can refer to information processing of the visible light images, only the multispectral images are not easily influenced by the external environment, and the result is more accurate.
For the evaluation indexes such as rice yield, water seal and the like, a sample to be detected needs to be crushed firstly, and then the grain grade detection method is used for testing.
Before the step of obtaining the sample image of the sample to be detected under the irradiation of a certain characteristic wavelength, the method comprises the steps of obtaining relevant information of the sample to be detected and storing the relevant information, wherein the relevant information comprises the type of the sample. The grain sample detection method has the advantages that information such as types, quantity, detection batches and the like of grain samples to be detected is stored, and storage backup and result output of detection data are facilitated according to detection results.
Synthesizing a plurality of sample images, and processing spectral data and image data to obtain the ratio of the indexes of the particles to be detected, wherein the index particles to be detected comprise impurities and the like. And aiming at the breakage rate index, the grain inside grains exposed from the grain skin damage position of the index grain value to be detected.
Referring to fig. 4 to 6, the hand-held testing apparatus 100 includes: the detector comprises a detector body 1, an image acquisition device 2 and a control device 3, wherein the image acquisition device 2 is positioned at the front end of the detector body 1 and is used for acquiring a sample image of a sample to be detected under the irradiation of light with characteristic wavelength, and the control device 3 is arranged on the detector body 1 and is electrically connected with the image acquisition device 2. Through controlling means 3 control the operation of image acquisition device 2 to the focus of treating the testing sample is shot, and transmits the sample image for server 200, simple structure, the design of easy time miniaturization, portable.
Specifically, the image capturing device 2 is a ccd (charge coupled device) chip, which is made of a semiconductor material with high sensitivity, and can convert light into charges, convert the charges into digital signals through an analog-to-digital converter chip, and store the digital signals after compression in a flash memory or a built-in hard disk card inside the camera, so that data can be easily transmitted to a computer, and the image can be modified as needed and desired by means of processing of the computer. The CCD chip is composed of many light sensing units, typically in mega-pixels. When the CCD surface is irradiated by light, each photosensitive unit reflects charges on the component, and signals generated by all the photosensitive units are added together to form a complete picture.
It should be noted that, during image acquisition, focusing is performed in advance, so that a clear visible light image is displayed in the lens, and the image is acquired after exposure and filtering, thereby improving efficiency and saving time. The CCD is responsible for completing image acquisition and has automatic focusing and row connecting functions. The automatic focusing can be realized according to the distance of the sample, so that the imaging is clear.
In addition, in order to realize the irradiation of light with a plurality of characteristic wavelengths, in the present invention, the handheld inspection apparatus 100 further includes a light source assembly 4 and a light filtering assembly 5, wherein the light source assembly 4 is disposed at the front end of the inspection apparatus body 1 and is used for providing a plurality of light sources; the light filtering component 5 is positioned at the front side of the light source component 4 and is used for filtering a plurality of light sources to obtain light with characteristic wavelength; wherein, the control device 3 is electrically connected with the light source assembly 4 and the filter assembly 5. The light source of the light source assembly 4 is just exposed to the sample to be detected, and the light is filtered by the light filtering assembly 5 to obtain the required characteristic wavelength light, so that the sample image acquired by the image acquisition device 2 is not a visible light image, but the filtered characteristic wavelength light, and the operation is convenient.
In order to realize the light filtering function, the light filtering component 5 comprises an annular mounting plate 51 and a light filter structure, the annular mounting plate 51 is sleeved at the front end of the detector body 1, the annular mounting plate 51 is provided with a light transmitting hole 511, the light filter structure is installed on the annular mounting plate 51 along the rotation of the front and back axial lines, the light filter structure comprises a plurality of light filters 5211 which are arranged in sequence, each light filter 5211 can be rotated to the cover to be arranged at the light transmitting hole 511. By adjusting the light filters 5211 to correspond to the light holes 511, the light filters 5211 with different colors can filter light with different characteristic wavelengths, and the structure is simple and easy to implement.
Further, since the light source passes through the optical filter 5211, the light with different wavelengths may be irradiated to the sample, and the CCD photographs once every time the optical filter 5211 rotates, the image information of all the important wavelengths is collected.
Moreover, the filtering component 5 further comprises an end cover, the end cover is detachably mounted on the annular mounting plate 51, and the end cover corresponds to the light hole 511 and is provided with a through hole. To protect the optical filter 5211. The opening and closing of the end cap and the rotation of the structure of the optical filter 5211 are both driven mechanically, and the mechanical drive is controlled by the control device 3, so that the optical filter 5211 of the next wavelength can be rotated to the light hole 511 every time a signal is received.
Moreover, the handheld detector 100 further includes a display screen disposed on the outer surface of the detector body 1, and the display screen is electrically connected to the image acquisition assembly and the control device 3. So as to facilitate the information acquisition input and grade detection result display of the grade sample to be detected. The display screen can realize the display of information and the interaction with the detection personnel, and can be a touch screen.
In this embodiment, the handheld detector 100 further includes a power supply assembly, which is located at the rear end of the detector body 1 and electrically connected to the light source assembly 4, the filtering assembly 5, the image capturing assembly, and the control assembly. The power supply is provided through the battery pack, an external power line is not needed, the moving range of the handheld detector is enlarged, and the handheld detector is more convenient and fast.
Specifically, in this embodiment, in order to enhance the effect, the light source assembly 4 has two light sources arranged oppositely, and two light holes 511 are correspondingly arranged; the optical filter structure comprises two optical filter segments 521 arranged in a central symmetry manner, each optical filter segment 521 is provided with a plurality of optical filters 5211 which are sequentially arranged, and the two optical filters 5211 which are oppositely arranged can rotate to cover the corresponding light holes 511. The two filter segments 521 can rotate simultaneously, the two symmetrical filters 5211 have the same color, the light holes 511 can be covered simultaneously, and the purpose of using two light sources is to keep symmetry, reduce the generation of shadows and ensure the quality of hyperspectral images.
It should be noted that the characteristic wavelengths of japonica rice are 703, 811, 939, etc., the characteristic wavelengths of indica rice are 652, 733, 811, etc., and the characteristic wavelengths of corn are different, and the characteristic wavelengths of corresponding grains are different, so different filters 5211 are customized for different types of grains, the filter 5211 corresponding to japonica rice is changed when japonica rice is detected, and the filter 5211 corresponding to indica rice is changed when indica rice is detected.
The selection of the characteristic wavelength has a special model, and a large amount of work needs to be done in the early stage, which is specifically as follows: under the condition of unknown specific wavelength, firstly, the hyperspectral equipment is used for collecting data of all wave bands, and a full-wave-band grade detection model is established. And selecting certain specific wavelengths by utilizing algorithms such as PCA (principal component analysis), LASSO (laser absorption optical spectroscopy) and the like, establishing a level detection model of the characteristic wave band, and if the selected level detection model of the characteristic wave band has the same result as the full-wave-band model, indicating that the effect of the full-wave-band model can be achieved only by acquiring data of the characteristic wave band. For the existing grains such as japonica rice, indica rice, corn and the like, the characteristic wavelength is determined before the optical filter 5211 is manufactured.
The control device 3 is the core of the whole handheld detector 100 and is responsible for controlling each component of the handheld detector to coordinate and complete the whole process of sample detection. After the inspector presses the start button, the control device 3 sends a signal to the CCD for focusing, and displays the result of focusing of the CCD on the display screen, and the focusing process is completed, the control device 3 sends a signal to the light source assembly 4 and the light filtering assembly 5 respectively, the two symmetrical light sources instantly release strong light, after the light filtering assembly 5 filters the light, the light with specific wavelength irradiates the sample, the CCD collects the image corresponding to the wavelength, stores the image in the control device 3, and displays and transmits the image to the server 200. After the control device 3 finishes collecting the images with 1 wavelength, the optical filter 5211 in the optical filter assembly 5 is driven to rotate once, and the operation is repeated to collect the image with the 2 nd wavelength, and the process is repeated until the collection of the images with all wavelengths is finished. These images are processed in the server 200, and after the result is obtained, the result is fed back to the control device 3 of the handheld test apparatus 100 for display.
Specifically, the detailed detection steps are as follows:
from the grain to be detected, a large sample of about 500g is taken according to the sampling rule required by the national standard, and then a small amount of sample is taken from the large sample and is flatly paved on white paper or a white board, so that grains are required to be separated as far as possible and are not mutually overlapped, and the subsequent image processing is facilitated;
the server 200 and the handheld detector 100 are opened, the control device 3 in the handheld detector 100 is automatically in communication connection with the server 200, after the handheld detector 100 is ready, the display screen prompts to input relevant information of grain samples to be detected, and the input information is transmitted to the server 200 through the control device 3 for recording;
after the initial information is input, an image alignment button is clicked on the display screen, the control device 3 in the handheld detector 100 sends a signal to the CCD for focusing, and if necessary, the focusing lens of the CCD can be manually adjusted, so that a clear visible light image of the grain sample is presented on the display screen;
when the image capture button is clicked on the display screen, the control device 3 in the handheld inspection device 100 will send a signal to the light source assembly 4, and the two light sources will instantly emit strong light of 400-2000 nm. After the strong light passes through the light filtering component 5, only the light filter 5211 in the light hole 511 is activated, only the light under a certain characteristic wavelength is transmitted, and the light of other wavelengths is completely filtered;
the light filtered by the filter component 5 can irradiate the grain sample and then is reflected to the CCD, and the image of the sample collected by the CCD under a certain characteristic wavelength is obtained. This image data is immediately transmitted to the server 200 through the control device 3;
after receiving the image information, the server 200 will send a confirmation signal to the handheld inspection device 100, and the handheld inspection device 100 will automatically rotate the filter 5211 so that the filter 5211 with the next characteristic wavelength is located at the light hole 511 of the filter assembly 5. Then, under the control of the control device 3 in the handheld detector 100, the processes of exposure, image acquisition, data transmission and the like are sequentially completed, and the image acquisition and recording process of a second characteristic wavelength is completed;
after receiving the image information, the server 200 will send a confirmation signal to the handheld detector 100 again, and the handheld detector 100 will automatically repeat the above steps to complete the image acquisition and recording of the third characteristic wavelength, and so on until all characteristic wavelengths are acquired;
after the data acquisition is completed, the server 200 processes the data according to preset processing software to provide relevant indexes of the grain grade. These rating measurements are reported to the hand-held test meter 100 for easy viewing by the relevant personnel. Meanwhile, the detection result is recorded in the database, so that the next effective management is facilitated.
In different application scenarios, the control device 3 includes a memory, a processor, and a grain level detection program stored in the memory and executable on the processor, and the grain level detection program is configured to implement the steps of the grain level detection method. The server 200 is used for analyzing and then feeding back, the method is suitable for large grain depot scenes, communication between the server 200 and the handheld detector 100 is smooth, the given result is faster, and the result is recorded in the server 200 immediately, so that the result of manually changing grades can be prevented, and the phenomenon of being full of quality is avoided. The handheld detector 100 is only used for calculation, so that the handheld detector is suitable for a scene that small-sized grain purchasing merchants purchase grains at the homes of farmers, and at the moment, networks may not exist, the analysis result is slow, but the analysis result can be referred by the purchasing merchants, and the grain purchasing price is determined more accurately. Specifically, the handheld inspection device 100 is provided with a processing chip therein to satisfy real-time processing.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and all modifications and equivalents of the present invention, which are made by the contents of the present specification and the accompanying drawings, or directly/indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A grain grade detection method is used for a server or a handheld detector, and is characterized by comprising the following steps:
obtaining a plurality of sample images under the irradiation of light with a plurality of characteristic wavelengths corresponding to a sample to be detected;
synthesizing a plurality of sample images, and processing spectral data and image data to obtain the ratio of the index particles to be measured;
and comparing the ratio with a preset grain grade ratio to judge the grain grade.
2. The grain grade detection method of claim 1, wherein the step of obtaining a sample image of the sample to be detected under irradiation of a certain characteristic wavelength is preceded by:
and acquiring related information of the sample to be detected, and storing the related information, wherein the related information comprises the sample type.
3. The grain grade detecting method according to claim 1, wherein in the step of synthesizing a plurality of sample images, performing spectral data and image data processing to obtain a ratio of indexes of the grains to be measured,
the index particles to be measured include impurities and the like.
4. A hand-held test meter, comprising:
a detector body;
the image acquisition device is positioned at the front end of the detector body and is used for acquiring a sample image of a sample to be detected under the irradiation of light with characteristic wavelength; and the number of the first and second groups,
and the control device is arranged on the detector body and is electrically connected with the image acquisition device.
5. The hand-held test meter of claim 4, wherein the hand-held test meter further comprises:
the light source assembly is arranged at the front end of the detector body and used for providing a plurality of light sources; and the number of the first and second groups,
the light filtering component is positioned at the front side of the light source component and is used for filtering the light sources to obtain light with characteristic wavelength;
wherein, the control device is electrically connected with the light source component and the light filtering component.
6. The hand-held measuring instrument of claim 5, wherein the filter assembly comprises:
the annular mounting plate is sleeved at the front end of the detector body and provided with a light transmission hole; and the number of the first and second groups,
the optical filter structure is rotatably installed on the annular installation plate along the front-back axis and comprises a plurality of optical filters which are sequentially arranged, and each optical filter can rotate to cover the light holes.
7. The hand-held measuring instrument of claim 6, wherein the light source assembly has two oppositely disposed light sources, and two corresponding light holes are provided;
the light filter structure comprises two light filter segments which are arranged in a central symmetry manner, each light filter segment is provided with a plurality of light filters which are arranged in sequence, and the two light filters which are arranged oppositely can rotate to cover to form corresponding light holes.
8. The hand-held measuring instrument according to claim 4, wherein the control device comprises a memory, a processor and a detection program for grain level detection stored on the memory and executable on the processor, the detection program for grain level detection being configured to implement the steps of the grain level detection method according to any one of claims 1 to 3.
9. A server, characterized in that the server comprises a memory, a processor and a detection program for grain level detection stored on the memory and operable on the processor, the detection program for grain level detection being configured to implement the steps of the grain level detection method according to any one of claims 1 to 3.
10. A food grade detection system comprising a server as claimed in claim 9 and at least one hand-held detector as claimed in claims 4 to 7, each hand-held detector being communicatively connected to the server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011011837.8A CN112082913A (en) | 2020-09-23 | 2020-09-23 | Grain grade detection method and system, handheld detector and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011011837.8A CN112082913A (en) | 2020-09-23 | 2020-09-23 | Grain grade detection method and system, handheld detector and server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112082913A true CN112082913A (en) | 2020-12-15 |
Family
ID=73739629
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011011837.8A Pending CN112082913A (en) | 2020-09-23 | 2020-09-23 | Grain grade detection method and system, handheld detector and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112082913A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103698009A (en) * | 2013-12-25 | 2014-04-02 | 北京农业智能装备技术研究中心 | Multispectral image acquiring method and system on basis of line scanning hyperspectral imaging |
| CN103954570A (en) * | 2014-04-21 | 2014-07-30 | 江苏大学 | Food insect attack degree distinguishing method based on spectral imaging technology |
| CN106323909A (en) * | 2016-09-14 | 2017-01-11 | 江苏大学 | Handheld near infrared spectrum detection system and detection method for quality of fruits and vegetables |
| CN109580492A (en) * | 2017-09-28 | 2019-04-05 | 孙凯 | A kind of rice quality detection method |
| CN109580521A (en) * | 2019-01-21 | 2019-04-05 | 浙江创谱科技有限公司 | A kind of infrared spectroscopy food detector |
| CN109668843A (en) * | 2019-01-07 | 2019-04-23 | 江苏大学 | A method of the Portable multiple spectrum imaging technique based on mobile phone detects bacon quality |
-
2020
- 2020-09-23 CN CN202011011837.8A patent/CN112082913A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103698009A (en) * | 2013-12-25 | 2014-04-02 | 北京农业智能装备技术研究中心 | Multispectral image acquiring method and system on basis of line scanning hyperspectral imaging |
| CN103954570A (en) * | 2014-04-21 | 2014-07-30 | 江苏大学 | Food insect attack degree distinguishing method based on spectral imaging technology |
| CN106323909A (en) * | 2016-09-14 | 2017-01-11 | 江苏大学 | Handheld near infrared spectrum detection system and detection method for quality of fruits and vegetables |
| CN109580492A (en) * | 2017-09-28 | 2019-04-05 | 孙凯 | A kind of rice quality detection method |
| CN109668843A (en) * | 2019-01-07 | 2019-04-23 | 江苏大学 | A method of the Portable multiple spectrum imaging technique based on mobile phone detects bacon quality |
| CN109580521A (en) * | 2019-01-21 | 2019-04-05 | 浙江创谱科技有限公司 | A kind of infrared spectroscopy food detector |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6038965B2 (en) | Coloring inspection apparatus and coloring inspection method | |
| US10168215B2 (en) | Color measurement apparatus and color information processing apparatus | |
| Lu et al. | Hyperspectral imaging for safety inspection of food and agricultural products | |
| CN103018180B (en) | Method and device for detecting cotton diseases based on multisource light information technology | |
| US8315692B2 (en) | Multi-spectral imaging spectrometer for early detection of skin cancer | |
| US20120061586A1 (en) | Method and detection system for detection of aflatoxin in corn with fluorescence spectra | |
| CN105021617B (en) | Whole strain chlorophyll content of rice measurement apparatus and method based on high light spectrum image-forming | |
| CN101692052B (en) | Hyperspectrum image technique-based method and hyperspectrum image technique-based device for identifying true and false famous tea | |
| WO2016044521A1 (en) | Test and measurement system with removable imaging tool | |
| IL288218B2 (en) | Apparatus and method for fluorescence grading of gemstones | |
| CN101832941A (en) | Fruit quality evaluation device based on multispectral image | |
| DE102018103509B3 (en) | Mobile ingredient analysis system as well as procedures for sample-correct measurement and user guidance with this | |
| CN102253025A (en) | Composite fluorescence imaging system applied in forensic science evidence testing, and application method thereof | |
| CN102621116A (en) | Detection device and method for quality evaluation of American ginseng | |
| US20130262008A1 (en) | Measurement of light-absorption qualities in the visible spectrum using a camera | |
| US20200196869A1 (en) | A hand-held biophotonic medical device, method and system for multimodal and multispectral imaging of a tissue | |
| CN101021488A (en) | Method and apparatus for detecting rice damage | |
| RU2726257C1 (en) | Apparatus for automatic measurement of plant parameters | |
| CN109100337A (en) | Multiband multi-orientation detection device and detection method | |
| CN112082913A (en) | Grain grade detection method and system, handheld detector and server | |
| CN112464017B (en) | Infrared material evidence extractor, spectral feature library establishing method and utilization method | |
| JP4247362B2 (en) | Feature extraction device | |
| US20150365608A1 (en) | Inspection arrangement and inspection method for a solar installation | |
| CN201051074Y (en) | Multi-spectrum flesh verdure artificial intelligence measurement system | |
| CN104345039B (en) | A kind of wheat water content rapid assay methods based on image processing techniques |
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 |
Application publication date: 20201215 |
|
| RJ01 | Rejection of invention patent application after publication |