CN109030755A - The detection device and method of grain moisture content, mass of 1000 kernel and bulk density based on image processing techniques - Google Patents
The detection device and method of grain moisture content, mass of 1000 kernel and bulk density based on image processing techniques Download PDFInfo
- Publication number
- CN109030755A CN109030755A CN201810673175.7A CN201810673175A CN109030755A CN 109030755 A CN109030755 A CN 109030755A CN 201810673175 A CN201810673175 A CN 201810673175A CN 109030755 A CN109030755 A CN 109030755A
- Authority
- CN
- China
- Prior art keywords
- grain
- kernel
- mass
- moisture content
- bulk density
- 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
Classifications
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01G—WEIGHING
- G01G17/00—Apparatus for or methods of weighing material of special form or property
- G01G17/04—Apparatus for or methods of weighing material of special form or property for weighing fluids, e.g. gases, pastes
Abstract
The invention discloses the detection devices of a kind of grain moisture content based on image processing techniques, mass of 1000 kernel and bulk density, comprising: workbench；Template, place on the table, be uniformly arranged in the template it is fluted, for the grain that tiles；Support rod, setting is on the workbench；Image acquisition device, liftable is arranged on the support rod, for acquiring the original image of grain.The present invention also provides the detection method of a kind of grain moisture content based on image processing techniques, mass of 1000 kernel and bulk density, can accurate rapid survey grain moisture content, mass of 1000 kernel and bulk density, realize the more quality parameters of quick nondestructive and disposably detect；It is not limited by Crop Group and kind；Breach the high Humid Area high moisture grain in Northeast Cold Area and south can not rapid survey problem；Influenced by ambient temperature and humidity it is small, night shift without temperature and humidity correct；Structure is simple, easy to operate, and continuity is good, avoids overlapped, interference between grain seed, improves detection accuracy.
Description
Technical field
The present invention relates to grain moisture content and Quality Detection technical fields, it is more particularly related to a kind of based on figure
As the detection device and method of the grain moisture content of processing technique, mass of 1000 kernel and bulk density.
Background technique
China is one of main Chan Liang state of the world as large agricultural country, and the quality of grain quality is most important, and in grain
Moisture content be influence grain quality an important factor for one of.Grain moisture content is excessively high to be easy to produce fever, mildew and infested etc.
Physiological change should not save.Grain moisture content is too low to will lead to organic substance reduction inside grain, and dry biomass reduces, and influences
Grain quality.Therefore, the quick accurate detection of grain moisture content may insure foodstuff preservation, and processing and commercialization are gone on smoothly.
Currently used grain measurement of moisture content method specifically includes that Oven Method, electric-resistivity method, capacitance method, Near-Infrared Absorption Method.Wherein
The water content detection of cereal is subject to Oven Method, is chiefly used in laboratory precise measurement, measurement period is long, and real-time is poor.Electric-resistivity method benefit
With the difference of grain moisture content and its conductivity, broken by grain by carrying out to grain, detection cereal resistance value is reacted indirectly
The problems such as its water content, this method are destructive detection, and there are sampling difficulties, poor anti jamming capability, need to carry out temperature and humidity correction,
It is poor particularly with the detection accuracy of high moisture grain.Capacitance method and Near-Infrared Absorption Method belong to non-destructive testing, but Near-Infrared Absorption Method pair
Environmental requirement is high, and cost is larger, is only applicable to laboratory testing.Capacitance detecting method utilizes the dielectric constant of moisture in grain
Much larger than the dielectric constant of other compositions in grain, cereal kernel group to be measured is sent into inside the container equipped with capacitance sensor,
The capacitance of acquisition cereal reacts its water content indirectly, and this method equally exists poor for the detection accuracy of high moisture grain
The problem of, and since the relative dielectric constant in measured zone is by cereal porosity, cereal dry matter, moisture, air and environment
Temperature and humidity, electromagnetic field effects are larger, therefore must assure that cereal capacity is identical with porosity in measured zone when each detection, and
Cereal capacity is sufficiently large, to guarantee measurement accuracy.
With the rapid development of computer technology, the NI Vision Builder for Automated Inspection based on image processing techniques is more and more answered
Grain context of detection is used, unique advantage has been shown.
Chinese patent 201310329180.3 " a kind of wheat water content rapid assay methods based on image processing techniques ", benefit
With the difference of wheat water content and its color, the Color characteristics parameters in wheat image to be measured are extracted with image processing techniques,
And the moisture content of wheat is calculated according to the mathematical model demarcated in advance.The test object of this method is wheat, and application surface is opposite
Relatively narrow, wheat color is unobvious with its aqueous magnitude relation compared with deep, and measurement accuracy is poor, while needing to slide sample room and connecting to reach
The purpose of continuous detection, continuity are poor.
Chinese patent 201310216793.6 " a kind of method and device for measuring thousand grain weigth ", by weight method and image
Processing technique combines, and extracts its quantity of the profile line computation of seed, root in grain image to be measured with image processing techniques
The mass of 1000 kernel that weight calculates seed is measured according to the quantity and its of seed.The suitable measurement accuracy of this method is poor.
Summary of the invention
It is an object of the invention to designed and developed a kind of grain moisture content based on image processing techniques, mass of 1000 kernel and
Grain can quickly be paved non-overlapping, raising detection accuracy by the detection device of bulk density.
Another object of the present invention be designed and developed a kind of grain moisture content based on image processing techniques, mass of 1000 kernel with
And the detection method of bulk density, it being capable of accurate rapid survey grain moisture content, mass of 1000 kernel and bulk density.
Technical solution provided by the invention are as follows:
A kind of detection device of grain moisture content based on image processing techniques, mass of 1000 kernel and bulk density, comprising:
Workbench；And
Template, place on the workbench, be uniformly arranged in the template it is fluted, for the grain that tiles；
Support rod, setting is on the workbench；
Image acquisition device, liftable is arranged on the support rod, for acquiring the original image of grain.
Preferably, further includes:
Processor is connect with described image collector；
Electronic scale, setting on the workbench, and are connected to the processor；
Display screen is connected to the processor, for showing testing result.
The measuring method of a kind of grain moisture content based on image processing techniques, mass of 1000 kernel and bulk density, includes the following steps:
Step 1: more seeds to be tested being tiled, acquire seed group original image, and carry out to the original image
Pretreatment；
Step 2: obtain elemental area in seed group forward projection domain:
In formula,For seed sets of pixels area,For the elemental area of i-th seed, n is seed number；
Step 3: obtain seed group real area:
In formula, XaFor seed group's real area；K is the conversion coefficient of Pixel Dimensions and actual size；
Step 4: obtain grain moisture content:
M=AMXa+BM
In formula, M is grain moisture content；AM, BMFor grain moisture content coefficient.
Preferably, further includes:
Obtain grain mass of 1000 kernel:
M=AmXa 2+BmXa+Cm
In formula, m is grain mass of 1000 kernel；Am, Bm, CmFor grain mass of 1000 kernel coefficient.
Preferably, further includes:
Obtain grain volume weight:
D=AdXa 2+BdXa+Cd
In formula, d is grain mass of 1000 kernel；Ad, Bd, CdFor grain volume weight coefficient.
Preferably, carrying out pretreatment to the original image in the step 1 includes:
The R component in RGB original image is extracted as gray level image；
It calculates gray level image threshold value automatically using maximum variance between clusters and carries out Binary Sketch of Grey Scale Image；
Erosion operation, area filtering, boundary removal and holes filling are carried out to the bianry image.
Preferably, the conversion coefficient K=0.0071 of the Pixel Dimensions and actual size.
Preferably, the grain moisture content, mass of 1000 kernel and bulk density peg model are established by least square method.
Preferably, the grain moisture content coefficient meets:
1.13≤AM≤2.15,-160.5≤BM≤-80.4。
Preferably, the grain mass of 1000 kernel coefficient meets:
0.92≤Am≤1.86,-225.12≤Bm≤-121.32,7600≤Cm≤7900。
Preferably, the grain volume weight coefficient meets:
-0.72≤Ad≤-0.41,71.35≤Bd≤110.56,-3015.7≤Cd≤-2689.5。
Preferably,
When grain is corn, n >=30；
When grain is rice or wheat, n >=100.
It is of the present invention the utility model has the advantages that
1, the more quality parameters of quick nondestructive are realized disposably to detect.
2, it is not limited by Crop Group and kind.
3, breach the high Humid Area high moisture grain in Northeast Cold Area and south can not rapid survey problem.
4, influenced by ambient temperature and humidity it is small, night shift without temperature and humidity correct.
5, structure is simple, easy to operate, and continuity is good, avoids overlapped, interference between grain seed, improves inspection
Survey precision.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of detection system of the present invention.
Fig. 2 is the structural schematic diagram of template of the present invention.
Fig. 3 is the flow chart of the present invention for establishing peg model.
Fig. 4 is the flow chart of detection process of the present invention.
Specific embodiment
Present invention will be described in further detail below with reference to the accompanying drawings, to enable those skilled in the art referring to specification text
Word can be implemented accordingly.
As shown in Figure 1, 2, the present invention provides a kind of grain moisture content based on image processing techniques, mass of 1000 kernel and bulk density
Detection system includes: workbench 100, template 200 (template colors are one of dark color such as black, green, blue), the mould
Plate 200 is designed according to different grain shape and size, has different type hole numbers (i.e. groove), it can be achieved that seed to be measured
Grain it is quick, accurately, non-overlapping tiling, support rod 300, image acquisition device 400, processor 500, display 600, auxiliary equipment
700.The workbench 100 which is provided with support rod 300 for placing template 200.The liftable fixation of image acquisition device 400
It is connected on the support rod 300 and with processor 500, to acquire the original image of grain to be measured.It is equipped in processor 500
The control system of image processing program and well-established peg model, to handle acquired image and calculate grain water
Point, mass of 1000 kernel and bulk density.Display 600 is connected with processor 500, to show measurement result.Auxiliary equipment 700 is with logical
The electronic scale of communication interface, to improve mass of 1000 kernel measurement accuracy.
When measurement, workbench is placed horizontally at using the certain grain number grain of 200 grab sample of template (non-overlapping tiling)
100, grain seed group original image to be measured is obtained by image acquisition device 400 and is transmitted to the progress image procossing of processor 500
And the calculating of grain moisture content, mass of 1000 kernel and bulk density, measurement result are shown by display 600.Or it can be replaced with auxiliary equipment 700
Workbench 100 is realized and obtains its weight while acquiring grain image to be measured, and real-time Transmission improves thousand to processor 500
Resurvey accuracy of measurement.
The detection device of grain moisture content of the present invention based on image processing techniques, mass of 1000 kernel and bulk density, can
Grain is quickly paved to non-overlapping, raising detection accuracy.
The present invention also provides the measuring method of a kind of grain moisture content based on image processing techniques, mass of 1000 kernel and bulk density,
Include the following steps:
The implementation case selects corn as laboratory sample, and image acquisition device is HP M1216nfh scanner, wherein is swept
Retouching instrument output image is jpeg format, and image pixel dimensions are 2550 × 3506, and image actual size is 214 × 296.8mm.
Step 1: the peg model of grain moisture content M, grain mass of 1000 kernel m and grain volume weight d are established, as shown in Figure 3；
Step 1.1 after corn cleaning cleans, makes calibration sample by different in moisture gradient.
Step 1.2, the grain according to as defined in national standard " inspection of grain and oil Volume-weight Determination " GB/T 5498-2013, oil plant hold
The measuring method of weight carries out bulk density measurement to the calibration sample.
Step 1.3 is weighed using 100 corns of template grab sample (non-overlapping tiling), is accurate to 1g.
Template in step 1.3 is placed in scanner by step 1.4, carries out seed group scan original image.
Step 1.5 demarcates original image described in step 1.4, determines the conversion of Pixel Dimensions and actual size
COEFFICIENT K:
It should be noted that Pixel Dimensions and the conversion coefficient K of actual size are come out according to the parameter conversion of scanner
, the conversion coefficient of different image acquisition devices is different.
Step 1.6 pre-processes the original image, comprising: color image gray processing, Binary Sketch of Grey Scale Image and
Morphological operation.
(1), color image gray processing: the R component in RGB original image is extracted as gray level image.
(2), gray level image threshold value Binary Sketch of Grey Scale Image: is calculated using maximum variance between clusters (Ostu algorithm) automatically.
(3), erosion operation, area filtering, boundary removal, holes filling morphological operation: are carried out to bianry image in (2)
Deng operation.
Step 1.7, the seed sets of pixels area for calculating bianry image in (3)
Wherein,For seed sets of pixels area；The elemental area of i-th seed；N is seed number, n=100.
Step 1.8, by the elemental areaIt is converted into real area Xa:
Wherein, XaFor seed group's real area；For seed sets of pixels area；K is changing for Pixel Dimensions and actual size
Calculate coefficient, K=0.0071.
Step 1.9, the peg model that corn moisture M is established using least square method:
M=AMXa+BM
Wherein, M is grain moisture content；XaFor seed group's real area；AM, BMFor grain moisture content coefficient, AM1.13~2.15
Between, BMBetween -160.5~-80.4.
Step 1.10, the peg model that corn mass of 1000 kernel m is established using least square method:
M=AmXa 2+BmXa+Cm
Wherein, m is grain mass of 1000 kernel；XaFor seed group's real area；Am, Bm,CmFor grain mass of 1000 kernel coefficient, Am0.92
Between~1.86, BmBetween -225.12~-121.32, CmBetween 7600~7900.
Step 1.11, the peg model that corn bulk density d is established using least square method:
D=AdXa 2+BdXa+Cd
Wherein, d is grain mass of 1000 kernel；XaFor seed group's real area；Ad, Bd,CdFor grain volume weight coefficient, Ad- 0.72
Between~-0.41, BdBetween 71.35~110.56, CmBetween -3015.7~-2689.5.
Step 2: moisture, mass of 1000 kernel and the bulk density of corn to be tested are measured using peg model, as shown in Figure 4；
Step 2.1 utilizes 100 corns of template grab sample (non-overlapping tiling).
The template is placed in scanner by step 2.2, obtains grain seed group's original image to be measured.
Step 2.3 pre-processes the original image, comprising: color image gray processing, Binary Sketch of Grey Scale Image and
Morphological operation.
(1), color image gray processing: the R component in RGB original image is extracted as gray level image.
(2), Binary Sketch of Grey Scale Image: the threshold of gray level image is calculated automatically using maximum variance between clusters (Ostu algorithm)
Value.
(3), erosion operation, area filtering, boundary removal, holes filling morphological operation: are carried out to bianry image in (2)
Deng.
Step 2.4, the seed sets of pixels area for calculating bianry image in (3)
Wherein,For seed sets of pixels area；The elemental area of simple grain seed, n are seed number, n=100.
Step 2.5 is by the seed sets of pixels areaIt is converted into real area Xa:
Wherein, XaFor seed group's real area；For seed sets of pixels area；K is changing for Pixel Dimensions and actual size
Calculate coefficient, K=0.0071.
Step 2.6 calculates corn moisture M, mass of 1000 kernel m and bulk density d to be measured using peg model.
Embodiment
Step 1: the peg model of grain moisture content M, grain mass of 1000 kernel m and grain volume weight d are determined
Step 1.1 after corn cleaning cleans, makes calibration sample by different in moisture gradient.
Step 1.2, the grain according to as defined in national standard " inspection of grain and oil Volume-weight Determination " GB/T 5498-2013, oil plant hold
The measuring method of weight carries out bulk density measurement to the calibration sample.
Step 1.3 is weighed using 100 corns of template grab sample (non-overlapping tiling), is accurate to 1g.
Template in step 1.3 is placed in scanner by step 1.4, carries out seed group scan original image.
Step 1.5 demarcates original image described in step 1.4, determines the conversion of Pixel Dimensions and actual size
COEFFICIENT K:
Step 1.6 pre-processes the original image, comprising: color image gray processing, Binary Sketch of Grey Scale Image and
Morphological operation.
(1), color image gray processing: the R component in RGB original image is extracted as gray level image.
(2), gray level image threshold value Binary Sketch of Grey Scale Image: is calculated using maximum variance between clusters (Ostu algorithm) automatically.
(3), erosion operation, area filtering, boundary removal, holes filling morphological operation: are carried out to bianry image in (2)
Deng operation.
Step 1.7, the seed sets of pixels area for calculating bianry image in (3)
Wherein,For seed sets of pixels area,；The elemental area of i-th seed；N is seed number, n=100.
Step 1.8, by the elemental areaIt is converted into real area Xa:
Xa=0.0071Xa *
Wherein, XaFor seed group's real area；For seed sets of pixels area；K is changing for Pixel Dimensions and actual size
Calculate coefficient.
Step 1.9 obtains the peg model of corn moisture M using least square method:
M=1.61Xa-117.77
Wherein, M is grain moisture content；XaFor seed group's real area；AM, BMFor grain moisture content coefficient,.
Step 1.10 obtains the peg model of corn mass of 1000 kernel m using least square method:
M=1.11Xa 2-187.97Xa+7800.8
Wherein, m is grain mass of 1000 kernel；XaFor seed group's real area；Am, Bm,CmFor grain mass of 1000 kernel coefficient.
Step 1.11 obtains the peg model of corn bulk density d using least square method:
D=-0.58Xa 2+91.35Xa-2849.5
Wherein, d is grain mass of 1000 kernel；XaFor seed group's real area；Ad, Bd,CdFor grain volume weight coefficient.
Step 2: moisture, mass of 1000 kernel and the bulk density of corn to be tested are measured using peg model；
Step 2.1 utilizes 100 corns of template grab sample (non-overlapping tiling).
The template is placed in scanner by step 2.2, obtains grain seed group's original image to be measured.
Step 2.3 pre-processes the original image, comprising: color image gray processing, Binary Sketch of Grey Scale Image and
Morphological operation.
(1), color image gray processing: the R component in RGB original image is extracted as gray level image.
(2), Binary Sketch of Grey Scale Image: the threshold of gray level image is calculated automatically using maximum variance between clusters (Ostu algorithm)
Value.
(3), erosion operation, area filtering, boundary removal, holes filling morphological operation: are carried out to bianry image in (2)
Deng.
Step 2.4, the seed sets of pixels area for calculating bianry image in (3)
Wherein,For seed sets of pixels area；The elemental area of simple grain seed, n are seed number, n=100.
Step 2.5 is by the seed sets of pixels areaIt is converted into real area Xa:
Xa=0.0071Xa *=82.63
Wherein, XaFor seed group's real area (cm2)；For seed sets of pixels area；K is Pixel Dimensions and actual size
Conversion coefficient.
Step 2.6 calculates corn moisture M:14.9%, mass of 1000 kernel m:355g, bulk density d to be measured using obtaining peg model:
727g/L。
The detection method of grain moisture content of the present invention based on image processing techniques, mass of 1000 kernel and bulk density, can
Accurate rapid survey grain moisture content, mass of 1000 kernel and bulk density.The more quality parameters of quick nondestructive are realized disposably to detect；Do not made
Species not and kind limitation；Breach the high Humid Area high moisture grain in Northeast Cold Area and south can not rapid survey difficulty
Topic；Influenced by ambient temperature and humidity it is small, night shift without temperature and humidity correct；Structure is simple, easy to operate, and continuity is good, avoids
Overlapped, interference between grain seed, improve detection accuracy.
Although the embodiments of the present invention have been disclosed as above, but its is not only in the description and the implementation listed
With it can be fully applied to various fields suitable for the present invention, for those skilled in the art, can be easily
Realize other modification, therefore without departing from the general concept defined in the claims and the equivalent scope, the present invention is simultaneously unlimited
In specific details and legend shown and described herein.
Claims (10)
1. the detection device of a kind of grain moisture content based on image processing techniques, mass of 1000 kernel and bulk density, which is characterized in that packet
It includes:
Workbench；And
Template, place on the workbench, be uniformly arranged in the template it is fluted, for the grain that tiles；
Support rod, setting is on the workbench；
Image acquisition device, liftable is arranged on the support rod, for acquiring the original image of grain.
2. the detection device of the grain moisture content based on image processing techniques, mass of 1000 kernel and bulk density as described in claim 1,
It is characterized in that, further includes:
Processor is connect with described image collector；
Electronic scale, setting on the workbench, and are connected to the processor；
Display screen is connected to the processor, for showing testing result.
3. the detection method of a kind of grain moisture content based on image processing techniques, mass of 1000 kernel and bulk density, which is characterized in that including
Following steps:
Step 1: more seeds to be tested being tiled, acquire seed group original image, and located in advance to the original image
Reason；
Step 2: obtain elemental area in seed group forward projection domain:
In formula,For seed sets of pixels area,For the elemental area of i-th seed, n is seed number；
Step 3: obtain seed group real area:
In formula, XaFor seed group's real area；K is the conversion coefficient of Pixel Dimensions and actual size；
Step 4: obtain grain moisture content:
M=AMXa+BM
In formula, M is grain moisture content；AM, BMFor grain moisture content coefficient.
4. the detection method of the grain moisture content based on image processing techniques, mass of 1000 kernel and bulk density as claimed in claim 3,
It is characterized in that, further includes:
Obtain grain mass of 1000 kernel:
M=AmXa 2+BmXa+Cm
In formula, m is grain mass of 1000 kernel；Am, Bm, CmFor grain mass of 1000 kernel coefficient.
5. the detection method of the grain moisture content based on image processing techniques, mass of 1000 kernel and bulk density as claimed in claim 3,
It is characterized in that, further includes:
Obtain grain volume weight:
D=AdXa 2+BdXa+Cd
In formula, d is grain mass of 1000 kernel；Ad, Bd, CdFor grain volume weight coefficient.
6. the detection side of the grain moisture content based on image processing techniques, mass of 1000 kernel and bulk density as described in claim 3,4 or 5
Method, which is characterized in that carrying out pretreatment to the original image in the step 1 includes:
The R component in RGB original image is extracted as gray level image；
It calculates gray level image threshold value automatically using maximum variance between clusters and carries out Binary Sketch of Grey Scale Image；
Erosion operation, area filtering, boundary removal and holes filling are carried out to the bianry image.
7. the detection method of the grain moisture content based on image processing techniques, mass of 1000 kernel and bulk density as claimed in claim 6,
It is characterized in that, the conversion coefficient K=0.0071 of the Pixel Dimensions and actual size.
8. the detection method of the grain moisture content based on image processing techniques, mass of 1000 kernel and bulk density as claimed in claim 3,
It is characterized in that, the grain moisture content coefficient meets:
1.13≤AM≤2.15,-160.5≤BM≤-80.4。
9. the detection method of the grain moisture content based on image processing techniques, mass of 1000 kernel and bulk density as claimed in claim 4,
It is characterized in that, the grain mass of 1000 kernel coefficient meets:
0.92≤Am≤1.86,-225.12≤Bm≤-121.32,7600≤Cm≤7900。
10. the detection method of the grain moisture content based on image processing techniques, mass of 1000 kernel and bulk density as claimed in claim 5,
It is characterized in that, the grain volume weight coefficient meets:
-0.72≤Ad≤-0.41,71.35≤Bd≤110.56,-3015.7≤Cd≤-2689.5。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810673175.7A CN109030755A (en) | 2018-06-27 | 2018-06-27 | The detection device and method of grain moisture content, mass of 1000 kernel and bulk density based on image processing techniques |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810673175.7A CN109030755A (en) | 2018-06-27 | 2018-06-27 | The detection device and method of grain moisture content, mass of 1000 kernel and bulk density based on image processing techniques |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109030755A true CN109030755A (en) | 2018-12-18 |
Family
ID=64611364
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810673175.7A Pending CN109030755A (en) | 2018-06-27 | 2018-06-27 | The detection device and method of grain moisture content, mass of 1000 kernel and bulk density based on image processing techniques |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109030755A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111539920A (en) * | 2020-04-16 | 2020-08-14 | 泸州老窖酿酒有限责任公司 | Automatic detection method for fermented grain quality in white spirit brewing process |
| CN112858076A (en) * | 2021-02-25 | 2021-05-28 | 山东省农业科学院作物研究所 | Evaluation method of grain postpartum loss |
| CN112861372A (en) * | 2021-03-04 | 2021-05-28 | 中国地质调查局成都地质调查中心 | Debris flow volume weight calculation method |
| CN112907558A (en) * | 2021-03-15 | 2021-06-04 | 南京农业大学 | Full-automatic image determination method for thousand grain weight of rape seeds |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3230217B2 (en) * | 1999-06-16 | 2001-11-19 | ベルスリーニシハツ株式会社 | Dry laver quality inspection method |
| JP4143380B2 (en) * | 2002-10-29 | 2008-09-03 | 日清製粉株式会社 | Grain characteristic measurement method and apparatus |
| CN101929938A (en) * | 2009-06-25 | 2010-12-29 | 田志和 | Method and equipment for measuring volume weight of grain |
| CN102253052A (en) * | 2011-05-04 | 2011-11-23 | 浙江大学 | Grain quality on-line detection apparatus based on field programmable gate array (FPGA), and method thereof |
| CN103308430A (en) * | 2013-06-03 | 2013-09-18 | 浙江大学 | Method and device for measuring weight of thousand of seeds |
| CN206330969U (en) * | 2016-12-23 | 2017-07-14 | 内蒙古正隆谷物食品有限公司 | A kind of grain quality Comprehensive Assessment device |
| CN107328681A (en) * | 2017-08-04 | 2017-11-07 | 中国计量大学 | Cereal and beans mass of 1000 kernel and moisture content detection system based on machine vision |
-
2018
- 2018-06-27 CN CN201810673175.7A patent/CN109030755A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3230217B2 (en) * | 1999-06-16 | 2001-11-19 | ベルスリーニシハツ株式会社 | Dry laver quality inspection method |
| JP4143380B2 (en) * | 2002-10-29 | 2008-09-03 | 日清製粉株式会社 | Grain characteristic measurement method and apparatus |
| CN101929938A (en) * | 2009-06-25 | 2010-12-29 | 田志和 | Method and equipment for measuring volume weight of grain |
| CN101929938B (en) * | 2009-06-25 | 2012-08-15 | 田志和 | Method for measuring volume weight of grain |
| CN102253052A (en) * | 2011-05-04 | 2011-11-23 | 浙江大学 | Grain quality on-line detection apparatus based on field programmable gate array (FPGA), and method thereof |
| CN103308430A (en) * | 2013-06-03 | 2013-09-18 | 浙江大学 | Method and device for measuring weight of thousand of seeds |
| CN206330969U (en) * | 2016-12-23 | 2017-07-14 | 内蒙古正隆谷物食品有限公司 | A kind of grain quality Comprehensive Assessment device |
| CN107328681A (en) * | 2017-08-04 | 2017-11-07 | 中国计量大学 | Cereal and beans mass of 1000 kernel and moisture content detection system based on machine vision |
Non-Patent Citations (5)
| Title |
|---|
| M. BULENT COSKUN等: "Physical properties of sweet corn seed (Zea mays saccharata Sturt.)", 《JOURNAL OF FOOD ENGINEERING》 * |
| 于徊萍等: "《粮油品质分析》", 31 March 2010 * |
| 周鸿达等: "基于图像处理玉米水分检测方法研究", 《河南工业大学学报（自然科学版）》 * |
| 王刚: "基于机器视觉的玉米千粒重快速检测仪的研制", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 重庆市测绘学会: "《城乡建设中的现代测绘高新技术研究与应用》", 31 March 2008, 西南交通大学出版社 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111539920A (en) * | 2020-04-16 | 2020-08-14 | 泸州老窖酿酒有限责任公司 | Automatic detection method for fermented grain quality in white spirit brewing process |
| CN111539920B (en) * | 2020-04-16 | 2022-03-15 | 泸州老窖酿酒有限责任公司 | Automatic detection method for fermented grain quality in white spirit brewing process |
| CN112858076A (en) * | 2021-02-25 | 2021-05-28 | 山东省农业科学院作物研究所 | Evaluation method of grain postpartum loss |
| CN112861372A (en) * | 2021-03-04 | 2021-05-28 | 中国地质调查局成都地质调查中心 | Debris flow volume weight calculation method |
| CN112907558A (en) * | 2021-03-15 | 2021-06-04 | 南京农业大学 | Full-automatic image determination method for thousand grain weight of rape seeds |
| CN112907558B (en) * | 2021-03-15 | 2023-11-17 | 南京农业大学 | Full-automatic image determination method for thousand grain weight of rapeseeds |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109030755A (en) | The detection device and method of grain moisture content, mass of 1000 kernel and bulk density based on image processing techniques | |
| CN108537851B (en) | Detection method of soil humidity and application thereof | |
| CN111751376B (en) | Rice nitrogen nutrition estimation method based on canopy image feature derivation | |
| CN105181912A (en) | Method for detection of freshness during rice storage | |
| CN104457627A (en) | Method for utilizing Photoshop for precisely measuring area of plane of irregular object | |
| CN102565061A (en) | Crop biomass nondestructive testing image acquisition and processing device and testing method | |
| Martynenko | Computer-vision system for control of drying processes | |
| CN110782455B (en) | Novel method for determining mud content of raw sand based on image processing method | |
| CN108802060B (en) | Rapid nondestructive testing system and method for freshness of eggs | |
| CN202793544U (en) | Hundred-grain weight measuring device of corn kernels | |
| CN105466921A (en) | Simultaneous detection method of many samples | |
| CN108120402A (en) | A kind of method that plant leaf area is measured based on Photoshop softwares | |
| CN116429988B (en) | Dynamic remote sensing monitoring device for ocean plant carbon sink | |
| CN109827957A (en) | A kind of rice leaf SPAD value estimating and measuring method based on computer vision and system | |
| CN201503392U (en) | Handheld soil nutrient nondestructive measurement device based on near infrared spectrum | |
| CN109030488B (en) | Algae biomass detection method and device | |
| WO2024041560A1 (en) | Surface water quality monitoring method based on high-spatial-resolution satellite | |
| CN108827962B (en) | Egg maturity detection method based on light transmission method | |
| CN113393460A (en) | Cut tobacco quality parameter detection method and system based on image processing | |
| CN116912672A (en) | Unmanned survey vessel-based biological integrity evaluation method for large benthonic invertebrates | |
| CN107255611A (en) | A kind of indoor native case water infiltration is from dynamic test measurement system | |
| Barman et al. | Predication of soil pH using K mean segmentation and HSV color image processing | |
| CN110836799A (en) | Suction control type rapid unsaturated soil sample preparation control system and method | |
| CN105928861A (en) | Wheat quality detection method | |
| JP6863154B2 (en) | Dry weight estimation program, dry weight estimation method and dry weight estimation device |
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: 20181218 |
|
| RJ01 | Rejection of invention patent application after publication |