CN104155312A - Method for detecting pests in food grains based on near infrared machine vision, and apparatus thereof - Google Patents
Method for detecting pests in food grains based on near infrared machine vision, and apparatus thereof Download PDFInfo
- Publication number
- CN104155312A CN104155312A CN201410404698.3A CN201410404698A CN104155312A CN 104155312 A CN104155312 A CN 104155312A CN 201410404698 A CN201410404698 A CN 201410404698A CN 104155312 A CN104155312 A CN 104155312A
- Authority
- CN
- China
- Prior art keywords
- grain
- image
- near infrared
- wavelength
- collecting cassette
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 235000013305 food Nutrition 0.000 title claims abstract description 20
- 241000607479 Yersinia pestis Species 0.000 title abstract description 20
- 238000001514 detection method Methods 0.000 claims abstract description 27
- 238000012545 processing Methods 0.000 claims abstract description 22
- 230000005540 biological transmission Effects 0.000 claims abstract description 21
- 238000005070 sampling Methods 0.000 claims abstract description 21
- 230000003287 optical effect Effects 0.000 claims abstract description 14
- 235000013339 cereals Nutrition 0.000 claims description 462
- 241000238631 Hexapoda Species 0.000 claims description 52
- 239000000284 extract Substances 0.000 claims description 15
- 238000005457 optimization Methods 0.000 claims description 9
- 230000005484 gravity Effects 0.000 claims description 6
- 230000008676 import Effects 0.000 claims description 6
- 239000011800 void material Substances 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 230000019771 cognition Effects 0.000 claims description 4
- 238000003756 stirring Methods 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 claims description 3
- 238000013144 data compression Methods 0.000 claims description 3
- 238000003909 pattern recognition Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000003595 spectral effect Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 2
- 230000000266 injurious effect Effects 0.000 claims 10
- 238000004064 recycling Methods 0.000 claims 1
- 238000005286 illumination Methods 0.000 abstract description 4
- 230000006870 function Effects 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 5
- 238000003333 near-infrared imaging Methods 0.000 description 5
- 241000209140 Triticum Species 0.000 description 4
- 235000021307 Triticum Nutrition 0.000 description 4
- 238000004497 NIR spectroscopy Methods 0.000 description 3
- 238000005452 bending Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 238000001931 thermography Methods 0.000 description 2
- LENZDBCJOHFCAS-UHFFFAOYSA-N tris Chemical compound OCC(N)(CO)CO LENZDBCJOHFCAS-UHFFFAOYSA-N 0.000 description 2
- 238000009827 uniform distribution Methods 0.000 description 2
- 101100117236 Drosophila melanogaster speck gene Proteins 0.000 description 1
- 241000233866 Fungi Species 0.000 description 1
- 206010036590 Premature baby Diseases 0.000 description 1
- 241000318997 Rhyzopertha dominica Species 0.000 description 1
- 241000254179 Sitophilus granarius Species 0.000 description 1
- 241000254152 Sitophilus oryzae Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 239000002551 biofuel Substances 0.000 description 1
- 235000008429 bread Nutrition 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 235000013601 eggs Nutrition 0.000 description 1
- 210000003608 fece Anatomy 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 239000000725 suspension Substances 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses an apparatus for detecting pests in food grains based on near infrared machine vision. The detection apparatus comprises a food grain sampling part, a food grain transmission part and a machine vision processing part; the food grain sampling part utilizes a grain discharge motor to drive a grain discharge wheel to rotate in order to rapidly and effectively separate a quantitative amount of food grains from a feeder; the food grain transmission part can convey a collecting box to an assigned position, and can automatically clean the food grains in the collecting box; and the machine vision processing part comprises a near infrared camera, a light source, an optical filter rotating wheel, an illumination case, a computer and corresponding software, and an identification model automatically determines the attitude of the food grains, and judges that whether the food grains are invaded by pests after the multi-wavelength near infrared image acquisition on the food grains in the collecting box. The invention also discloses a detection method corresponding to the apparatus for detecting pests in food grains based on near infrared machine vision. The apparatus and the method realize the real-time, accurate and automatic detection of the pests in the food grains.
Description
Technical field
The invention discloses a kind of grain intragranular portion pest detection method and apparatus based near infrared computer vision, be specifically related to the grain intragranular portion pest detection method based near infrared hyper-spectral image technique
Background technology
" bread is the staff of life ", " food be take grain as first ", grain security is related to national economy, economic prosperity and social development.Yet Disastrous climate takes place frequently in recent years, bio-fuel is striven grain, and global grain yield deposit declines, and grain security situation is increasingly serious.In addition, along with the raising of people's living standard, grain quality is had higher requirement.According to data, the grain loss in weight after whole world results is about 10-15%, and the grain of annual storage period has at least 5% by insect, to be ravaged.China < < grain and oil storage technology standard > > clearly stipulates, what the pest density in worm grain classification standard was added up is the quantity of worm alive, and the borer population amount of living is the inside and outside borer population sum alive of grain grain.Therefore, the detection of grain worm comprises the detection of the outside insect of grain grain and grain intragranular portion insect.
The boring pest such as rice weevil, lesser grain borer directly endangers complete grain grain, and its prematurity larva grows in grain intragranular portion, until adult just from grain intragranular out, is difficult for being found by naked eyes in several weeks after laying eggs, and is difficult to detect from exterior visualization.Insect is not only caused the loss in weight of grain, and its excreta, corpse, cot etc. also can produce serious pollution to grain, easily increase the infection of fungi, cause the decline of grain quality.Visible, the harm that grain intragranular portion insect is caused is sizable, and detection is more difficult.Therefore, how early detection, and the insect that accurately, automatically detects grain intragranular portion is very important.
Traditional grain intragranular portion pest detection method has artificial sense method of inspection, insect fragment method of inspection, suspension method, electrical conductivity method etc.These methods have one or more shortcomings, as too subjective, complicated loaded down with trivial details, inaccurate, consuming time, have destructive etc.In recent years, there is the detection method that some are new, as Electronic Nose method, near infrared spectroscopy, computer vision method.Electronic Nose method is had relatively high expectations to detecting the leakproofness of sample container, the overlong time that sample is prepared and sampled.Near infrared spectroscopy is for the lower situation of the level that infects, not too reliable to the quantification containing worm grain grain, can not differentiate the situation that infects of single grain intragranular portion insect.
Computer vision method detects grain intragranular portion insect, comprises thermal imaging method, grenz ray imaging method, near infrared imaging method etc.Thermal imaging method testing process is too loaded down with trivial details, and sample setup time is long.Grenz ray imaging method can be determined the grain grain that early stage grain worm is infected, and due to safety problem and cost, has affected its practical application.
Near infrared imaging method is compared with other imaging systems at aspects such as hardware costs, simple, small and exquisite, securities, all there is certain advantage, be the very potential developing direction of grain intragranular portion pest detection, researchist is studied in this respect, makes some progress.The insect that the difference image artificial visual of the manual 1202nm selecting of the utilizations such as Ridgway and 1300nm wavelength detects in wheat is infected, but does not study automatic discrimination algorithm.The selected wavelength going out of the utilization near infrared spectroscopies such as Ridgway, develop the near infrared grain weevil of 981nm and infected detection system, the differentiation rate of this method is better than artificial visual and detects, but the extraction effect of grain intragranular portion speck is larger on infecting the impact of detection, and detection efficiency awaits further raising.Singh etc. carry out high spectrum image collection to wheat, under 1101.69nm and two sensitive wave lengths of 1305.05nm, extract the statistical picture feature of wheat, distinguish in wheat and whether have the accuracy of worm more than 85%, but the attitude of grain grain is manual placement, and only studied grain grain ventral groove upward with ventral groove two kinds of attitudes down.
Near infrared imaging method in computer vision method can realize the detection of grain intragranular portion insect, it is the direction of grain intragranular portion pest detection development, but current near infrared computer vision system China Oil and Food Import and Export Corporation grain is artificial sampling mode, also cannot detect grain grain by automatic acquisition, need to improve the automaticity detecting, whether grain intragranular portion has the discrimination precision of worm also to need further raising.Therefore, be necessary to study grain intragranular portion insect automatic testing method and device thereof, realize automatically, accurately detecting of grain intragranular portion insect.
Summary of the invention
Technical matters to be solved by this invention is: for the defect of prior art, a kind of grain intragranular portion insect automatic testing method and device thereof based near infrared computer vision is provided, can from grain sample, automatically take out part grain grain, and automatic transmission carries out image acquisition to computer vision system, whether attitude and the grain grain of by model of cognition, automatically being determined the grain of putting out cereal are subject to infecting of insect, realize the insect pest of grain intragranular portion in real time, accurately, automatically detect.
The present invention is for solving the problems of the technologies described above by the following technical solutions:
Grain intragranular portion insect automatic detection device based near infrared computer vision of the present invention is comprised of grain grain sampling part, grain grain hop and computer vision processing section.Grain grain sampling part and computer vision processing section be all arranged on grain grain hop above.
The function that described grain grain sampling part realizes is that quantitative grain grain is separated quickly and efficiently from feeder, mainly comprises feeder, row's grain wheel, row's grain motor and clear grain brush.Existing grain intragranular portion insect pest computer vision system does not possess automatic ration sampled functions, and grain grain sampling part of the present invention automatically detects and designs for grain intragranular portion insect pest computer vision.Feeder is fixed on device frame, directly over row's grain wheel.A circumferential surface for row grain wheel is uniform-distribution with 4 flat trapezoidal grooves, by single belt, is connected with row's motor, is a bit larger tham the height of collecting cassette with the difference in height of travelling belt 9.Clear grain brush is fixed together with feeder, consistent with the Way out of grain grain, and the outside surface of row's grain wheel keeps certain interval.Therefore,, when grain sample is poured into after feeder, by the motor-driven row's grain of above-mentioned row's grain wheel, automatically carry out quantitative sampling.
The function that described grain grain hop is realized accurately receives grain grain, carry the first collecting cassette and the second collecting cassette under computer vision processing section for image acquisition, and the grain grain in 2 collecting cassettes, mainly comprise control module, transmission motor, disposable box, travelling belt, the first collecting cassette, the second collecting cassette, the first photoelectric sensor and the second photoelectric sensor.Control module is connected with the first photoelectric sensor, the second photoelectric sensor, row's grain motor, computing machine and transmission motor by data line, computing machine receives the trigger pip from the first photoelectric sensor and the second photoelectric sensor by it, and by it, row's grain motor and transmission motor is sent to steering order.Travelling belt adopts chain chain transmission transport sector, by transmission driven by motor, turns round.The first collecting cassette and the second collecting cassette are uniformly distributed on chain, and 2 collecting cassette front ends are hinged on chain, and rear end is free end, can flexible rotating.The below of the row's of the being arranged on grain wheel outlet respectively of 2 photoelectric sensors, near infrared camera, the inboard of travelling belt, and slightly lower than the position of collecting cassette height.When they detect 2 collecting cassettes move to row grain wheel outlet, near infrared camera under time, the trigger pip that provides the sampling of grain grain and multi-wavelength image to take successively to control module.Disposable box is used for the grain grain in collecting cassette, be positioned at travelling belt right side under, the height in the time of should being greater than collecting cassette and standing upside down apart from the difference in height of travelling belt, makes collecting cassette carry out button and stirs after making to topple over grain grain and can continue to move forward.
Described computer vision processing section, major function is the multi-wavelength near-infrared image that gathers grain grain, near infrared camera, optical filter runner, near-infrared light source, lighting box, computing machine and corresponding software, consists of.Lighting box be arranged on travelling belt directly over, there is the light source of the near-infrared band of uniform illumination the inside, for the grain grain in collecting cassette provides uniformly, diffuses.Near infrared camera is arranged in lighting box, be vertically mounted on travelling belt directly over, with collecting cassette direction of motion in same plane, apart from the height of travelling belt 9, should make the collecting cassette bottom surface effective range that collects large as far as possible, and can distinguish the multi-wavelength near-infrared image of clear shooting, collecting box China Oil and Food Import and Export Corporation grain.The spectral range of near infrared camera is 900-1700nm, and its front end is with near infrared filter runner.Near infrared camera is connected with computing machine through data line, and by the image transmitting of taking to computing machine.Optical filter runner the inside is provided with the near infrared filter of several different wave lengths, and the half-band width of near infrared filter is all less than 10nm.Optical filter runner is connected with computing machine through data line, receives the control information from computing machine, the automatic switchover of several optical filters while automatically gathering to control multi-wavelength image.
The invention also discloses a kind of detection method that is applicable to the described grain intragranular portion insect automatic detection device based near infrared computer vision, concrete steps are as follows:
(1) grain grain sampling part extracts quantitative grain grain automatically from feed appliance, and makes grain grain automatically fall into collecting cassette.
(2) grain grain hop collecting cassette be sent near infrared camera under, the collection of multi-wavelength near-infrared image is carried out to the grain grain in collecting cassette in computer vision processing section, and transfers to computing machine.
(3) the first wavelength image of grain grain is carried out to image processing, according to image, cut apart the area information of rear target in image, accurately determine effective target (grain grain), record the information such as the coordinate of all grain grain targets in the first wavelength image, center of gravity, be partitioned into single complete grain grain, obtain background complete black only containing the grayscale sub-image of single grain grain.
(4) for the place an order grayscale sub-image of grain grain of the first wavelength, by asking for the difference of bianry image after grain intragranular contouring and Threshold segmentation, whether according to the difference of the ultimate range on target in difference image and grain grain border, can automatic discrimination going out this target is border or inner void.If grain grain target has border hole or inner void, this grain grain is directly identified as insect and infects grain grain, if grain grain target without hole, enters next step attitude, differentiates.
(5) for the place an order grayscale sub-image of grain grain of the first wavelength, extract invariant moment features (if bending moment 1 not, not bending moment 2 ..., bending moment 7 etc. not), along the absolute value of grain grain length axle two ends area invariant moment features difference etc.; For place an order a grain grain bianry image of the first wavelength, extract the features such as nearest equivalent distances on flexibility, circle, the long limit of major axis boundary rectangle minimum with it, the primitive character space of formation grain grain attitude.Utilize data compression technique, as principal component analysis (PCA), Fisher discriminatory analysis etc., to grain grain primitive character space Dimension Reduction Analysis, extract accumulation contribution rate higher than 90% characteristic parameter information, form the optimization feature space of grain grain attitude.
(6) for the optimization feature space of grain grain attitude, utilize nonlinear pattern recognition sorting technique, as neural network classifier, support vector machine classifier, Fuzzy Classifier, extension classification device etc., set up the relational model of characteristic parameter and grain grain attitude after the grain optimization of the first wavelength image China Oil and Food Import and Export Corporation, grain grain attitude common are ventral groove down, upward, side direction, and Model Identification precision is more than 95%, automatically determines the attitude of each grain grain by grain grain gesture recognition model.
(7) for the grain grain gray level image under multi-wavelength, extract respectively its statistical nature (as maximal value, minimum value, intermediate value, standard deviation etc.), histogram transformation feature, textural characteristics etc., form and optimize the primitive character space under different grain grain attitudes.Grain grain according to different attitudes, utilize intelligent mode sorting technique, set up respectively in multi-wavelength image optimize after grain grain image features and grain grain whether be subject to the relational model that insect is infected, and the disaggregated model precision that guarantees 3 attitudes is all more than 95%, uses grain intragranular portion insect model of cognition can determine whether the grain of putting out cereal is subject to infecting of insect.
(8) count and in obtained multi-wavelength image, be subject to the grain grain quantity that insect is infected, if exist, infect grain grain, record this multi-wavelength image, infect the information such as center of gravity of grain grain.
(9) when computing machine to obtain multi-wavelength near-infrared image analyzing and processing time, grain grain hop continues operation, when running to extreme position, Automatic clearance is removed the grain grain in collecting cassette.
Further, described image is processed and is comprised and remove that collecting cassette background, filtering strengthen image, cut apart image, grain grain is accurately located.
The intensity of light source in lighting box and position can be adjusted, and choose light source and the locus of suitable frequency spectrum, and make to form uniform illumination in the visual field of camera, make camera can obtain screen underflow image clearly.
The present invention adopts above technical scheme compared with prior art, has following technique effect:
(1) the present invention adopts near infrared computer vision system to detect grain grain, Automatic Extraction part grain grain, and according to the different attitudes of grain grain, whether grain grain is subject to infecting of insect and carries out automatic discrimination;
(2) the present invention utilizes near infrared imaging technology, by the attitude of automatic discrimination grain grain, and adopt different disaggregated models according to the different attitudes of grain grain, make grain grain whether be subject to the classification accuracy rate that insect infects and reach more than 95%, improved the discrimination that near infrared imaging method detects grain intragranular portion insect automatically;
(3) the present invention combines grain grain automatic sampling transmitting device and the Computer Vision Detection System that includes high speed processing software, realized that grain intragranular portion insect pest infects automatically, accurately differentiate, improve the automaticity that the insect pest of grain intragranular portion detects, reduced labour intensity.
Accompanying drawing explanation
Fig. 1 is structural representation of the present invention;
Wherein, 1. feeder, 2. row grain wheel, 3. row's grain motor, 4. transmission motor, 5. near infrared camera, 6. optical filter runner, 7. near-infrared light source, 8. clear grain brush, 9. travelling belt, 10. lighting box, 11. computing machines, 12. disposable boxes, 13. second collecting cassettes, 14. second photoelectric sensors, 15. first collecting cassettes, 16. first photoelectric sensors, 17. control modules.
Fig. 2 is method processing flow chart of the present invention.
Embodiment
Describe embodiments of the present invention below in detail, the example of described embodiment is shown in the drawings, and wherein same or similar label represents same or similar element or has the element of identical or similar functions from start to finish.Below by the embodiment being described with reference to the drawings, be exemplary, only for explaining the present invention, and can not be interpreted as limitation of the present invention.
Below in conjunction with accompanying drawing, technical scheme of the present invention is described in further detail:
As shown in Figure 1, described pick-up unit is comprised of grain grain sampling part, grain grain hop and computer vision processing section structural representation of the present invention.Grain grain sampling part and computer vision processing section be all arranged on grain grain hop above.It is characterized in that:
The function that described grain grain sampling part realizes is that quantitative grain grain is separated quickly and efficiently from feeder, mainly comprises feeder 1, row's grain wheel 2, row's grain motor 3 and clear grain brush 8.Existing grain intragranular portion insect pest computer vision system does not possess automatic ration sampled functions, and grain grain sampling part of the present invention automatically detects and designs for grain intragranular portion insect pest computer vision.Feeder 1 is fixed on device frame, directly over row's grain wheel 2.A circumferential surface for row grain wheel 2 is uniform-distribution with 4 flat trapezoidal grooves, by single belt, is connected with row's motor 3, is a bit larger tham the height of collecting cassette with the difference in height of travelling belt 9.Clear grain brush 8 is fixed together with feeder 1, consistent with the Way out of grain grain, and the outside surface of row's grain wheel 2 keeps certain interval.Therefore,, when grain sample is poured into after feeder 1, the row's grain wheel 2 driving by above-mentioned row's grain motor 3 carries out quantitative sampling automatically.
The function that described grain grain hop is realized accurately receives grain grain, carry the first collecting cassette 15 and the second collecting cassette 13 under computer vision processing section for image acquisition, and clear up the grain grain in the first collecting cassette 15 and the second collecting cassette 13, mainly comprise control module 17, transmission motor 4, disposable box 12, travelling belt 9, the first collecting cassette 15, the second collecting cassette 13, the first photoelectric sensor 16 and the second photoelectric sensor 14.Control module 17 is connected with the first photoelectric sensor 16, the second photoelectric sensor 14, row's grain motor 3, computing machine 11 and transmission motor 4 by data line, computing machine 11 receives the trigger pip from the first photoelectric sensor 16 and the second photoelectric sensor 14 by it, and by it, row's grain motor 3 and transmission motor 4 is sent to steering order.Travelling belt 9 adopts chain chain transmission transport sector, by transmission motor 4, drives running.The first collecting cassette 15 and the second collecting cassette 13 are uniformly distributed on chain, and 2 collecting cassette front ends are hinged on chain, and rear end is free end, can flexible rotating.The below of the row's of being arranged on grain wheel 2 outlets respectively of 2 photoelectric sensors, near infrared camera 5, the inboard of travelling belt 9, and slightly lower than the position of collecting cassette 15 height.When they detect 2 collecting cassettes move to 2 outlets of row grain wheel, near infrared camera 5 under time, the trigger pip of providing the sampling of grain grain and multi-wavelength image to take successively to control module 17.When the first collecting cassette 15 or the second collecting cassette 13 run to extreme position, carry out button and stir work, topple over the grain grain in collecting cassette, and collected by the disposable box 12 being arranged under it.Disposable box 12 be positioned at travelling belt 9 right sides under, the height in the time of should being greater than collecting cassette and standing upside down apart from the difference in height of travelling belt 9, carries out after button stirs work collecting cassette and can continue to move forward.
Described computer vision processing section, major function is the multi-wavelength near-infrared image that gathers grain grain, near infrared camera 5, optical filter runner 6, near-infrared light source 7, lighting box 10, computing machine 11 and corresponding software, consists of.Lighting box 10 be arranged on travelling belt 9 directly over, there is the annular light source of the near-infrared band of uniform illumination the inside, for the grain grain in collecting cassette provides uniformly, diffuses.Near infrared camera 5 is arranged in lighting box 10, be vertically mounted on travelling belt 9 directly over, with collecting cassette direction of motion in same plane, apart from the height of travelling belt 9, should make the collecting cassette bottom surface effective range that collects large as far as possible, and can distinguish the multi-wavelength near-infrared image of clear shooting, collecting box China Oil and Food Import and Export Corporation grain.The spectral range of near infrared camera 5 is 900-1700nm, and its front end is with near infrared filter runner.Near infrared camera 5 is connected with computing machine 11 through data line, and by the image transmitting of taking to computing machine 11.Optical filter runner 6 the insides are provided with the near infrared filter of several different wave lengths, and the half-band width of near infrared filter is all less than 10nm.Optical filter runner is connected with computing machine 11 through data line, receives the control information from computing machine 11, the automatic switchover of several optical filters while automatically gathering to control multi-wavelength image.
Method processing flow chart of the present invention as shown in Figure 2, during work, grain sample is sent into after feeder 1, and computing machine 11 sends steering order to control module 17 and starts row's grain motor 3, the rotation of row's grain motor 3 row's of drive grain wheels 2, grain grain falls into the first collecting cassette 15 of row's grain wheel 2 outlet belows.Transmission motor 4 drives travelling belts 9 to rotate, and after the first photoelectric sensor 16 detects the first collecting cassette 15 and puts in place, near infrared cameras 5 controlled by computing machine 11 and optical filter runner 6 carries out multi-wavelength image acquisition, and after collection, travelling belt 13 moves on.The first wavelength image to grain grain carries out image processing, according to image, cut apart the area information of rear target in image, accurately determine effective grain grain target, record the information such as the coordinate of all grain grain targets in the first wavelength image, center of gravity, be partitioned into single complete grain grain, obtain background complete black only containing the grayscale sub-image of single grain grain.For the place an order grayscale sub-image of grain grain of the first wavelength, by asking for the difference of bianry image after grain grain (inside) profile and Threshold segmentation, whether according to the difference of the ultimate range on target in difference image and grain grain border, can automatic discrimination going out this target is border (inside) hole.If grain grain target has border hole or inner void, this grain grain is directly identified as insect and infects grain grain, if grain grain target without hole, enters next step attitude, differentiates.For the place an order grayscale sub-image of grain grain of the first wavelength, extract invariant moment features, along the absolute value of grain grain length axle two ends area invariant moment features difference etc.; For place an order a grain grain bianry image of the first wavelength, extract the features such as nearest equivalent distances on flexibility, circle, the long limit of major axis boundary rectangle minimum with it, the primitive character space of formation grain grain attitude.Utilize data compression technique, to grain grain primitive character space Dimension Reduction Analysis, extract accumulation contribution rate higher than 90% characteristic parameter information, form the optimization feature space of grain grain attitude.Optimization feature space for grain grain attitude, utilize nonlinear pattern recognition sorting technique set up characteristic parameter and grain grain attitude after the grain optimization of the first wavelength image China Oil and Food Import and Export Corporation (ventral groove down, upward, side direction) relational model, by grain grain gesture recognition model, automatically determine the attitude of each grain grain.Grain grain gray level image under multi-wavelength, extracts respectively its statistical nature, histogram transformation feature, textural characteristics etc., forms and optimize the primitive character space under different grain grain attitudes.Grain grain according to different attitudes, utilize intelligent mode sorting technique, set up respectively in multi-wavelength image optimize after grain grain image features and grain grain whether be subject to the relational model that insect is infected, and the disaggregated model precision that guarantees 3 attitudes is all more than 95%, uses grain intragranular portion insect model of cognition can determine whether the grain of putting out cereal is subject to infecting of insect.Count and in obtained multi-wavelength image, be subject to the grain grain quantity that insect is infected, if exist, infect grain grain, record this multi-wavelength image, infect the information such as center of gravity of grain grain.When the first collecting cassette 15 moves to rightmost, spin upside down, grain grain falls into disposable box 12 automatically.After the first photoelectric sensor 16 detects the second collecting cassette 13 and puts in place, 4 stalls of transmission motor detect to wait for next time.
By reference to the accompanying drawings embodiments of the present invention are explained in detail above, but the present invention is not limited to above-mentioned embodiment, in the ken possessing those of ordinary skills, can also under the prerequisite that does not depart from aim of the present invention, makes a variety of changes.The above, it is only preferred embodiment of the present invention, not the present invention is done to any pro forma restriction, although the present invention discloses as above with preferred embodiment, yet not in order to limit the present invention, any those skilled in the art, do not departing within the scope of technical solution of the present invention, when can utilizing the technology contents of above-mentioned announcement to make a little change or being modified to the equivalent embodiment of equivalent variations, in every case be not depart from technical solution of the present invention content, according to technical spirit of the present invention, within the spirit and principles in the present invention, the any simple modification that above embodiment is done, be equal to replacement and improvement etc., within all still belonging to the protection domain of technical solution of the present invention.
Claims (10)
1. the grain intragranular portion injurious insect detector based near infrared computer vision, it is characterized in that: described pick-up unit is comprised of grain grain sampling part, grain grain hop and computer vision processing section, described grain grain sampling part and computer vision processing section be arranged at described grain grain hop directly over, wherein:
Described grain grain sampling part comprises feeder, row grain wheel, row's grain motor and clear grain brush, and described feeder and row's grain wheel fixedly mount by support, row's grain wheel be installed on feeder outlet under; The surface uniform of described row's grain wheel is distributed with flat groove, and row's grain wheel is connected with row's grain motor by single belt; The exit of described feeder is fixedly connected with grain brush clearly, between clear grain brush and the outside surface of row's grain wheel, leaves gap;
Described computer vision processing section comprises lighting box and computing machine, wherein, lighting box inside center place is disposed with that near-infrared light source is near from the bottom to top, optical filter runner and infrared camera, and described optical filter runner is all connected with computing machine via data line with infrared camera;
Described grain grain hop comprises control module, transmission motor, disposable box, travelling belt, the first collecting cassette, the second collecting cassette, the first photoelectric sensor and the second photoelectric sensor, wherein, described control module is connected with transmission motor with the first photoelectric sensor, the second photoelectric sensor, row's grain motor, computing machine by data line respectively, computing machine receives the trigger pip from the first photoelectric sensor and the second photoelectric sensor by control module, then via control module, row's grain motor and transmission motor is sent to control signal; One end of transmission motor and travelling belt is connected, and drives travelling belt running, and described disposable box is arranged at the below of the travelling belt other end; Being arranged on described travelling belt of described first, second collecting cassette proportional spacing, the hinged travelling belt of the front end of first, second collecting cassette, rear end is free end, collecting cassette can hinged place be that axle rotates; Described first, second photoelectric sensor respectively row's of being arranged at grain is taken turns the travelling belt inboard of locating under exit and lighting box, when described photoelectric sensor detect collecting cassette move near infrared camera in row grain wheel outlet and lighting box under time, photoelectric sensor sends to control module the trigger pip that grain grain samples and multi-wavelength image is taken successively;
The height of described first, second collecting cassette of take is reference, and the lower end of described row's grain wheel is greater than the height of collecting cassette apart from the distance of travelling belt; Described lighting box apart from the distance of travelling belt be greater than the height of collecting cassette and the collecting cassette area that makes to photograph in infrared camera maximum; Height when described disposable box is greater than collecting cassette and erects apart from the distance of travelling belt, makes collecting cassette carry out button and stirs after making to topple over grain grain and can continue to move forward.
2. a kind of grain intragranular portion injurious insect detector based near infrared computer vision as claimed in claim 1, is characterized in that: described travelling belt is chain chain transmission transport sector.
3. a kind of grain intragranular portion injurious insect detector based near infrared computer vision as claimed in claim 1, is characterized in that: the flatter that the surface uniform of described row's grain wheel distributes is trapezoidal, and quantity is four.
4. a kind of grain intragranular portion injurious insect detector based near infrared computer vision as claimed in claim 1, is characterized in that: the spectral range of described near infrared camera is 900-1700nm.
5. a kind of grain intragranular portion injurious insect detector based near infrared computer vision as claimed in claim 1, it is characterized in that: the near infrared filter of a plurality of different wave lengths is installed in described optical filter runner, and the half-band width of described near infrared filter is all less than 10nm.
6. a detection method that is applicable to the described grain intragranular portion injurious insect detector based near infrared computer vision, is characterized in that, concrete steps comprise:
Step (1), grain grain sampling part extract quantitative grain grain from feed appliance, and make grain grain fall into collecting cassette;
Step (2), grain grain hop collecting cassette be sent near infrared camera under, the collection of multi-wavelength near-infrared image is carried out to the grain grain in collecting cassette in computer vision processing section, and collection result is transported to computing machine;
Step (3), the first wavelength near infrared of grain grain is gathered to image carry out image processing, according to image, cut apart the area information of rear grain grain in image, determine effective grain grain target, record the parameter information of all grain grain targets in the first wavelength image, be partitioned into single complete grain grain, obtain background complete black only containing the grayscale sub-image of single grain grain;
Step (4), for the place an order grayscale sub-image of grain grain of the first wavelength, ask for the difference of bianry image after grain intragranular contouring and Threshold segmentation, according to the difference of the target in difference image and grain grain object boundary ultimate range, whether the target determining in this difference image is border hole or inner void:
(401), when grain grain target has border hole or inner void, judge that this grain grain infects grain grain as insect;
(402), when grain grain target is during without hole, the attitude that enters next step is differentiated;
Step (5), for the place an order grayscale sub-image of grain grain of the first wavelength, extract corresponding gray level image feature, for place an order a grain grain bianry image of the first wavelength, extract corresponding bianry image feature, the final primitive character space that forms grain grain attitude, recycling data compression technique, to grain grain primitive character space Dimension Reduction Analysis, extract accumulation contribution rate higher than 90% characteristic parameter information, form the optimization feature space of grain grain attitude;
Step (6), for the optimization feature space of grain grain attitude, utilize nonlinear pattern recognition sorting technique to set up the relational model of characteristic parameter and grain grain attitude after the grain optimization of the first wavelength image China Oil and Food Import and Export Corporation, by grain grain attitude relational model, determine the attitude of each grain grain;
Step (7), for the grain grain grayscale sub-image under multi-wavelength, extract respectively its statistical nature, histogram transformation feature, textural characteristics, form and optimize the primitive character space under different grain grain attitudes, grain grain according to different attitudes, utilize intelligent mode sorting technique, set up respectively in multi-wavelength image optimize after grain grain image features whether be subject to grain grain the relational model that insect is infected, use grain intragranular portion insect model of cognition to determine to put out cereal whether to be subject to infecting of insect;
Step (8), count and in obtained multi-wavelength image, be subject to the grain grain quantity that insect is infected, and record infects multi-wavelength image and the centre of gravity place information of grain grain;
Step (9), computing machine to obtain multi-wavelength near-infrared image analyzing and processing time, grain grain hop continues operation, when collecting cassette runs to travelling belt free end extreme position, the grain grain in collecting cassette is poured onto to disposable box.
7. fit as claimed in claim 6 a kind of detection method for the grain intragranular portion injurious insect detector based near infrared computer vision, it is characterized in that: in step (3), described image is processed and comprised and remove that collecting cassette background, filtering strengthen image, cut apart image, grain grain is accurately located.
8. fit as claimed in claim 6 a kind of detection method for the grain intragranular portion injurious insect detector based near infrared computer vision, it is characterized in that: in step (3), the parameter information of described grain grain target in the first wavelength image comprises co-ordinate position information and centre of gravity place information.
9. fit as claimed in claim 6 a kind of detection method for the grain intragranular portion injurious insect detector based near infrared computer vision, it is characterized in that: in step (5), the place an order characteristics of image of grayscale sub-image of grain grain of described the first wavelength comprises: invariant moment features and along the absolute value of grain grain length axle two ends area invariant moment features difference; The place an order characteristics of image of grain grain bianry image of described the first wavelength comprises: flexibility, circle, major axis boundary rectangle minimum with it are grown the nearest equivalent distances on limit.
10. suitable a kind of detection method for the grain intragranular portion injurious insect detector based near infrared computer vision as claimed in claim 6, is characterized in that: described in step (6), grain grain attitude comprises: ventral groove down, upward and side direction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410404698.3A CN104155312B (en) | 2014-08-11 | 2014-08-11 | Grain intragranular portion pest detection method and apparatus based on near-infrared computer vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410404698.3A CN104155312B (en) | 2014-08-11 | 2014-08-11 | Grain intragranular portion pest detection method and apparatus based on near-infrared computer vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104155312A true CN104155312A (en) | 2014-11-19 |
| CN104155312B CN104155312B (en) | 2017-06-16 |
Family
ID=51880871
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410404698.3A Expired - Fee Related CN104155312B (en) | 2014-08-11 | 2014-08-11 | Grain intragranular portion pest detection method and apparatus based on near-infrared computer vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104155312B (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104749189A (en) * | 2015-02-28 | 2015-07-01 | 华北水利水电大学 | Grain interior insect pest detection device based on multi-spectral imaging technology |
| CN106127226A (en) * | 2016-06-14 | 2016-11-16 | 河南工业大学 | Grain grain and the flexible grain quality detection method of grain grain test sample |
| WO2017049923A1 (en) * | 2015-06-17 | 2017-03-30 | 广州市巽腾信息科技有限公司 | Multi-function mobile image processing apparatus, processing method, and application |
| WO2017049922A1 (en) * | 2015-06-17 | 2017-03-30 | 广州市巽腾信息科技有限公司 | Image information collection apparatus, image collection method, and application thereof |
| CN106770002A (en) * | 2016-11-21 | 2017-05-31 | 无锡艾科瑞思产品设计与研究有限公司 | A kind of near infrared ray domestic food detection means |
| CN106769980A (en) * | 2016-11-22 | 2017-05-31 | 南京财经大学 | A kind of method for distinguishing cereal and insect infrared radiation absorption characteristic |
| CN107610122A (en) * | 2017-09-30 | 2018-01-19 | 华北水利水电大学 | Insect pest detection method inside a kind of single grain cereal based on Micro CT |
| CN107894419A (en) * | 2017-12-29 | 2018-04-10 | 南京艾龙信息科技有限公司 | A kind of original grain pest detection means and method |
| CN109034269A (en) * | 2018-08-22 | 2018-12-18 | 华北水利水电大学 | A kind of bollworm female male imago method of discrimination based on computer vision technique |
| CN109791111A (en) * | 2016-08-22 | 2019-05-21 | 丘比株式会社 | The learning method of the identification mechanism of food inspection device, food inspection method and food inspection device |
| US20190164272A1 (en) * | 2017-11-30 | 2019-05-30 | Pinhas Yosef Akrav | Automatic System for Separating and Identifying Insects on Leaves |
| CN111768404A (en) * | 2020-07-08 | 2020-10-13 | 北京滴普科技有限公司 | Mask appearance defect detection system, method and device and storage medium |
| CN112415009A (en) * | 2020-12-14 | 2021-02-26 | 河南牧业经济学院 | Wheat grain non-adhesion image acquisition method and system based on sticky dot matrix |
| CN112505340A (en) * | 2020-12-08 | 2021-03-16 | 山东泓盛智能科技有限公司 | Automatic testing system and method for multiple grains |
| CN112505049A (en) * | 2020-10-14 | 2021-03-16 | 上海互觉科技有限公司 | Mask inhibition-based method and system for detecting surface defects of precision components |
| CN113866176A (en) * | 2021-09-18 | 2021-12-31 | 北京中仪智控科技有限公司 | Full-automatic analyzer for imperfect grains |
| CN114037704A (en) * | 2022-01-10 | 2022-02-11 | 安徽高哲信息技术有限公司 | Feeding system, control method and control device thereof, and storage medium |
| CN117074353A (en) * | 2023-08-18 | 2023-11-17 | 广东省农业科学院设施农业研究所 | Nondestructive detection method and system for litchi fruit Di-moths |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1183733A (en) * | 1997-09-03 | 1999-03-26 | Kubota Corp | Grade measuring instrument for grain |
| CN201382896Y (en) * | 2009-03-05 | 2010-01-13 | 华中农业大学 | Sorting experimental bench for multisource information detection of chesnut quality |
| CN101701915A (en) * | 2009-11-13 | 2010-05-05 | 江苏大学 | Device and method for detecting stored-grain insects based on visible light-near infrared binocular machine vision |
| US20100216114A1 (en) * | 2009-02-26 | 2010-08-26 | Kws Saat Ag | Method and apparatus for determination of components in root crops |
| CN102072883A (en) * | 2010-07-07 | 2011-05-25 | 北京农业智能装备技术研究中心 | Device and method for detecting comprehensive quality of crop seeds |
| CN102095481A (en) * | 2010-12-02 | 2011-06-15 | 江苏大学 | Device and method for automatically discriminating cocoon sexuality |
| JP2013238524A (en) * | 2012-05-16 | 2013-11-28 | Panasonic Corp | Sorting method and sorting system of plastic inclusion |
| CN103706574A (en) * | 2013-12-25 | 2014-04-09 | 中国科学院半导体研究所 | Automatic solid grain sorting system |
-
2014
- 2014-08-11 CN CN201410404698.3A patent/CN104155312B/en not_active Expired - Fee Related
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1183733A (en) * | 1997-09-03 | 1999-03-26 | Kubota Corp | Grade measuring instrument for grain |
| US20100216114A1 (en) * | 2009-02-26 | 2010-08-26 | Kws Saat Ag | Method and apparatus for determination of components in root crops |
| CN201382896Y (en) * | 2009-03-05 | 2010-01-13 | 华中农业大学 | Sorting experimental bench for multisource information detection of chesnut quality |
| CN101701915A (en) * | 2009-11-13 | 2010-05-05 | 江苏大学 | Device and method for detecting stored-grain insects based on visible light-near infrared binocular machine vision |
| CN102072883A (en) * | 2010-07-07 | 2011-05-25 | 北京农业智能装备技术研究中心 | Device and method for detecting comprehensive quality of crop seeds |
| CN102095481A (en) * | 2010-12-02 | 2011-06-15 | 江苏大学 | Device and method for automatically discriminating cocoon sexuality |
| JP2013238524A (en) * | 2012-05-16 | 2013-11-28 | Panasonic Corp | Sorting method and sorting system of plastic inclusion |
| CN103706574A (en) * | 2013-12-25 | 2014-04-09 | 中国科学院半导体研究所 | Automatic solid grain sorting system |
Non-Patent Citations (4)
| Title |
|---|
| F.E.DOWELL ET AL.: "Identifying Stored-Grain Insects Using Near-Infrared Spectroscopy", 《JOURNAL OF ECONOMIC ENTOMOLOGY》 * |
| S.NEETHIRAJAN ET AL.: "Detection techniques for stored-product insects in grain", 《FOOD CONTROL》 * |
| 张红涛 等: "储粮害虫图像识别中的特征提取", 《农业工程学报》 * |
| 王润涛 等: "基于机器视觉的大豆籽粒精选技术", 《农业工程学报》 * |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104749189A (en) * | 2015-02-28 | 2015-07-01 | 华北水利水电大学 | Grain interior insect pest detection device based on multi-spectral imaging technology |
| WO2017049923A1 (en) * | 2015-06-17 | 2017-03-30 | 广州市巽腾信息科技有限公司 | Multi-function mobile image processing apparatus, processing method, and application |
| WO2017049922A1 (en) * | 2015-06-17 | 2017-03-30 | 广州市巽腾信息科技有限公司 | Image information collection apparatus, image collection method, and application thereof |
| CN106127226A (en) * | 2016-06-14 | 2016-11-16 | 河南工业大学 | Grain grain and the flexible grain quality detection method of grain grain test sample |
| CN106127226B (en) * | 2016-06-14 | 2019-09-03 | 河南工业大学 | The flexible grain quality detection method of grain grain and grain grain test sample |
| CN109791111A (en) * | 2016-08-22 | 2019-05-21 | 丘比株式会社 | The learning method of the identification mechanism of food inspection device, food inspection method and food inspection device |
| CN109791111B (en) * | 2016-08-22 | 2022-01-11 | 丘比株式会社 | Food inspection device, food inspection method, and method for learning identification means of food inspection device |
| CN106770002A (en) * | 2016-11-21 | 2017-05-31 | 无锡艾科瑞思产品设计与研究有限公司 | A kind of near infrared ray domestic food detection means |
| CN106769980A (en) * | 2016-11-22 | 2017-05-31 | 南京财经大学 | A kind of method for distinguishing cereal and insect infrared radiation absorption characteristic |
| CN107610122B (en) * | 2017-09-30 | 2020-07-28 | 华北水利水电大学 | Micro-CT-based single-grain cereal internal insect pest detection method |
| CN107610122A (en) * | 2017-09-30 | 2018-01-19 | 华北水利水电大学 | Insect pest detection method inside a kind of single grain cereal based on Micro CT |
| US10810724B2 (en) * | 2017-11-30 | 2020-10-20 | Pinhas Yosef Akrav | Automatic system for separating and identifying insects on leaves |
| US20190164272A1 (en) * | 2017-11-30 | 2019-05-30 | Pinhas Yosef Akrav | Automatic System for Separating and Identifying Insects on Leaves |
| CN107894419B (en) * | 2017-12-29 | 2023-10-27 | 南京艾龙信息科技有限公司 | Device and method for detecting raw grain pests |
| CN107894419A (en) * | 2017-12-29 | 2018-04-10 | 南京艾龙信息科技有限公司 | A kind of original grain pest detection means and method |
| CN109034269A (en) * | 2018-08-22 | 2018-12-18 | 华北水利水电大学 | A kind of bollworm female male imago method of discrimination based on computer vision technique |
| CN111768404A (en) * | 2020-07-08 | 2020-10-13 | 北京滴普科技有限公司 | Mask appearance defect detection system, method and device and storage medium |
| CN112505049A (en) * | 2020-10-14 | 2021-03-16 | 上海互觉科技有限公司 | Mask inhibition-based method and system for detecting surface defects of precision components |
| CN112505340A (en) * | 2020-12-08 | 2021-03-16 | 山东泓盛智能科技有限公司 | Automatic testing system and method for multiple grains |
| CN112415009A (en) * | 2020-12-14 | 2021-02-26 | 河南牧业经济学院 | Wheat grain non-adhesion image acquisition method and system based on sticky dot matrix |
| CN112415009B (en) * | 2020-12-14 | 2024-06-11 | 河南牧业经济学院 | Wheat grain non-adhesion image acquisition method and system based on viscous lattice |
| CN113866176A (en) * | 2021-09-18 | 2021-12-31 | 北京中仪智控科技有限公司 | Full-automatic analyzer for imperfect grains |
| CN114037704A (en) * | 2022-01-10 | 2022-02-11 | 安徽高哲信息技术有限公司 | Feeding system, control method and control device thereof, and storage medium |
| CN114037704B (en) * | 2022-01-10 | 2022-04-22 | 安徽高哲信息技术有限公司 | Feeding system, control method and control device thereof, and storage medium |
| CN117074353A (en) * | 2023-08-18 | 2023-11-17 | 广东省农业科学院设施农业研究所 | Nondestructive detection method and system for litchi fruit Di-moths |
| CN117074353B (en) * | 2023-08-18 | 2024-05-03 | 广东省农业科学院设施农业研究所 | Nondestructive detection method and system for litchi fruit Di-moths |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104155312B (en) | 2017-06-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104155312A (en) | Method for detecting pests in food grains based on near infrared machine vision, and apparatus thereof | |
| Momin et al. | Machine vision based soybean quality evaluation | |
| CN107952696A (en) | A kind of detection grading plant and detection method suitable for fresh tobacco leaf | |
| CN101701906B (en) | Method and device for detecting stored-grain insects based on near infrared super-spectral imaging technology | |
| CN103323457B (en) | Fruit appearance defect real-time online detection system and detection method | |
| CN101701915B (en) | Device and method for detecting stored-grain insects based on visible light-near infrared binocular machine vision | |
| CN104198324B (en) | Computer vision-based method for measuring proportion of cut leaves in cut tobacco | |
| CN111709333B (en) | Tracing early warning system based on abnormal excrement of cage-raised chickens and health monitoring method | |
| Li et al. | A machine vision system for identification of micro-crack in egg shell | |
| CN107486415A (en) | Thin bamboo strip defect on-line detecting system and detection method based on machine vision | |
| CN110705655A (en) | Tobacco leaf classification method based on coupling of spectrum and machine vision | |
| CN103323455A (en) | Tobacco leaf grading method based on reflection, perspective and microscopic images | |
| CN110766702B (en) | Agaricus bisporus grading judgment method | |
| CN1485616A (en) | Fowl eggs quality non-destruction automatic detection grading apparatus and process | |
| NL2006600C2 (en) | DEVICE AND METHOD FOR DETECTING TRACKS | |
| CN104949998A (en) | Online visual inspection device and method for surface dirt of group origin eggs | |
| Lunadei et al. | Automatic identification of defects on eggshell through a multispectral vision system | |
| CN105806751A (en) | On-line monitoring system and method for crushing of cereals in grain tank of combine harvester | |
| CN114993965B (en) | Automatic pollution source identification method and system | |
| CN106076890B (en) | Early stage fruit corruption fruit on-line detecting system and method | |
| Shin et al. | Postharvest citrus mass and size estimation using a logistic classification model and a watershed algorithm | |
| CN104749189A (en) | Grain interior insect pest detection device based on multi-spectral imaging technology | |
| CN110575973B (en) | Crop seed quality detection and screening system | |
| Al-Mallahi et al. | Detection of potato tubers using an ultraviolet imaging-based machine vision system | |
| CN105195438A (en) | Embedded type automatic pearl sorting device and method based on image recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170616 |