CN206139527U - Panoramic vision potato is selected separately and defect detecting device - Google Patents
Panoramic vision potato is selected separately and defect detecting device Download PDFInfo
- Publication number
- CN206139527U CN206139527U CN201621055789.1U CN201621055789U CN206139527U CN 206139527 U CN206139527 U CN 206139527U CN 201621055789 U CN201621055789 U CN 201621055789U CN 206139527 U CN206139527 U CN 206139527U
- Authority
- CN
- China
- Prior art keywords
- rhizoma solani
- solani tuber
- tuber osi
- module
- camera bellows
- 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.)
- Expired - Fee Related
Links
Abstract
The utility model discloses a panoramic vision potato is selected separately and defect detecting device, including conveyor, detect camera bellows, sorting mechanism, infrared sensor module, image acquisition mechanism, built -inly have convolutional neural network and SVMs SVM's image processing analysis module, a built -in timing module who has SVMs SVM's data fusion module and be used for coordinating each part action. The utility model discloses a panoramic vision potato is selected separately and defect detecting device need not the potato and overturns the motion can accomplish the omnidirectional and detect in the testing process, has avoided the unneccessary damage of potato on the one hand, and on the other hand has avoided the developments instability in detecting that shoots, improves image definition, has promoted the rate of accuracy that detects. The utility model discloses can extensively be used for the real -time on -line measuring of potato agricultural product external sort, it is significant to the development that promotes china's potato industry.
Description
Technical field
This utility model is related to the apparatus and method of agricultural product appearance quality detection, concretely relates to a kind of Rhizoma Solani tuber osi
Sorting and defect detecting device and detection method.
Background technology
Shape and surface defect are the key characters of Rhizoma Solani tuber osi exterior quality, by quantitatively being surveyed to these characteristic indexs
Amount, can complete comprehensive detection and the classification of the indexs such as Rhizoma Solani tuber osi External Defect, shape.
China is Rhizoma Solani tuber osi manufacturing country maximum in the world, and the Potato Quality detection overwhelming majority is remained in manually
Sense organ is identified the judgement stage.This manual detection, evaluation Potato Quality method efficiency it is low, objectivity, accuracy compared with
Difference, it is difficult to meet the requirement of high standard classification, be unfavorable for realizing scale, automatization's Quality Detection operation.
Carry out detecting using machine vision and can exclude the interference of artificial subjective factor, can be to realize scale, automatically
Change Quality Detection operation and reliable basis are provided.
The grading plant of the Rhizoma Solani tuber osi used in major part Potato ring rot bacteria enterprise typically all enters simply by weight at present
Row classification, obtains weight information using balance or pressure transducer, then by entering according to lever principle or control circuit
Row classification.But these devices can only be according to weight grading, for defective Rhizoma Solani tuber osi potato wedges, it is impossible to choose automatically.It is such
Equipment needs the extra manpower that increases first to choose substandard products, then according still further to weight grading, so during actual operation
Rhizoma Solani tuber osi classification cost will be increased, increase manpower and materials, so as to improve production cost, classification process cannot really leave people
The participation of work, it is impossible to realize that scale, automatization's Quality Detection operation provide reliable basis.
Although being increasingly becoming focus to the Rhizoma Solani tuber osi stage division and equipment research based on computer vision now, typically
It is only limited to laboratory research or Rhizoma Solani tuber osi is taken pictures using single photographic head, real high volume applications is processed in actual production
Few in journey, although some hierarchical algorithmses have the high discrimination of comparison, but due to only with a photographic head, to Rhizoma Solani tuber osi
Defects detection is not comprehensive, the probability that there is missing inspection.
Can only be according to weight grading or the defect of single photographic head in order to solve existing Rhizoma Solani tuber osi classifying equipoment, it is impossible to very
The problems such as meeting well the requirement of real-time detection, it is proposed that a kind of panoramic vision Rhizoma Solani tuber osi sorting and defect detecting device and its side
Method.
Find there are some Patents documents to report by the domestic Searches of Patent Literature, mainly have following some：
1st, publication No. discloses a kind of fruit and vegerable sorting rejecting mechanism for the patent of 202539096 U of CN, is especially suitable for
In the sorting rejecting mechanism of large-scale fruit and vegerable, the soil block being mixed among fruit and vegerable, stone and glass etc. can be rejected, also can will be immature
Fruit rejected.The patent is by the way of head-on impact fruit and vegerable, and the fruit and vegerable after sorting directly are dropped in material bin,
Easily fruit and vegerable are caused damage.
2nd, notification number is 104056790 A of CN, and the practicality of entitled " a kind of Rhizoma Solani tuber osi intelligent separation method and device " is newly
Type patent, solve existing Rhizoma Solani tuber osi classifying equipoment can only according to weight grading, although and some equipment can be according to external appearance characteristic
Classification, but hierarchical algorithmses are more complicated, it is impossible to the problems such as meeting the requirement of real-time detection well.
3rd, notification number be 204746897 U of CN, a kind of entitled " Rhizoma Solani tuber osi grading control based on machine vision technique
Device " utility model patent, it is possible to achieve impurity, the quick detection sorting of different quality Rhizoma Solani tuber osis, is picked using air ejector
The removal of impurity, controls Rhizoma Solani tuber osi and the collision angle that is oriented between driving lever to reduce impact force, reduces the mechanical damage of Rhizoma Solani tuber osi；Root
Rhizoma Solani tuber osi is rejected using one or more guiding mechanisms according to the detection transverse diameter of Rhizoma Solani tuber osi, realize dividing for Rhizoma Solani tuber osi to be fractionated
Choosing.
4th, notification number be 203732461 A of CN, a kind of entitled " horizontal feed for Potato Quality image acquisition
The utility model patent of at the uniform velocity turning device ", designs a kind of horizontal feed for Potato Quality image acquisition and at the uniform velocity
Turning device, it is possible to achieve in Rhizoma Solani tuber osi external sort Non-Destructive Testing, it is at the uniform velocity steady in horizontal feed to overturn, and horse can be ensured
The centralized positioning of bell potato detection process, realizes the dynamic acquisition of Rhizoma Solani tuber osi external sort image.
Although above-mentioned patent proposes the method for sorting of Rhizoma Solani tuber osi and Rhizoma Solani tuber osi classifying equipoment, although some equipment can be according to
External appearance characteristic is classified, but due to only with a photographic head, needing to overturn Rhizoma Solani tuber osi, it is not comprehensive to its defects detection, exist
The probability of missing inspection, and the means for being analyzed process to the photo that photographic head shoots are more simple and crude, it is impossible to accurately, rapidly and comprehensively
Ground analysis of the image, analysis result are not fully up to expectations.In addition, being likely to cause Rhizoma Solani tuber osi to occur to damage during upset Rhizoma Solani tuber osi.
Utility model content
The purpose of this utility model is to provide a kind of panoramic vision Rhizoma Solani tuber osi sorting and defect detecting device, can be automatic
Conveying Rhizoma Solani tuber osi, need not be shot comprehensively and be detected to Rhizoma Solani tuber osi by upset Rhizoma Solani tuber osi, and detection is more efficiently and accurately.
For achieving the above object, panoramic vision Rhizoma Solani tuber osi sorting of the present utility model and defect detecting device include conveying dress
Put, detect camera bellows, sorting mechanism, infrared sensor module, image acquisition mechanism, be built-in with convolutional neural networks and supporting vector
The image processing and analyzing module of machine SVM, the data fusion module for being built-in with support vector machines and for coordinating each component actuation
Tfi module；
Conveyer device includes frame, and conveying roller is interval with frame, and each conveying roller is located in same level, phase
At a distance of 1-2.5 centimetre between adjacent conveying roller；With conveying direction as front, the frame at conveying roller foremost connects forward
It is connected to blanking plate；Frame at the conveying roller of rearmost end is connected with feeding device backward, the downward-sloping setting of feeding device, on
Material device adopts belt conveyor or chain conveyor；The frame of the conveying roller left and right sides is provided with for stopping Ma Ling
The baffle conveying group that potato is fallen in left-right direction；The left part of each conveying roller is equipped with for being connected with actuating unit
Travelling gear；
Frame in the middle part of conveyer device has connected up detection camera bellows, detects the front side wall bottom and rear wall bottom of camera bellows
Correspondence is offered for by the opening of Rhizoma Solani tuber osi；Detection camera bellows in be provided with described image collecting mechanism, upper illuminator and under
Illuminator；The lower lighting device is provided with two；
Two neighboring conveying roller immediately below the medium position of detection camera bellows fore-and-aft direction adopts transparent roller mechanism；Thoroughly
Bright roller mechanism includes hollow setting and the clear glass roller bearing of open at both ends, left squeegee, right squeegee, left support dress
Put, right support device and support link；Left and right support meanss include roller support and are connected to roller bearing by rolling bearing
Grafting cylinder on frame；The left part of the grafting cylinder of left support device is provided with the travelling gear for being connected with actuating unit；
Left squeegee described in the left end grafting of clear glass roller bearing, right squeegee described in the right-hand member grafting of clear glass roller bearing, left,
Right squeegee with the clear glass roller bearing interference fit；The right-hand member of right squeegee is plugged on the right support device
In grafting cylinder and with the grafting cylinder interference fit, the left end of left squeegee is plugged in the grafting cylinder of the left support device simultaneously
With the grafting cylinder interference fit；The hollow setting of right squeegee, the right-hand member of the support link and a shooting power set transmission
Connection, images the right part that power set are connected to the frame, and support link is to the left through the grafting of the right support device
Cylinder and right squeegee and its left end are located in the clear glass roller bearing；
Gap between described two transparent roller mechanisms forms infrared sensing passage, and the infrared sensor module includes
Infrared transmitter and infrared remote receiver, infrared transmitter and infrared remote receiver are respectively positioned at the left and the right side of infrared sensing passage
Side, and infrared transmitter and infrared remote receiver are just to the infrared sensing passage；
Image acquisition mechanism include 1 for gather Rhizoma Solani tuber osi global image global image acquisition module and 6 be used for
Topography's acquisition module of collection Rhizoma Solani tuber osi topography；Global image acquisition module includes being arranged on rear side in detection camera bellows
Global photographic head at the top of wall；
6 topography's acquisition modules are respectively 1 and are located at the rear Local map in detection camera bellows in the middle part of rear wall
As acquisition module, 1 are located at detection camera bellows positioned at the left topography acquisition module detected in camera bellows in the middle part of left side wall, 1
Right topography acquisition module, 1 front topography in detection camera bellows in the middle part of front side wall in the middle part of interior right side wall
Acquisition module and 2 lower section topography acquisition modules, in the clear glass roller bearing of the transparent roller mechanism described in each respectively
The lower section topography acquisition module being provided with described in 1 and the lower lighting device described in 1, lower section topography acquisition module and
Lower lighting device is both connected to the left part of the support link；
Front, rear, left and right topography acquisition module structure are identical, include past for driving photographic head to make
The cam movement mechanism of linear motion and the local cameras being connected in cam movement mechanism；Local map below each
As acquisition module includes a local cameras；
The frame side in detection camera bellows exit is provided with the sorting for Rhizoma Solani tuber osi is pushed away conveyer device in left-right direction
Mechanism, the baffle conveying group corresponding to sorting mechanism are provided with for by the breach of Rhizoma Solani tuber osi；The sorting mechanism is push-down
Sorting mechanism or jet-propelled sorting mechanism；Conveyer device part at sorting mechanism forms region to be separated；
Installing rack is connected with frame in front of the detection camera bellows, installing rack is provided with described image Treatment Analysis mould
Block, data fusion module and the tfi module for coordinating each component actuation；Tfi module connects the actuating unit, photographic head
The driving means of motion, infrared sensor module, sorting mechanism and image processing and analyzing module；
The local cameras and global photographic head are all connected with described image Treatment Analysis module.
The left and right sides of blanking plate have connected up discharge flapper.So that Rhizoma Solani tuber osi will not be from when by blanking plate
Fall down the left and right sides.
The push-down sorting mechanism includes the push rod for sorting power set and being connected with sorting power set, push rod
It is provided with for promoting the plate of Rhizoma Solani tuber osi.
The jet-propelled sorting mechanism includes air jet pipe, and air jet pipe one end connection high-pressure air source, the other end are connected with valve,
Valve be located at the frame side in detection camera bellows exit and valve opening towards frame opposite side.
This utility model has the following advantages：
This utility model is not stirring horse with reference to national export standard, the shape, weight and external appearance characteristic according to Rhizoma Solani tuber osi
In the case of bell potato, up, down, left, right, before and after panoramic vision detection is carried out to Rhizoma Solani tuber osi, so as to complete the real-time inspection of Rhizoma Solani tuber osi
Survey and classification.
Panoramic vision Rhizoma Solani tuber osi sorting of the present utility model and defect detecting device and its sorting detection method, without the need for Ma Ling
Potato completes omnibearing detection by flip-flop movement is carried out in detection process, on the one hand avoids the unnecessary damage of Rhizoma Solani tuber osi
Wound, on the other hand avoids the unstability that dynamic is taken pictures in detection, improves image clearly degree, improves the accurate of detection
Rate.This utility model can be widely used in the real-time online detection of Rhizoma Solani tuber osi agricultural product external sort, for promotion China Rhizoma Solani tuber osi
The development of industry has important practical significance and good application prospect.
Panoramic vision Rhizoma Solani tuber osi sorting of the present utility model and defect detecting device are rational in infrastructure, its point of the present utility model
Selected Inspection is surveyed method and step and arranges compact efficient, both combinations realize the automatic transportation of Rhizoma Solani tuber osi, take pictures, analyze detection, horse
Defective Rhizoma Solani tuber osi is sorted out automatically by bell potato after detection means of the present utility model, is the follow-up of Rhizoma Solani tuber osi
Offer support is sold in processing.
Transparent roller mechanism is adjacent to be provided with two, therefore the image for shooting can be completely covered the bottom characteristic of Rhizoma Solani tuber osi.
Description of the drawings
Fig. 1 is structural representation of the present utility model；
Fig. 2 is the flow chart of detection method of the present utility model；
Fig. 3 is the structural representation for detecting camera bellows；
Fig. 4 is the decomposition texture schematic diagram of transparent roller mechanism；
Fig. 5 is the structural representation of the built-in convolutional neural networks of image analysis processing module；
Fig. 6 is the data fusion flow chart of image analysis processing module and data fusion module.
Specific embodiment
This utility model with the conveying direction of Rhizoma Solani tuber osi as it is front to；In Fig. 1, direction shown in arrow is the conveying of Rhizoma Solani tuber osi
Direction.
As shown in Figures 1 to 6, this utility model provides a kind of panoramic vision Rhizoma Solani tuber osi and sorts and defect detecting device,
Including conveyer device, detection camera bellows, sorting mechanism, infrared sensor module, image acquisition mechanism, it is built-in with convolutional neural networks
Image processing and analyzing module 30 with support vector machines, it is built-in with the data fusion module 31 of support vector machines and is used for
Coordinate the tfi module 32 of each component actuation；
Conveyer device includes frame 1, and conveying roller 2 is interval with frame 1, and each conveying roller 2 is located at same level
On, at a distance of 1-2.5 centimetre between adjacent conveyor roller bearing 2, so that the Rhizoma Solani tuber osi of normal size will not be from adjacent conveying roller 2
Between slit source go down；With conveying direction as front, the frame 1 at conveying roller 2 foremost is connected with forward blanking plate
3；Frame 1 at the conveying roller 2 of rearmost end is connected with feeding device, the downward-sloping setting of feeding device, feeding device backward
Using belt conveyor or chain conveyor.During using belt conveyor, in Fig. 1, reference 35 show and is arranged at
Upper flitch on belt conveyor, during work, upper flitch catches Rhizoma Solani tuber osi, makes Rhizoma Solani tuber osi be transported to conveying roller 2 with belt
Place.During using chain conveyor, in Fig. 1, reference 35 show the elevating hopper being arranged on chain, elevating hopper during work
Rhizoma Solani tuber osi is caught, Rhizoma Solani tuber osi is transported at conveying roller 2.The left and right sides of feeding device is provided with for stopping Rhizoma Solani tuber osi edge
The feeding baffle plate 36 that left and right directions falls.
The frame 1 of 2 left and right sides of conveying roller is provided with for stopping baffle conveying that Rhizoma Solani tuber osi falls in left-right direction
Group 4；The left part of each conveying roller 2（Baffle conveying group 4 is stretched out to the left in the left part of conveying roller 2）Be equipped with for power
The travelling gear of mechanism driving connection；Actuating unit is common gear drive, is the ordinary skill in the art, and which is concrete
Structure is no longer described in detail, not shown.
Frame 1 in the middle part of conveyer device has connected up detection camera bellows 5, detects front side wall bottom and the rear wall of camera bellows 5
Bottom correspondence is offered for by the opening 6 of Rhizoma Solani tuber osi；Described image collecting mechanism, upper illumination dress are provided with detection camera bellows 5
Put 7 and lower lighting device 8；（Upper illuminator 7 adopts circular lamp, lower lighting device 8 to adopt LED）The lower lighting device 8
It is provided with two；
Two neighboring conveying roller 2 immediately below the medium position of detection 5 fore-and-aft direction of camera bellows adopts transparent roller mechanism；
Transparent roller mechanism include hollow setting and the clear glass roller bearing 9 of open at both ends, left squeegee 10, right squeegee 11,
Left support device, right support device and support link 15；Left and right support meanss include roller support 12 and pass through rolling bearing
13 are connected to the grafting cylinder 14 on roller support 12；The left part of the grafting cylinder 14 of left support device be provided with for actuating unit
The travelling gear being connected（Travelling gear is conventional structure, not shown）；Left rubber described in the left end grafting of clear glass roller bearing 9
Rubber-surfaced roll axle 10, right squeegee 11 described in the right-hand member grafting of clear glass roller bearing 9, left and right squeegee 10,11 with it is described
Bright 9 interference fit of glass roller bearing；The right-hand member of right squeegee 11 be plugged in the grafting cylinder 14 of the right support device and with this
14 interference fit of grafting cylinder, the left end of left squeegee 10 be plugged in the grafting cylinder 14 of the left support device and with the grafting
14 interference fit of cylinder；The 11 hollow setting of right squeegee, the right-hand member of the support link 15 and a shooting power set transmission connect
Connect, image the right part that power set are connected to the frame 1.Shooting power set are using cylinder, hydraulic cylinder, electric pushrod etc.
Various common form, are this area routine techniquess, not shown.During work, under the control of tfi module 32, power set are imaged
Drive the local cameras of lower section topography acquisition module to move to by support link 15 and be adapted to below Rhizoma Solani tuber osi what is taken pictures
Position.
Support link 15 is located at through the grafting cylinder 14 and right squeegee 11 and its left end of the right support device to the left
In the clear glass roller bearing 9；
Gap between described two transparent roller mechanisms forms infrared sensing passage 16, the infrared sensor module bag
Infrared transmitter 17 and infrared remote receiver 18 are included, infrared transmitter 17 and infrared remote receiver 18 are located at infrared sensing passage 16 respectively
Left and right, and infrared transmitter 17 and infrared remote receiver 18 are just to the infrared sensing passage 16；
Image acquisition mechanism include 1 for gather Rhizoma Solani tuber osi global image global image acquisition module and 6 be used for
Topography's acquisition module of collection Rhizoma Solani tuber osi topography；After global image acquisition module includes being arranged in detection camera bellows 5
The global photographic head 19 of top side wall；
6 topography's acquisition modules are respectively 1 and are located at the rear Local map in detection camera bellows 5 in the middle part of rear wall
As the left topography acquisition module being located in detection camera bellows 5 in the middle part of left side wall 23,1 of acquisition module 22,1 is located at detection
Right topography acquisition module in camera bellows 5 in the middle part of right side wall 24,1 is located at the front in detection camera bellows 5 in the middle part of front side wall
Topography's acquisition module 25 and 2 lower section topography acquisition modules 26, the transparent glass of the transparent roller mechanism described in each
The lower section topography acquisition module 26 being respectively equipped with glass roller bearing 9 described in 1 and the lower lighting device 8 described in 1, lower section office
Portion's image capture module 26 and lower lighting device 8 are both connected to the left part of the support link 15；
Front, rear, left and right topography acquisition module structure are identical, include past for driving photographic head to make
The cam movement mechanism 20 of linear motion and the local cameras 21 being connected in cam movement mechanism 20；Photographic head is transported
Motivation structure 20 includes guide rail and driving means, and photographic head is slidably connected on guide rail and is connected with driving means.Drive dress
Putting can be using various common linear drive apparatus such as cylinder, electric pushrod, micromachine and screw bodies.Cam movement
Mechanism 20 is this area routine techniquess, schemes not being shown in detail.Below each, topography's acquisition module 26 includes local cameras 21.
1 side of frame in 5 exit of detection camera bellows is provided with for Rhizoma Solani tuber osi to be pushed away conveyer device divide in left-right direction
Mechanism is selected, the baffle conveying group 4 corresponding to sorting mechanism is provided with for by the breach 27 of Rhizoma Solani tuber osi；The sorting mechanism is to push away
Rod-type sorting mechanism or jet-propelled sorting mechanism；Sorting mechanism shown in Fig. 1 is push-down sorting mechanism.When using jet-propelled
During sorting mechanism, jet-propelled sorting mechanism includes breather, breather one end connection air nozzle, other end connection high-pressure cylinder or
Person's air pump.Each part of push-down sorting mechanism or jet-propelled sorting mechanism is this area routine techniquess, and figure is not shown in detail which
Concrete structure.
Conveyer device part at sorting mechanism forms region to be separated.
Installing rack 29 is connected with frame 1 in front of the detection camera bellows 5, installing rack 29 is provided with described image and processes and divides
Analysis module 30, data fusion module 31 and the tfi module 32 for coordinating each component actuation（In Fig. 1 at not specifically illustrated image
Reason analysis module 30, data fusion module 31 and tfi module 32）；Tfi module 32 connects the actuating unit, photographic head fortune
The driving means of motivation structure 20, infrared sensor module, sorting mechanism and image processing and analyzing module 30；
The local cameras 21 and global photographic head 19 are all connected with described image Treatment Analysis module 30.
The left and right sides of blanking plate 3 have connected up discharge flapper 33.So that Rhizoma Solani tuber osi by blanking plate 3 when not
Can fall down from the left and right sides.
Sorting mechanism shown in Fig. 1 be push-down sorting mechanism, the push-down sorting mechanism include sort power set
（Sorting power set are using various common form such as cylinder, hydraulic cylinder, electric pushrods, not shown）And pass with sorting power set
The push rod 34 of dynamic connection, push rod 34 are provided with for promoting the plate 28 of Rhizoma Solani tuber osi.
The jet-propelled sorting mechanism includes air jet pipe, air jet pipe one end connection high-pressure air source（Such as air pump or compression sky
Gas tank）, the other end is connected with valve, and valve is located at 1 side of frame in 5 exit of detection camera bellows and valve opening is towards frame 1
Opposite side.Each part of jet-propelled sorting mechanism is routine techniquess, not shown.
The invention also discloses using the sorting of above-mentioned panoramic vision Rhizoma Solani tuber osi and the Rhizoma Solani tuber osi point of defect detecting device
Detection method is selected, is carried out according to the following steps successively：
Before starting to carry out sorting detection to Rhizoma Solani tuber osi, first using the size and shape rule of normal zero defect Rhizoma Solani tuber osi
Degree, and the size of defective Rhizoma Solani tuber osi, regular shape degree and surface defect kind of information, the support to data fusion module 31
Vector machine SVM carries out off-line training, builds the support vector machines grader of on-line checking；
Rhizoma Solani tuber osi region area under being classified using different size, different shape in off-line training sample data simultaneously
Eigenvalue corresponding to Area, girth Perimeter and ellipticity Ellipticity, the support to image analysis processing module
Vector machine SVM carries out off-line training, builds the support vector machines grader of on-line checking；During work, above-mentioned two
Individual support vector machines obtain increasing data, make method of the present utility model have the characteristic of study, with what is processed
The image of Rhizoma Solani tuber osi is more and more, and processing speed of the present utility model and process accuracy can get a promotion.
First step is artificial or Rhizoma Solani tuber osi is placed on feeding device using machinery, is then turned on actuating unit,
The upper flitch of feeding device（Or elevating hopper）Rhizoma Solani tuber osi is sent at conveying roller 2, actuating unit drives each conveying roller 2
Rotation, drives Rhizoma Solani tuber osi to travel forward；
Second step is to open infrared sensor module, blocks infrared transmitter when Rhizoma Solani tuber osi is by infrared sensing passage 16
17 infrared ray for being sent；After tfi module 32 detects the signal that the infrared ray that infrared sensor module sends is blocked,
Control actuating unit stops（Now Rhizoma Solani tuber osi is located between two clear glass roller bearings 9）, and control global photographic head 19 and carry out
Take pictures；Global photographic head 19 sends image to image processing and analyzing module 30, image procossing point after taking pictures to Rhizoma Solani tuber osi
Analysis module 30 calculates position of the Rhizoma Solani tuber osi in detection camera bellows 5 and believes the positional information of Rhizoma Solani tuber osi, shape information and size
Breath sends tfi module 32 to；The photographic head of the control of tfi module 32 front, rear, left and right topography acquisition module
The shooting power set of motion 20 and lower section topography acquisition module, make each local cameras 21 to being close to Rhizoma Solani tuber osi
Direction move to suitable camera site, each local cameras 21（Image including two in clear glass roller bearing 9
Head）The image of shooting is sent to image processing and analyzing module 30 respectively after taking pictures from different azimuth to Rhizoma Solani tuber osi；This step
In rapid, the collection image of each local cameras 21 is original triple channel RGB image, and the pixel of image is 256*256.
Third step is that 30 pairs of images for receiving of image processing and analyzing module are processed, and the surface for obtaining Rhizoma Solani tuber osi lacks
Sunken species；The Rhizoma Solani tuber osi surface that image processing and analyzing module 30 is obtained for the graphical analyses gathered by topography's acquisition module
Defect kind information, and the graphical analyses gathered by global image acquisition module obtain Rhizoma Solani tuber osi position, shapes and sizes
Information is sent to data fusion module 31；
Four steps is the support vector machines grader built using data fusion module 31, to the Ma Ling for receiving
Potato surface defect kind of information, Rhizoma Solani tuber osi position, shapes and sizes information carry out data fusion, whether judge Rhizoma Solani tuber osi to be detected
It is qualified, and will determine that result is sent to tfi module 32；
5th step is that the control actuating unit of tfi module 32 starts, and Rhizoma Solani tuber osi pulls away from detecting camera bellows 5 and arrival is treated
After separated region, the control sorting mechanism of tfi module 32 starts, by underproof Rhizoma Solani tuber osi by baffle conveying for passing through
Conveyer device is pushed away at the breach 27 of Rhizoma Solani tuber osi, and qualified Rhizoma Solani tuber osi is sent after blanking plate 3 being delivered to by conveyer device, completes Ma Ling
The sorting work of potato.
In the second step, image analysis processing module obtains Ma Ling according to the graphical analyses that global photographic head 19 is gathered
The processing procedure of the shapes and sizes information of potato is：
Carry out binaryzation first to image, and be filtered, shape operation, obtain binary image, and utilize
Roberts edge detection operators carry out rim detection, and Rhizoma Solani tuber osi region area Area, girth are tried to achieve on binary image
Perimeter and ellipticity Ellipticity；Further, it is using support vector machines, according to off-line training sample data, real
When according to Rhizoma Solani tuber osi region area Area, the girth Perimeter and ellipticity Ellipticity of current detection judging Ma Ling
The size of potato, regular shape degree；
(1) currently pending image and background image are subtracted each other so as to obtain the foreground pixel portion of Rhizoma Solani tuber osi to be checked
Point；Picture captured by global photographic head 19 when background image is no Rhizoma Solani tuber osi；
The Rhizoma Solani tuber osi that accurately can be detected by infrared sensor module on conveyer device conveys situation, thus can be image
Treatment Analysis module 30 provides accurate reference signal input.By two hardwood image subtractions, the collection of pixels for differing is obtained.
Gray processing is carried out to the foreground pixel part of Rhizoma Solani tuber osi to be checked, foreground part is obtained；
(2) extract edge feature；This operation is the edge feature that the foreground part by having obtained obtains Rhizoma Solani tuber osi；Tool
Body is foreground part to be calculated using Roberts edge detection operators, obtains deputy delegate's Rhizoma Solani tuber osi principal outline information
Black and white binary image；
(3) global characteristics value is extracted；On the basis of black and white binary image, Rhizoma Solani tuber osi region area to be detected is calculated
Area, girth Perimeter and ellipticity Ellipticity；
(4) outward appearance and size classes；Using the support vector machines of image analysis processing module, according to the horse for calculating
Bell potato region area Area, girth Perimeter and ellipticity Ellipticity calculate the shapes and sizes letter of Rhizoma Solani tuber osi
Breath.
In the third step, image analysis processing module obtains Ma Ling according to the graphical analyses that local cameras 21 are gathered
The processing procedure of the defect kind information of potato is：
（1）The original triple channel RGB images of 256*256 that local cameras 21 are gathered are scaled 224*224 triple channel RGB
Image,
Again the image after scaling is recognized by convolutional neural networks CNN, convolutional neural networks CNN includes 8 layers,
First 5 layers is convolutional layer, and the 6th ~ 8 layer is full articulamentum.Export 10 dimensional vectors and represent that the image belongs to 10 class Rhizoma Solani tuber osi surface defects
Probability density distribution.Its convolutional neural networks structure C NN is as shown in figure 5, the flow chart of data processing of network is as follows：
（2）The input layer of convolutional neural networks is the image after whole scaling, as shown in figure 5, image is launched by row, shape
Into 50176 nodes；Wherein the node of ground floor does not have forward any tie line.
（3）Convolution is carried out to the image after expansion, three feature extraction figures is produced, then to per group in feature extraction figure
Four pixels carry out suing for peace again, weighted value, biasing are put, and obtain three Feature Mapping figures by Sigmoid functions；
（4）Three Feature Mapping figures to producing carry out convolution again, and three Further Feature Extractions are produced after convolution
Then per group in Further Feature Extraction figure of four pixels are carried out suing for peace, weighted value, biasing are put, by Sigmoid letters by figure again
Number obtains three quadratic character mapping graphs.
（5）Three quadratic character mapping graphs are rasterized, and connects into a vector and be input to traditional volume
Product neutral net, obtains the defect kind information of Rhizoma Solani tuber osi.
Classification is completed by convolutional neural networks in the Rhizoma Solani tuber osi defects detection of topography, the network is inherently one
The mapping for being input to output is planted, it can learn the mapping relations between substantial amounts of input and output, without any input
Accurate mathematic(al) representation and output between, as long as being trained to convolutional network with known pattern, network just has defeated
Enter mapping ability of the output between.Convolutional network perform be have tutor to train, so its sample set be by shape such as：（Ma Ling
Potato local surfaces two-value input picture vector, Rhizoma Solani tuber osi surface defect type output vector）Vector to constitute.It is all these
Vector is right, should all derive from the actual " RUN " result of the system that network will be simulated, and they are adopted from actual motion system
What collection came.Before training is started, all of power is all initialized with some different little randoms number.
In image processing and analyzing module 30, the off-line training Sample Storehouse of its support vector machines and convolutional neural networks
The off-line training Sample Storehouse of CNN can increase sample size.In addition, the size of Rhizoma Solani tuber osi, regular shape degree and surface defect kind
Class can be further segmented with the increase of sample size.
Claims (4)
1. panoramic vision Rhizoma Solani tuber osi sorts and defect detecting device, it is characterised in that：Including conveyer device, detection camera bellows, sorting
Mechanism, infrared sensor module, image acquisition mechanism, the image procossing for being built-in with convolutional neural networks and support vector machines
Analysis module, the data fusion module for being built-in with support vector machines and the tfi module for coordinating each component actuation；
Conveyer device includes frame, and conveying roller is interval with frame, and each conveying roller is located in same level, adjacent defeated
Send between roller bearing at a distance of 1-2.5 centimetre；With conveying direction as front, the frame at conveying roller foremost is connected with forward
Blanking plate；Frame at the conveying roller of rearmost end is connected with feeding device, the downward-sloping setting of feeding device, feeding dress backward
Put using belt conveyor or chain conveyor；
The frame of the conveying roller left and right sides is provided with for stopping baffle conveying group that Rhizoma Solani tuber osi falls in left-right direction；It is each defeated
The left part of roller bearing is sent to be equipped with the travelling gear for being connected with actuating unit；
Frame in the middle part of conveyer device has connected up detection camera bellows, detects that the front side wall bottom of camera bellows is corresponding with rear wall bottom
Offer for by the opening of Rhizoma Solani tuber osi；Described image collecting mechanism, upper illuminator and lower illumination are provided with detection camera bellows
Device；The lower lighting device is provided with two；
Two neighboring conveying roller immediately below the medium position of detection camera bellows fore-and-aft direction adopts transparent roller mechanism；Transparent rolling
Axis mechanism include hollow setting and the clear glass roller bearing of open at both ends, left squeegee, right squeegee, left support device,
Right support device and support link；Left and right support meanss include roller support and are connected to roller support by rolling bearing
On grafting cylinder；The left part of the grafting cylinder of left support device is provided with the travelling gear for being connected with actuating unit；Thoroughly
Left squeegee described in the left end grafting of bright glass roller bearing, right squeegee described in the right-hand member grafting of clear glass roller bearing are left and right
Squeegee with the clear glass roller bearing interference fit；The right-hand member of right squeegee is plugged on inserting for the right support device
Connect in cylinder and with the grafting cylinder interference fit, the left end of left squeegee be plugged in the grafting cylinder of the left support device and with
The grafting cylinder interference fit；The hollow setting of right squeegee, the right-hand member of the support link and a shooting power set transmission connect
Connect, image the right part that power set are connected to the frame, support link is to the left through the grafting cylinder of the right support device
With right squeegee and its left end be located at the clear glass roller bearing in；
Gap between described two transparent roller mechanisms forms infrared sensing passage, and the infrared sensor module includes infrared
Emitter and infrared remote receiver, infrared transmitter and infrared remote receiver are located at the left and right of infrared sensing passage respectively, and
Infrared transmitter and infrared remote receiver are just to the infrared sensing passage；
Image acquisition mechanism include 1 for gather Rhizoma Solani tuber osi global image global image acquisition module and 6 be used for gather
Topography's acquisition module of Rhizoma Solani tuber osi topography；Global image acquisition module includes being arranged on rear wall top in detection camera bellows
The global photographic head in portion；
6 topography's acquisition modules are respectively 1 rear topography in detection camera bellows in the middle part of rear wall and adopt
Collection module, 1 be located at the left topography acquisition module in detection camera bellows in the middle part of left side wall, 1 be located at it is right in detection camera bellows
Right topography acquisition module, 1 front topography collection being located in detection camera bellows in the middle part of front side wall in the middle part of the wall of side
Module and 2 lower section topography acquisition modules, are respectively equipped with 1 in the clear glass roller bearing of the transparent roller mechanism described in each
Individual described lower section topography acquisition module and the lower lighting device described in 1, lower section topography acquisition module and lower photograph
Bright device is both connected to the left part of the support link；
Front, rear, left and right topography acquisition module structure are identical, include reciprocal straight for driving photographic head to make
The cam movement mechanism of line motion and the local cameras being connected in cam movement mechanism；Below each, topography adopts
Collection module includes a local cameras；
The frame side in detection camera bellows exit is provided with the sorting mechanism for Rhizoma Solani tuber osi is pushed away conveyer device in left-right direction,
Baffle conveying group corresponding to sorting mechanism is provided with for by the breach of Rhizoma Solani tuber osi；The sorting mechanism is push-down separator
Structure or jet-propelled sorting mechanism；Conveyer device part at sorting mechanism forms region to be separated；
Installing rack is connected with frame in front of the detection camera bellows, installing rack is provided with described image Treatment Analysis module, number
Tfi module according to Fusion Module and for coordinating each component actuation；Tfi module connects the actuating unit, cam movement
The driving means of mechanism, infrared sensor module, sorting mechanism and image processing and analyzing module；
The local cameras and global photographic head are all connected with described image Treatment Analysis module.
2. panoramic vision Rhizoma Solani tuber osi according to claim 1 sorts and defect detecting device, it is characterised in that：Blanking plate
Left and right sides have connected up discharge flapper, so that Rhizoma Solani tuber osi will not be fallen down from the left and right sides when by blanking plate.
3. panoramic vision Rhizoma Solani tuber osi according to claim 1 and 2 sorts and defect detecting device, it is characterised in that：It is described
Push-down sorting mechanism includes the push rod for sorting power set and being connected with sorting power set, and push rod is provided with for pushing away
The plate of dynamic Rhizoma Solani tuber osi.
4. panoramic vision Rhizoma Solani tuber osi according to claim 1 and 2 sorts and defect detecting device, it is characterised in that：It is described
Jet-propelled sorting mechanism includes air jet pipe, and air jet pipe one end connection high-pressure air source, the other end are connected with valve, and valve is located at detection
The opposite side of the frame side in camera bellows exit and valve opening towards frame.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201621055789.1U CN206139527U (en) | 2016-09-14 | 2016-09-14 | Panoramic vision potato is selected separately and defect detecting device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201621055789.1U CN206139527U (en) | 2016-09-14 | 2016-09-14 | Panoramic vision potato is selected separately and defect detecting device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN206139527U true CN206139527U (en) | 2017-05-03 |
Family
ID=58618518
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201621055789.1U Expired - Fee Related CN206139527U (en) | 2016-09-14 | 2016-09-14 | Panoramic vision potato is selected separately and defect detecting device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN206139527U (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106238342A (en) * | 2016-09-14 | 2016-12-21 | 郑州轻工业学院 | The sorting of panoramic vision Rhizoma Solani tuber osi and defect detecting device and sorting detection method thereof |
| CN107280697A (en) * | 2017-05-15 | 2017-10-24 | 北京市计算中心 | Lung neoplasm grading determination method and system based on deep learning and data fusion |
| CN107321648A (en) * | 2017-08-31 | 2017-11-07 | 东北农业大学 | Potato multi-level sorting machine based on machine vision technique |
| CN107860777A (en) * | 2017-12-20 | 2018-03-30 | 桂林电子科技大学 | A kind of electrolytic capacitor open defect detection means and detection method |
| CN107985668A (en) * | 2017-11-30 | 2018-05-04 | 韩秋霞 | A kind of needle tubing automatic finisher |
| CN108940805A (en) * | 2018-08-08 | 2018-12-07 | 黑龙江八农垦大学 | A kind of potato full automatic grading cleaning and sorting system based on light spectrum image-forming |
| CN109092699A (en) * | 2018-07-25 | 2018-12-28 | 浙江大学 | A kind of detection of garlic and prepare mashed garlic device and method |
| CN112517420A (en) * | 2020-11-17 | 2021-03-19 | 苏州迈之升电子科技有限公司 | Sorting method and system for application grating |
| CN112970032A (en) * | 2018-11-07 | 2021-06-15 | 格立莫农业机械制造有限两合公司 | Method for regulating the operation of a machine for harvesting root crops |
| CN115007489A (en) * | 2022-06-09 | 2022-09-06 | 蒲丰(海宁)智能装备有限公司 | Potato grading and sorting device based on artificial intelligence technology |
| CN115318659A (en) * | 2022-10-13 | 2022-11-11 | 江苏蜜心枣业有限公司 | Online visual inspection grading system for red date appearance |
-
2016
- 2016-09-14 CN CN201621055789.1U patent/CN206139527U/en not_active Expired - Fee Related
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106238342B (en) * | 2016-09-14 | 2018-05-15 | 郑州轻工业学院 | Panoramic vision potato sorts and defect detecting device and its sorting detection method |
| CN106238342A (en) * | 2016-09-14 | 2016-12-21 | 郑州轻工业学院 | The sorting of panoramic vision Rhizoma Solani tuber osi and defect detecting device and sorting detection method thereof |
| CN107280697A (en) * | 2017-05-15 | 2017-10-24 | 北京市计算中心 | Lung neoplasm grading determination method and system based on deep learning and data fusion |
| CN107321648A (en) * | 2017-08-31 | 2017-11-07 | 东北农业大学 | Potato multi-level sorting machine based on machine vision technique |
| CN107985668A (en) * | 2017-11-30 | 2018-05-04 | 韩秋霞 | A kind of needle tubing automatic finisher |
| CN107860777A (en) * | 2017-12-20 | 2018-03-30 | 桂林电子科技大学 | A kind of electrolytic capacitor open defect detection means and detection method |
| CN109092699B (en) * | 2018-07-25 | 2020-05-12 | 浙江大学 | Device and method for detecting garlic and preparing mashed garlic |
| CN109092699A (en) * | 2018-07-25 | 2018-12-28 | 浙江大学 | A kind of detection of garlic and prepare mashed garlic device and method |
| CN108940805A (en) * | 2018-08-08 | 2018-12-07 | 黑龙江八农垦大学 | A kind of potato full automatic grading cleaning and sorting system based on light spectrum image-forming |
| CN112970032A (en) * | 2018-11-07 | 2021-06-15 | 格立莫农业机械制造有限两合公司 | Method for regulating the operation of a machine for harvesting root crops |
| CN112517420A (en) * | 2020-11-17 | 2021-03-19 | 苏州迈之升电子科技有限公司 | Sorting method and system for application grating |
| CN115007489A (en) * | 2022-06-09 | 2022-09-06 | 蒲丰(海宁)智能装备有限公司 | Potato grading and sorting device based on artificial intelligence technology |
| CN115318659A (en) * | 2022-10-13 | 2022-11-11 | 江苏蜜心枣业有限公司 | Online visual inspection grading system for red date appearance |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106238342B (en) | Panoramic vision potato sorts and defect detecting device and its sorting detection method | |
| CN206139527U (en) | Panoramic vision potato is selected separately and defect detecting device | |
| CN1329132C (en) | On-line fruit quality detection and classification apparatus and method based on three camera chains | |
| CN108229665A (en) | A kind of the System of Sorting Components based on the convolutional neural networks by depth | |
| CN110648364A (en) | Multi-dimensional space solid waste visual detection positioning and identification method and system | |
| CN111862028B (en) | Wood defect detecting and sorting device and method based on depth camera and depth learning | |
| CN107999399A (en) | Building waste on-line sorting system and method based on the detection of dot matrix EO-1 hyperion | |
| CN106423913A (en) | Construction waste sorting method and system | |
| CN206139529U (en) | Transparent roller bearing mechanism | |
| CN112827846B (en) | Automatic garbage classification device and method | |
| CN112893159B (en) | Coal gangue sorting method based on image recognition | |
| CN106442553A (en) | Detection and recognition device and method for sprayed codes on cylindrical surfaces of copper rings | |
| CN113145492A (en) | Visual grading method and grading production line for pear appearance quality | |
| CN109675827A (en) | A kind of building waste identification sorting device, recognition methods and its grasping means | |
| CN202037127U (en) | Automatic egg quality detection and separation equipment | |
| CN110584164A (en) | Green plum sorting production line and sorting method | |
| CN110586502B (en) | Green plum sorting device and sorting method | |
| CN106622988A (en) | High-performance carrot computer vision track defective product removing and length and thickness grading device | |
| CN207126835U (en) | A kind of potato Fast nondestructive evaluation self-grading device | |
| CN113996545A (en) | Quick sorting production line for main roots of panax notoginseng based on computer vision | |
| CN113245222B (en) | Visual real-time detection and sorting system and sorting method for foreign matters in panax notoginseng | |
| CN114522900A (en) | Lotus seed core removing and defective product sorting device and sorting method | |
| CN112676195B (en) | Color sorting device and method for solid wood floor based on linear array CMOS camera | |
| CN112371559A (en) | Gangue identification method and gangue automatic separation system | |
| CN207929583U (en) | Building waste on-line sorting system based on the detection of dot matrix EO-1 hyperion |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170503 Termination date: 20180914 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |