CN112291547B - Impurity removal system with image recognition function - Google Patents
Impurity removal system with image recognition function Download PDFInfo
- Publication number
- CN112291547B CN112291547B CN202011184658.4A CN202011184658A CN112291547B CN 112291547 B CN112291547 B CN 112291547B CN 202011184658 A CN202011184658 A CN 202011184658A CN 112291547 B CN112291547 B CN 112291547B
- Authority
- CN
- China
- Prior art keywords
- image
- vibration
- image sensor
- img
- interception net
- 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.)
- Active
Links
- 239000012535 impurity Substances 0.000 title claims abstract description 75
- 238000012545 processing Methods 0.000 claims abstract description 45
- 238000012937 correction Methods 0.000 claims abstract description 43
- 239000002245 particle Substances 0.000 claims abstract description 21
- 239000000428 dust Substances 0.000 claims abstract description 20
- 230000000149 penetrating effect Effects 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 32
- 230000008569 process Effects 0.000 claims description 19
- 230000033001 locomotion Effects 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 6
- 230000001105 regulatory effect Effects 0.000 claims description 6
- 230000001276 controlling effect Effects 0.000 claims description 5
- 239000010813 municipal solid waste Substances 0.000 claims description 5
- 238000005286 illumination Methods 0.000 claims description 4
- 230000004044 response Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000006835 compression Effects 0.000 claims description 3
- 238000007906 compression Methods 0.000 claims description 3
- 239000000356 contaminant Substances 0.000 claims description 3
- 230000005855 radiation Effects 0.000 claims description 3
- 235000019504 cigarettes Nutrition 0.000 description 63
- 241000208125 Nicotiana Species 0.000 description 37
- 235000002637 Nicotiana tabacum Nutrition 0.000 description 37
- 230000006870 function Effects 0.000 description 15
- 239000002699 waste material Substances 0.000 description 14
- 230000000694 effects Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 10
- 238000005316 response function Methods 0.000 description 7
- 239000004071 soot Substances 0.000 description 7
- 230000008859 change Effects 0.000 description 6
- 239000004744 fabric Substances 0.000 description 6
- 238000003860 storage Methods 0.000 description 6
- 230000003044 adaptive effect Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000000926 separation method Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 239000008187 granular material Substances 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 230000001502 supplementing effect Effects 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000010355 oscillation Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000011897 real-time detection Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000003854 Surface Print Methods 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000002238 attenuated effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000000227 grinding Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- XEEYBQQBJWHFJM-UHFFFAOYSA-N iron Substances [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 210000001747 pupil Anatomy 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000005476 size effect Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N9/00—Details of colour television systems
- H04N9/64—Circuits for processing colour signals
- H04N9/646—Circuits for processing colour signals for image enhancement, e.g. vertical detail restoration, cross-colour elimination, contour correction, chrominance trapping filters
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B08—CLEANING
- B08B—CLEANING IN GENERAL; PREVENTION OF FOULING IN GENERAL
- B08B17/00—Methods preventing fouling
- B08B17/02—Preventing deposition of fouling or of dust
- B08B17/04—Preventing deposition of fouling or of dust by using removable coverings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
- G06T5/92—Dynamic range modification of images or parts thereof based on global image properties
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N9/00—Details of colour television systems
- H04N9/64—Circuits for processing colour signals
- H04N9/70—Circuits for processing colour signals for colour killing
- H04N9/71—Circuits for processing colour signals for colour killing combined with colour gain control
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N9/00—Details of colour television systems
- H04N9/64—Circuits for processing colour signals
- H04N9/73—Colour balance circuits, e.g. white balance circuits or colour temperature control
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an impurity removal system with an image recognition function, which comprises an eliminating device, an image sensor and a microcomputer controller, wherein the image sensor is arranged on the image sensor; the removing device comprises a vibration groove which is obliquely arranged and can vibrate up and down, an interception net and a control assembly thereof which are embedded in the bottom of the center of the vibration groove, and an impurity removing pipeline which is embedded in the middle of the vibration groove; the image sensor is arranged at the edge of the vibration groove and used for collecting images; the microcomputer controller identifies large-particle impurities in the acquired image after sequentially performing vignetting correction processing, automatic gain processing and white balance processing on the acquired image, generates a control signal according to an identification result and sends the control signal to the interception net control assembly; the vibration tank vibrates up and down to move so that impurities in the vibration tank move to the middle part, the interception net control assembly controls the interception net to rise according to a control signal, large-particle impurities in the middle part of the vibration tank are intercepted in the interception net and are removed through an impurity removal pipeline, and dust impurities penetrating through the interception net are discharged through the conveying tank at the end part of the vibration tank. The online impurity removal requirement of a single group or multiple groups of impurity removers can be met.
Description
Technical Field
The invention belongs to the technical field of dust removal, and particularly relates to an impurity removal system with an image recognition function.
Background
The pneumatic dust removal is the mainstream technology of the tobacco shred dust removal of domestic tobacco enterprises at present, and the pneumatic dust removal is to convey waste such as cigarette ash and the like generated in the production process of a cigarette making machine to an impurity removing machine through an impurity removing pipeline by negative pressure induced draft generated by a fan and to carry out the next screening and impurity removing work. The cigarette making machine inevitably carries a small amount of tobacco stems and tobacco ash blocks together with the tobacco ash to enter a downstream impurity removing machine in the high-speed operation process, and the tobacco stems and the tobacco ash blocks not only easily block a dust removing pipeline due to large volume, but also can increase the working load of the impurity removing machine and shorten the service life of the impurity removing machine.
Traditional cigarette edulcoration system adopts the screening structure, be about to the discarded object such as cigarette ash that produces in the cigarette machine production process at first induced draft through the negative pressure and get into the groove that shakes of terminal shaker, then shake through shaker shake groove shake repeatedly, with likepowder cigarette ash, tiny particle offal or fritter form cigarette ash drop to the collection bag in below through shaking the groove screen cloth, at last by the collection bag concentrate likepowder cigarette ash in the discarded object utilize the negative pressure induced draft with it all inhale in the shaker, tiny particle offal or fritter form cigarette ash in the discarded object then are inhaled the stalk extractor, pack after smashing by the stalk extractor.
The impurity removal system adopting the structure has obvious disadvantages: firstly, this structure can not guarantee discarded object such as cigarette ash, offal and can separate completely, because the sieve mesh aperture of the groove screen cloth that shakes is fixed, when doing simple separation to offal and cigarette ash, the segment offal can be shaken together and fall to collecting in the bag, causes the shaker edulcoration thoroughly, and stereoplasm offal can cause the damage of shaker inner part even. Secondly, the structure can not ensure that the cigarette ash blocks can effectively shake off, because most of the cigarette ash blocks are in a sticky mass shape, the shaking of the shaking groove can not effectively shake off the cigarette ash blocks, and the cigarette ash blocks can be bonded on the inner wall of the stem extractor after entering the stem extractor along with the tobacco stems, so that the normal operation of a motor inside the stem extractor is seriously influenced or a stem extraction channel is blocked. Thirdly, this structure can not guarantee that the negative pressure induced draft in the shaker keeps smooth and easy for a long time, discarded object such as tobacco ash, offal in the dust removal pipe is induced draft through the negative pressure and is driven and finally flow to the shaker, because the groove screen cloth that shakes in this structure can not effectively separate segment offal and cigarette ash cubic, long this past, segment offal and cigarette ash cubic can pile up on the screen cloth surface, it flows to hinder near the negative pressure induced draft of screen cloth, arouse that the negative pressure inlet scoop blocks up, cause the undersize to induced draft, and the negative pressure induced draft of this department is the air supply all the way with the negative pressure induced draft in the dust removal pipe network, these will jointly influence the interior negative pressure of dust removal pipeline and induced draft smoothly, very easily cause the interior jam of dust removal pipeline, in case block up, will consume a large amount of people and material resources and carry out broken pipe row stifled.
Therefore, there is a need for an impurity removal system that can quickly detect and accurately remove large pieces of foreign matter. There are many ways to do this, for example: the south China university (Weiyanda. IC card surface printing defect detection system based on machine vision is designed and realized [ D ] the south China university Master thesis, 2015) designs a printing image defect detection scheme based on an image difference distinguishing method, the scheme is divided into two steps of preprocessing and real-time detection, the preprocessing mainly corrects distortion of a lens, sets various image detection parameters and thresholds and makes a standard template, and the real-time detection comprehensively applies various image processing algorithms such as median filtering, image graying, image registration, image difference, image segmentation, mathematical morphology processing, Blob analysis and the like. The university of cigarette end (zhang ran. study of machine vision-based glass edge grinding defect detection and application [ D ] major paper of Shandong cigarette end university, 2018) adopts a machine vision technology, combines the imaging principle of an industrial CCD camera and an image processing technology (noise reduction, sharpening, segmentation, edge detection, mathematical morphology and file storage format), and studies out a feature extraction method of bright spots, edge explosion and white lines in the glass processing process. Shaanxi science and technology university (Wei Yi Ye, paper function information recognition research [ D ] based on image processing technology, Shaanxi science and technology university Master thesis, 2018) proposes an improved algorithm based on ORB, a BBF search algorithm is adopted to accelerate a nearest distance ratio matching criterion to complete matching, and after mismatching points are removed by using a RANSAC algorithm, a perspective transformation matrix is calculated to mark and recognize. The bar code image is identified by a maximum inter-class method and corrected by a gamma correction algorithm by using a digital camera with a CCD image sensor at North China Power university (Guo iron bridge, research [ D ] of a bar code identification system based on an image processing technology, Master thesis of North China Power university, 2014).
The method improves the scanning precision by scanning bar codes and adopting a corresponding algorithm, and the method cannot be suitable for cured substances such as cigarette ash, tobacco stems and the like. Or the characteristic quantities of bright spots, broken edges and white lines in the image are picked up to the maximum extent by methods of supplementing light to the shooting scene, adding an image sensor and the like, so that the definition and the identification degree of the acquired image are enhanced. Or the adjustment is differentiated by comparing with standard settings or templates, and the adjustment is fixed and has weak adaptability to the environment and the scene. Therefore, these methods have certain limitations for identifying flowing ash, tobacco stems and other waste materials.
Disclosure of Invention
In view of the above, the invention provides an impurity removal system with an image recognition function, which scans and recognizes wastes such as tobacco ash and tobacco stems through an image sensor, effectively removes small sections of tobacco stems and tobacco ash blocks through a removing device, and can meet the online impurity removal requirement of a single-group or multi-group impurity remover.
The technical scheme of the invention is as follows:
an impurity removal system with an image recognition function comprises an eliminating device, an image sensor and a signal processor;
the removing device comprises a vibration groove which is obliquely arranged and can vibrate up and down, an interception net and a control assembly thereof which are embedded in the bottom of the center of the vibration groove, and an impurity removing pipeline which is embedded in the middle of the vibration groove;
the image sensor is arranged at the edge of the vibration groove and used for collecting images;
the signal processor identifies large-particle impurities in the image after sequentially performing vignetting correction processing, automatic gain processing and white balance processing on the acquired image, generates a control signal according to an identification result and sends the control signal to the interception net control assembly;
the vibration tank vibrates up and down to enable impurities in the vibration tank to move towards the middle, the interception net control assembly controls the interception net to rise according to a control signal, large-particle impurities in the middle of the vibration tank are intercepted in the interception net and are removed through an impurity removal pipeline, and dust impurities penetrating through the interception net are discharged through the conveying tank at the end of the vibration tank.
Preferably, the intercepting net assembly comprises a communication module, a lifting rod connected with the intercepting net, an air valve connected with the lifting rod, an air inlet pipe and an air outlet pipe connected with the air valve, and an air valve island for controlling expansion and compression of the air valve, and after the communication module receives a control signal, the air valve island controls expansion of the air valve according to the control signal to drive the lifting rod to rise and then rise the intercepting net so as to realize connection of large-particle impurities.
Preferably, the edulcoration pipeline is including setting up at the rejection mouth of the groove bottom that shakes, connecting the conveying line who rejects the mouth, is equipped with valve, filter screen, air pressure regulating valve along direction of delivery in proper order on the conveying line, and air pressure regulating valve is connected with the negative pressure aspiration channel for absorb through the filterable dust impurity of filter screen, still not dredging the pipe on the conveying line between valve and filter screen, dredging the pipe is equipped with the negative pressure and induced drafts, is used for absorbing large granule impurity.
Preferably, a valve motor is further arranged on the conveying pipeline and used for controlling the valve to be opened or closed.
Preferably, the trash removal system further comprises a light source, which may be a strobe light.
Preferably, the vibration groove is evenly distributed with at least 1 pair of vibration groove feet, the vibration groove feet realize up-and-down vibration motion through a spring and further drive the vibration groove to vibrate up-and-down vibration motion, the image sensor is at least 1 pair, and the image sensor is evenly distributed and installed on the edge of the vibration groove.
Wherein, the vignetting correction processing process for the collected image comprises the following steps:
first, a uniform white light source is established, the input intensity level of the white light source on a reference target of lower specular reflection is collected with an image sensor, which is now directed to the reference surface, the response value for each pixel position is recorded, and then a correction factor for each pixel position is calculated according to the following formula:
wherein, IREF(x, y) is the gray scale factor of the contaminant at the pixel location (x, y), x and y tend to be positive infinite integer values, JLT(x, y) is a set of corresponding correction factors, which are stored in a look-up table;
then, aiming at the collected image of the image sensor at the same angle, the vignetting correction is realized by multiplying the pixel value of the image by the corresponding correction factor in the lookup table:
IMG(x,y)＝H(x,y)*JLT(x,y)
where IMG (x, y) represents the vignetting corrected image, and H (x, y) represents the pixel value of the captured image at position (x, y).
Wherein, the automatic gain processing process of the image after the vignetting correction comprises the following steps:
and (3) performing automatic gain processing on the image after the vignetting correction according to the radiation illumination and the exposure system by adopting the following formula:
IMG'(x,y)＝kL(x,y)+k(1-α)
wherein, IMG '(x, y) represents the image after the automatic gain, L (x, y) is the radiance value corresponding to the image IMG' (x, y), k represents the exposure coefficient (k is a constant) when the image sensor collects the image, and α represents the resolution of the image sensor.
The white balance processing process of the image after automatic gain comprises the following steps:
IMG'BAL(x,y)＝R'BAL(x,y)*G'BAL(x,y)*B'BAL(x,y)
wherein, IMG'BAL(x, y) represents a white-balanced image, R'BAL(x,y)、G'BAL(x,y)、B'BAL(x, y) are RGB three-channel images after white balance processing respectively, and the specific process is as follows:
wherein r represents an adjustment parameter, r is within 0,99]，L(xk,yk) Representing the radiance value of an image IMG' (x, y) containing an exposure coefficient k,
respectively representing weighted gain pixels, and the calculation formula is as follows:
where k denotes an exposure coefficient when the image sensor acquires an image, R (x)k,yk) Denotes an R gain pixel having an exposure coefficient k, B (x)k,yk) Representing a B gain pixel, G (x), having an exposure coefficient kk,yk) Representing the G gain pixel containing the exposure coefficient k,
preferably, the gain pixels are weighted during white balance processing of the automatically gained image
Using adaptively weighted gain pixels
Respectively as follows:
compared with the prior art, the invention has the beneficial effects that at least:
according to the impurity removal system with the image recognition function, the image sensor is used for collecting images, the processor is used for sequentially carrying out vignetting correction processing, automatic gain processing and white balance processing on the collected images, then medium and large particle impurities are recognized and a control signal is generated, and the removal device is used for removing impurities according to the control signal.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic structural diagram of an impurity removal system with an image recognition function according to an embodiment;
FIG. 2 is a schematic structural diagram of an intercepting net and its control components provided by the embodiment;
FIG. 3 is a diagram illustrating a closed state of a top cover of the rejection port according to an embodiment;
FIG. 4 is a diagram illustrating an open state of a top cover of the rejection port according to the embodiment;
FIG. 5 is a schematic diagram of a screen structure provided by an embodiment;
FIG. 6 is a schematic diagram of an image vignetting correction process provided by an embodiment;
FIG. 7 is a schematic diagram of an automatic gain implementation process provided by an embodiment;
fig. 8 is a schematic diagram of an image white balance process provided by the embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the detailed description and specific examples, while indicating the scope of the invention, are intended for purposes of illustration only and are not intended to limit the scope of the invention.
FIG. 1 is a schematic structural diagram of an impurity removal system with an image recognition function according to an embodiment. Fig. 2 is a schematic structural diagram of an intercepting network and its control components according to an embodiment. As shown in fig. 1 and fig. 2, an embodiment provides a trash removal system including: the system comprises a stroboscopic lamp 1, a rejection device 2, an image sensor 3, a microcomputer controller 4, a signal processor 5 and a PLC (programmable logic controller) 11. The stroboscopic lamp 1 is an LED stroboscopic lamp, when light is supplemented to the photosensitive element of the image sensor 3, the flashing duration time of the LED stroboscopic lamp is within 4ms, the flashing duration time during the light supplementing depends on the scene shooting pixel requirement, 1000 ten thousand pixels are 80ms, 800 ten thousand pixels are 60ms, and 500 ten thousand pixels are 28ms, so that the flashing duration time of the LED stroboscopic lamp can be set under various light conditions, and the light supplementing requirement of the image sensor 3 can be met.
Removing devices 2 sets up and presents oval hourglass hopper-shaped groove 6 that shakes including the slope, the embedding shakes the interception net and the control assembly 7 of groove center bottom, the embedding shakes impurity removal pipeline 8 at groove middle part, shake groove footing 9 and shake the cigarette ash conveying trough 10 of 6 edge ends in groove, wherein, it is 4 to shake groove footing 9, evenly distributed is shaking around groove 6, oscillation motion about realizing through the spring and then drive 6 oscillation motions about shaking groove, image sensor 3 is also 4, evenly distributed installs at 6 edges in groove that shakes, be used for gathering the image.
As shown in fig. 2, the intercepting net and the control component 7 thereof include an intercepting net 71, a communication module 72, a lifting rod 73, an air valve 74, an air inlet pipe 75, an air outlet pipe 76, an air valve island 77 and a power switch 78, the lifting rod 73 is connected with the intercepting net, one end of the air valve 74 is connected with the lifting rod 73, the air inlet pipe 75 and the air outlet pipe 76 are simultaneously connected with the other end of the air valve 74, the air valve island 76 is used for controlling expansion and compression of the air valve, and after receiving a control signal through the communication module 72, the air valve island 77 controls expansion of the air valve 74 according to the control signal to drive the lifting rod 73 to be lifted so as to lift the intercepting net 71, so as to realize connection of large-particle impurities.
In the embodiment, the interception net 71 is an elliptical metal 200-mesh gauze with edges, and is vibrated up and down by the positive pressure air below the interception net to intercept blocky cigarette ash and cigarette rods and enable the blocky cigarette ash and the cigarette rods to be gathered near the rejection opening 81.
In this embodiment, the front end of the removing opening 81 is adjustable and slightly protruded, so that the waste such as the cigarette ash and the tobacco stems can be effectively sucked. And the removing opening 81 is supported by a top cover 89 through a top cover spring support, and the top cover is in a closed state and an open state as shown in fig. 3 and 4.
The PLC 11 adopts a Siemens S7-300 system controller, and the microcomputer controller 4 adopts a Siemens 427D series microcomputer controller which has the characteristic of stable operation in a high-temperature and high-humidity environment, so that the PLC has the advantages of high operation reliability and rich interfaces. The collected image of the image sensor 3 is sent to the microcomputer controller 4. The microcomputer controller 4 identifies large-particle impurities in the collected image after the vignetting correction processing, the automatic gain processing and the white balance processing are sequentially carried out on the collected image, generates a control signal according to an identification result and sends the control signal to the interception net control component 7. The interception net control component 7 controls the interception net 71 to rise according to the control signal, intercepts large-particle impurities in the middle of the vibrating groove 6 in the interception net 71, eliminates the large-particle impurities through the impurity removal pipeline 8, and discharges the dust impurities penetrating through the interception net 71 through the conveying groove in the end part of the vibrating groove.
In the impurity removing system, waste such as tobacco stems, tobacco ash and the like are identified one by an image sensor before entering an impurity removing machine through an eliminating device, a light source for identification is from a strobe light arranged at the outlet position of the eliminating device, however, the bright light emitted by the strobe light is diffused and cannot uniformly irradiate the light on the tobacco stems and the tobacco ash, so that the light intensity is attenuated when the light reaches the convex surface of the image sensor, namely, the brightness at the periphery of an image is weakened, the change of the light intensity along with the positions of the tobacco stems and the tobacco ash is called a vignetting effect, and the following influence factors are generally included: (1) pore size effect: the aperture effect is generated when the aperture of the image sensor shields part of light, and the vignetting effect is more obvious when the effective aperture of the aperture is larger. (2) Pupil difference: the diffuse emission of the strobe light is partially refracted by surrounding objects (e.g., the walls of the dust removal tube) and results in a very uneven distribution of light across the aperture of the image sensor.
The vignetting correction should be performed because the image sensor generates a vignetting effect due to the uneven distribution of the flash light illumination amount. Specifically, as shown in fig. 6, the process of performing vignetting correction on the acquired image includes:
first, a uniform white light source is established, the input intensity level of the white light source on a reference target of lower specular reflection is collected with an image sensor, which is now directed to the reference surface, the response value for each pixel position is recorded, and then a correction factor for each pixel position is calculated according to the following formula:
wherein, IREF(x, y) is the gray scale factor of the contaminant at the pixel location (x, y), x and y tend to be positive infinite integer values, JLT(x, y) is a set of corresponding correction factors, which are stored in a look-up table;
then, aiming at the collected image of the image sensor at the same angle, the vignetting correction is realized by multiplying the pixel value of the image by the corresponding correction factor in the lookup table:
IMG(x,y)＝H(x,y)*JLT(x,y)
where IMG (x, y) represents the vignetting corrected image, and H (x, y) represents the pixel value of the captured image at position (x, y).
By carrying out vignetting correction processing on the collected image, the vignetting effect generated in the image collection process can be weakened or eliminated, the vignetting correction effect is automatically realized, and the image can be subjected to high-quality image collection in a dim light scene.
Wastes such as cigarette ash, tobacco stems and the like flow all the time in the dust removing pipe, and the dynamic range of a scene acquired by the image sensor is limited, so that the acquired image is compressed to the maximum extent in the dynamic scene, and then the image is expanded to realize the automatic gain effect, so that the acquired image can be acquired in the maximum range under the high-speed flowing state. As shown in fig. 7, when compressing the scene dynamic range of the image sensor, a non-linear relationship is introduced between the pixel value H (x, y) of the image location (x, y) and the image radiation illuminance L (x, y), which can be described as:
H(x,y)＝kL(x,y)
in general, in a removing device, when wastes such as soot and tobacco stalk flow rapidly, the image sensor is prone to losing frames after compressing a collected image in a dynamic range, so that image quality is reduced, and therefore automatic gain needs to be performed on the image.
The automatic gain is obtained by a fast gain change in the thermal imaging of the image sensor, assuming an IMG of the image at different exposure settings of the image sensor and vignetting corrected1(x, y) and IMG2(x, y) characterizing the correspondence between pixel values before and after exposure change by designing a parameter-containing model, thus generating a function related to pixel values before and after exposure change, called exposure response function, which is constructed by affine transformation during image capture and phasing of the image sensor, as follows:
C2(x,y)＝(choose(IMG1(x,y),IMG2(x,y)))
f(x,y)＝compare(C1(x,y),C2(x,y))
where α denotes a resolution of the image sensor and β denotes the image sensorSensitivity, r denotes the image sensor operating wavelength, C1Representing the pixel value of the image before exposure at position (x, y), C2Representing the pixel value of the image after exposure at position (x, y), f (x, y) representing the exposure response function, and outputs 0 or 1, 0 representing no change before and after exposure of the image pixel, and 1 representing a change before and after exposure of the image pixel. C2(x, y) indicates that the system will randomly first choose the IMG1(x, y) or IMG2Any one of the two images (x, y) is compared next, and the other image is compared after the images are compared, so that only one image can be selected in each comparison by using the choose command, and because the comparison between the image pixels wastes computer memory and takes a lot of time, the memory and the time can be saved by only using one image for comparison each time
For affine transformation, when the image sensor operating wavelength r is 1, the exposure response function of f (x, y) and f (kx, ky) is a linear function, as follows:
f(kx,ky)＝kf(x,y)+α(1-k)
the operating wavelength of the image sensor is a variable value, the wavelength range is generally in the range of 0.2-1, the exposure response function is linear only when the wavelength of the image sensor reaches the maximum range, but the premise is that the image currently acquired by the image sensor must be a vignetting corrected image, namely f (x, y) ═ zooseimg (x, y), and then the exposure of the image sensor is the highest, namely the automatic gain effect is the most obvious.
When the wavelength of the image sensor reaches the maximum range, the automatic gain effect of the image sensor is most obvious, so that the vignetting correction of the wastes such as the cigarette ash, the tobacco stems and the like at the current position is carried out, and the automatic gain image is as follows:
IMG'(x,y)＝kL(x,y)+k(1-α)
wherein, IMG '(x, y) represents the image after the automatic gain, L (x, y) is the radiance value corresponding to the image IMG' (x, y), k represents the exposure coefficient when the image sensor collects the image, k is a constant, and α represents the resolution of the image sensor.
If the cigarette ash and the tobacco stems are continuously captured by the image sensor in a flowing state in the same scene and are subjected to vignetting correction and automatic gain, the gray levels of the two images have the following relation:
IMG'2(x,y)＝T*IMG'1(x,y)
in the formula, T is called a gray scale transfer function, and generally T is a monotone increasing function passing through an origin, the magnitude of the function value of T determines the smoothness and fineness of the image when the image is converted and transited, and the magnitude of the function value of T also determines the image storage size. The automatic gain implementation process is shown in fig. 7.
When the image sensor acquires images of wastes such as cigarette ash, tobacco stems and the like, besides the monochrome images, color images can also be adopted. The color image can identify and scan the size, color, shape and the like of the waste more intuitively, but the input colors of the color image are different, which is closely related to the illumination condition of a strobe light during image acquisition, and different light sources have different spectral characteristics, so for a scene light source, the acquired image needs to be adjusted to enable the color of the image to be as original as possible. To this end, white balance techniques are introduced.
White balance is a method for automatically adjusting image color, parameters are set by searching for white-like areas in an image (the white-like areas refer to that soot and tobacco stems are acquired by an image sensor in a flowing state, and the image color of partial areas in the acquired image is close to the real image color), and then the color of the rest parts of the image is adjusted to be close to or reach the image color of the white-like areas.
Defining IMG ' (x, y) as an image with vignetting correction and automatic gain of size M N (M is length, N is width), then white balance aims to adjust the colors of IMG ' (x, y) to generate a color balanced RGB image, i.e. a color image, to generate IMG 'BALImage, each component of which is R'BAL(x,y)、G'BAL(x,y)、B'BAL(x, y), namely:
IMG'BAL(x,y)＝R'BAL(x,y)*G'BAL(x,y)*B'BAL(x,y)
since the wavelength of the gray pattern is the shortest in the color image, the wavelength is longThe storage size of the image is directly determined, so that the gray scale mode of the RGB image (namely the color image) is selected, and the image quality and the storage size can be well considered. After selecting the gray mode of the RGB image, when performing the white balance of the image, R 'is generated by the following formula by adopting the white balance algorithm of the gray mode'BAL(x,y)、G'BAL(x,y)、B'BAL(x, y), i.e.
Wherein r represents an adjustment parameter, r is within 0,99]，L(xk,yk) Representing the radiance value of an image IMG' (x, y) containing an exposure coefficient k,
respectively representing weighted gain pixels, and the calculation formula is as follows:
where k denotes an exposure coefficient when the image sensor acquires an image, R (x)k,yk) Denotes an R gain pixel having an exposure coefficient k, B (x)k,yk) Representing a B gain pixel, G (x), having an exposure coefficient kk,yk) Representing the G gain pixel containing the exposure coefficient k,
weighted gain pixel
However, such an operation result usually takes time, and it takes a long time to search for a white-like region in the color image. Therefore, the algorithm needs to be improved so that the operation result can be fully covered, thereby improving the searching speed. This improved algorithm is called an adaptive white balance algorithm.
The adaptive white balance algorithm replaces R, G, B three pixels with all pixels in the input image, and in this algorithm, allows
And
any variation can be made to either weight the gain or the vignetting to accommodate all pixels. The self-adaptive white balance algorithm of the color image in the gray scale mode is as follows:
wherein,
respectively RGB three channels adaptive weighted gain pixels, and correspondingly, in the adaptive white balance algorithm, R 'is generated by the following formula'BAL(x,y)、G’BAL(x, y) and B'BAL(x, y) are respectively:
where r is a constant value adjustable to obtain an optimum result, r is selected to be r ∈ [100,300] in the normal mode of the 24-bit input image (color), and r ∈ [0,99] in the grayscale mode of the 24-bit input image (color). The image white balance process is as shown in fig. 8, and it can be seen that the value of r is selected in relation to the image white balance effect, and a corresponding value is necessary when selecting the value of r, rather than the larger the value is, the better the value is, otherwise the image may exceed the wavelength range when passing through the adaptive weighting gain, which causes distortion.
The white balance processing is carried out on the image after the vignetting correction processing and the automatic gain processing, the single-color or color image acquisition can be realized on the sample, the white balance effect is automatically realized, and meanwhile, the gray mode of the color image is adopted, so that the optimal image acquisition quality and the minimum image storage size are achieved.
The microcomputer controller identifies large-particle impurities, namely tobacco stems and the like in the image after the vignetting correction processing, the automatic gain processing and the white balance processing are sequentially carried out on the collected image, generates a control signal according to an identification result and sends the control signal to the interception net control assembly to control the interception net 71 to rise so as to intercept the large-particle impurities, and the large-particle impurities are removed through an impurity removal pipeline.
The working process of the impurity removing system with the image recognition function comprises the following steps:
when impurities such as cigarette ash and tobacco stems enter the vibration groove 6, the strobe light 1 starts to work to provide a lighting light source for shooting in the vibration groove 6 and light supplement needs under various light conditions. The image sensor 3 totally four are installed respectively around groove 6 shakes for discerning cubic cigarette ash and the tobacco rod that mix with in the cigarette ash, owing to shake groove 6 and be the slope, set up the screen cloth on 6 surfaces in groove that shakes, can be used for carrying layer upon layer, cubic cigarette ash, tobacco rod and loose cigarette ash when shaking groove 6 up-and-down motion to carry out simple separation to them, the separation principle is: because the block-shaped cigarette ash and the cigarette rod are heavy, the loose cigarette ash is light and is acted by a stepped structure (as shown in figure 5) on the surface of the screen, simple separation can be carried out in the moving process, the precise separation also depends on subsequent image identification for screening, namely, when the vibration groove 6 moves up and down through four vibration groove bottom feet 9 at the bottom, the block-shaped cigarette ash, the cigarette rod and the loose cigarette ash gradually move from a point B in the figure to a point C through the vibration groove and finally to a point A, in the process of reaching the point C from the point B, the image sensors 3 around the vibration groove 6 continuously acquire images, the image information is processed in a digital mode (vignetting correction processing, automatic gain processing and white balance processing) by the signal processor 5 to generate control signals and is transmitted to the microcomputer controller 4, at the moment, the microcomputer controller 4 executes a control strategy program compiled by the control strategy method, the program is output to the PLC controller 11 after the program is executed, the PLC 11 controls the interception net 71 at the lower end of the screen to jack up so as to intercept the identified blocky cigarette ash and cigarette rods, at the moment, the blocky cigarette ash and the cigarette rods are gathered in the C area and cannot move to the point A, the intercepted blocky cigarette ash and cigarette rods can be gradually gathered near the rejection port 81, when the negative pressure air suction is opened, the top cover at the end of the rejection port 81 can be turned downwards under the action of the negative pressure air suction, and the blocky cigarette ash and cigarette rods can be sucked by the rejection port along with the trend; when loose cigarette ash passes through, the interception net 71 descends, the negative pressure air suction of the removing opening 81 is closed, the top cover of the removing opening is automatically turned upwards under the action of a spring support to ensure that the loose cigarette ash cannot fall into the removing opening, and the loose cigarette ash passes through the closed removing opening from the point C in the figure, reaches the point A in the figure and is conveyed out through the cigarette ash conveying groove (the cigarette ash conveying groove also has the negative pressure air suction). The removing port 81 is in a three-pipe round port shape, thereby improving the suction range. When the block-shaped cigarette ash and the cigarette rod vertically pass through the valve 83 along the rejecting caliber, the valve 83 is controlled by the valve motor 88 to open and close. The ash and tobacco rod continue downwards through the filter screen 84, where they are intercepted by the filter screen 84 and sucked out of the tube body by the dredging tube 87. The air pressure regulating valve 85 is used for regulating negative pressure to be sucked to a proper size, because the filter screen 84 is abraded too fast due to too large suction, and the blocked cigarette ash and cigarette stems in the removing opening 81 are blocked due to too small suction. The aspiration channel adopts a hose, and the tail end of the aspiration channel is connected with a vacuum pump.
In general, embodiments provide vignetting correction steps that are: firstly, a stroboscopic lamp can provide a white light source with consistent light color, the light source can ensure that wastes such as soot, tobacco rods and the like can still be irradiated even in a dark environment, at the moment, the image sensors arranged around the vibrating groove can identify blocky soot and tobacco rods mixed in the soot and generate pixel positions, then a response value of each pixel position is recorded by a system, a correction factor of each pixel position is obtained through conversion, and finally, subsequent images acquired by the image sensors at the same angle can realize vignetting correction by multiplying the image pixel values and the corresponding correction factors.
Generally, the embodiment provides the following automatic gain steps: the method comprises the steps of firstly capturing waste images of soot, tobacco stems and the like in a dynamic scene through an image sensor, then performing system vignetting correction after image imaging, then automatically generating a corresponding exposure response function by a system, wherein the exposure response function comprises a wavelength range (variation value), and finally determining the linear relation of the exposure response function through the value size of the wavelength range, namely determining whether the automatic gain effect of the system is obvious or not, and determining the image storage size through the value size of the wavelength range.
Overall, the embodiment provides the white balancing steps of: the method comprises the steps of firstly capturing waste images of soot, tobacco stems and the like in a dynamic scene through an image sensor, carrying out vignetting correction and automatic gain by a system after the images are imaged, then setting a parameter by searching a white-like area in the images through the system, and finally adjusting the color of the rest part of the images through the parameter to approach or reach the image color of the white-like area, namely the image color is close to the original color.
In this embodiment, there are interdependencies and inseparable relationships among the three processing procedures of vignetting correction, automatic gain and white balance, and the order of implementation of the three processing procedures cannot be reversed.
Above-mentioned impurity removal system who possesses image recognition function who provides gathers the image with image sensor, through the treater to gather the image and carry out vignetting correction in proper order and handle, automatic gain and discern the medium and large granule impurity and generate control signal after white balance handles, removing devices realizes the edulcoration according to this control signal, and the edulcoration is efficient, effectual.
The above-mentioned embodiments are intended to illustrate the technical solutions and advantages of the present invention, and it should be understood that the above-mentioned embodiments are only the most preferred embodiments of the present invention, and are not intended to limit the present invention, and any modifications, additions, equivalents, etc. made within the scope of the principles of the present invention should be included in the scope of the present invention.
Claims (9)
1. An impurity removal system with an image recognition function is characterized by comprising a rejection device, an image sensor and a signal processor;
the removing device comprises a vibration groove which is obliquely arranged and can vibrate up and down, an interception net and a control assembly thereof which are embedded in the bottom of the center of the vibration groove, and an impurity removing pipeline which is embedded in the middle of the vibration groove;
the image sensor is arranged at the edge of the vibration groove and used for collecting images;
the signal processor identifies large-particle impurities in the image after sequentially performing vignetting correction processing, automatic gain processing and white balance processing on the acquired image, generates a control signal according to an identification result and sends the control signal to the interception net control assembly;
the vibration tank vibrates up and down to enable impurities in the vibration tank to move towards the middle part, the interception net control assembly controls the interception net to rise according to a control signal, large-particle impurities in the middle part of the vibration tank are intercepted in the interception net and removed through an impurity removal pipeline, and dust impurities penetrating through the interception net are discharged through a conveying tank at the end part of the vibration tank;
the intercepting net assembly comprises a communication module, a lifting rod connected with the intercepting net, an air valve connected with the lifting rod, an air inlet pipe and an air outlet pipe connected with the air valve, and an air valve island for controlling expansion and compression of the air valve, wherein after the communication module receives a control signal, the air valve island controls expansion of the air valve according to the control signal to drive the lifting rod to rise and then rise the intercepting net so as to realize connection of large-particle impurities.
2. The system according to claim 1, wherein the impurity removing pipeline comprises a removing opening disposed at the bottom of the vibrating trough and a conveying pipeline connected to the removing opening, the conveying pipeline is sequentially provided with a valve, a filter screen and an air pressure regulating valve along a conveying direction, the air pressure regulating valve is connected to a negative pressure suction pipe for absorbing dust impurities filtered by the filter screen, the conveying pipeline between the valve and the filter screen is not provided with a dredging pipe, and the dredging pipe is provided with a negative pressure suction fan for absorbing large particle impurities.
3. The impurity removing system with the image recognition function as claimed in claim 2, wherein a valve motor is further arranged on the conveying pipeline and used for controlling the valve to be opened or closed.
4. The system according to claim 1, wherein at least 1 pair of feet of the vibration tank are uniformly distributed around the vibration tank, the feet of the vibration tank perform vertical oscillating motion through a spring to drive the vibration tank to perform vertical oscillating motion, and the image sensors are at least 1 pair and are uniformly distributed on the edge of the vibration tank.
5. The trash removal system with an image recognition function of claim 1 or 4, wherein the trash removal system further comprises a light source.
6. The impurity removing system with image recognition function according to claim 1, wherein the vignetting correction processing process for the collected image is as follows:
first, a uniform white light source is established, the input intensity level of the white light source on a specularly reflected reference target is captured with an image sensor, which is now directed at the reference surface, the response value for each pixel position is recorded, and then a correction factor for each pixel position is calculated according to the following formula:
wherein, IREF(x, y) is the gray scale factor of the contaminant at the pixel location (x, y), x and y tend to be positive infinite integer values, JLT(x, y) is a set of corresponding correction factors, which are stored in a look-up table;
then, aiming at the collected image of the image sensor at the same angle, the vignetting correction is realized by multiplying the pixel value of the image by the corresponding correction factor in the lookup table:
IMG(x,y)＝H(x,y)*JLT(x,y)
where IMG (x, y) represents the vignetting corrected image, and H (x, y) represents the pixel value of the captured image at position (x, y).
7. The impurity removing system with image recognition function according to claim 1, wherein the automatic gain processing process of the image after vignetting correction is as follows:
and (3) performing automatic gain processing on the image after the vignetting correction according to the radiation illumination and the exposure system by adopting the following formula:
IMG'(x,y)＝kL(x,y)+k(1-α)
wherein, IMG '(x, y) represents the image after the automatic gain, L (x, y) is the radiance value corresponding to the image IMG' (x, y), k represents the exposure coefficient when the image sensor collects the image, k is a constant, and α represents the resolution of the image sensor.
8. The trash removal system with an image recognition function of claim 1, wherein the white balance processing of the image after the automatic gain is:
IMG'BAL(x,y)＝R'BAL(x,y)*G'BAL(x,y)*B'BAL(x,y)
wherein, IMG'BAL(x, y) represents a white-balanced image, R'BAL(x,y)、G'BAL(x,y)、B'BAL(x, y) are RGB three-channel images after white balance processing respectively, and the specific process is as follows:
wherein r represents an adjustment parameter, r is within 0,99]，L(xk,yk) Representing the radiance value of an image IMG' (x, y) containing an exposure coefficient k,
respectively representing weighted gain pixels, and the calculation formula is as follows:
where k denotes an exposure coefficient when the image sensor acquires an image, R (x)k,yk) Denotes an R gain pixel having an exposure coefficient k, B (x)k,yk) Representing a B gain pixel, G (x), having an exposure coefficient kk,yk) Representing the G gain pixel containing the exposure coefficient k,
9. the system of claim 8, wherein the weighted gain pixels are weighted during white balance processing of the automatically gained image
Using adaptively weighted gain pixels
Respectively as follows:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011184658.4A CN112291547B (en) | 2020-10-29 | 2020-10-29 | Impurity removal system with image recognition function |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011184658.4A CN112291547B (en) | 2020-10-29 | 2020-10-29 | Impurity removal system with image recognition function |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112291547A CN112291547A (en) | 2021-01-29 |
| CN112291547B true CN112291547B (en) | 2022-01-04 |
Family
ID=74352550
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011184658.4A Active CN112291547B (en) | 2020-10-29 | 2020-10-29 | Impurity removal system with image recognition function |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112291547B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113317548B (en) * | 2021-06-10 | 2022-09-13 | 广东中烟工业有限责任公司 | Threshing and redrying impurity removal device, method, equipment and medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4829379A (en) * | 1986-03-31 | 1989-05-09 | Mitsubishi Denki Kabushiki Kaisha | Picture image signal compensation device |
| CN1184498A (en) * | 1995-03-20 | 1998-06-10 | 东陶机器株式会社 | Method of photocatalytically making the surface of base material ultrahydrophilic, base material having ultrahydraphilic and photocatalytic surface, and process for producing said material |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB1030912A (en) * | 1963-05-14 | 1966-05-25 | Deltech Eng Inc | Improvements in or relating to the filtering of gaseous fluids |
| EP0267783A3 (en) * | 1986-11-12 | 1989-02-01 | Pall Corporation | Filter device |
| DE8717960U1 (en) * | 1986-12-22 | 1991-10-17 | AG für industrielle Elektronik AGIE Losone bei Locarno, Losone | Labyrinth filters for the dielectric of EDM systems |
| JP2003037765A (en) * | 2001-07-24 | 2003-02-07 | Matsushita Electric Ind Co Ltd | Iris imager device |
| CN103817083A (en) * | 2014-02-24 | 2014-05-28 | 三星高新电机（天津）有限公司 | Tiny product high-speed screening device |
| CN111767871A (en) * | 2020-06-30 | 2020-10-13 | 武汉轻工大学 | System and method for cleaning screen surface of grain cleaning machine |
-
2020
- 2020-10-29 CN CN202011184658.4A patent/CN112291547B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4829379A (en) * | 1986-03-31 | 1989-05-09 | Mitsubishi Denki Kabushiki Kaisha | Picture image signal compensation device |
| CN1184498A (en) * | 1995-03-20 | 1998-06-10 | 东陶机器株式会社 | Method of photocatalytically making the surface of base material ultrahydrophilic, base material having ultrahydraphilic and photocatalytic surface, and process for producing said material |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112291547A (en) | 2021-01-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106872465B (en) | Poultry fertilized egg detection and screening device based on machine vision | |
| CN104062298B (en) | Combined harvester tanker seed percentage of impurity automated watch-keeping facility and method based on image procossing | |
| CN107309181B (en) | A kind of pearl intelligent sorting system based on machine vision | |
| CN1485616A (en) | Fowl eggs quality non-destruction automatic detection grading apparatus and process | |
| CN112291547B (en) | Impurity removal system with image recognition function | |
| CN109269951A (en) | Floating tail-coal ash content, concentration, coarse granule detection method of content based on image | |
| CN210449939U (en) | High-efficient rice look selection machine | |
| KR20090033568A (en) | The white and brown rice appearance characteristics measurement system and the same method | |
| JP2007283204A (en) | Color sorting apparatus | |
| CN206325858U (en) | A kind of cigarette perfume pearl automatic splinter screening device for screening | |
| CN107976447A (en) | A kind of accessory detection method and system based on machine vision | |
| CN102059221A (en) | Color material separation device and method | |
| CN110068518A (en) | Machine-made Sand quality detection apparatus and its detection method | |
| KR20210018672A (en) | Apparatus and method for providing predictive value for measurement of particulate matter concentration using a camera | |
| CN113552028B (en) | Mixture visual analysis device, and method and system for detecting granularity composition of mixture | |
| CN110614232B (en) | Agaricus bisporus grading system | |
| CN111202035B (en) | Automatic pest collecting device and method for agriculture and forestry pest prediction | |
| CN111389745A (en) | Intelligent sorting method based on machine vision | |
| CN209006184U (en) | A kind of food processing screen selecting and separating mechanism | |
| CN111804604B (en) | High-precision material color sorting device | |
| CN109389075B (en) | Intelligent smoke machine lens fuzzy self-checking method | |
| WO2020252879A1 (en) | Mobile phone screen defect detection system based on ultrasonic spray | |
| CN208592107U (en) | Building refuse brick concrete aggregate sorting unit | |
| CN108203849B (en) | It is a kind of for natural feather it is convenient for production to natural feather carry out rough segmentation sorting unit | |
| CN109529463A (en) | Dust gauze self-cleaning system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |