CN110586502A - Green plum sorting device and method - Google Patents
Green plum sorting device and method Download PDFInfo
- Publication number
- CN110586502A CN110586502A CN201911020420.5A CN201911020420A CN110586502A CN 110586502 A CN110586502 A CN 110586502A CN 201911020420 A CN201911020420 A CN 201911020420A CN 110586502 A CN110586502 A CN 110586502A
- Authority
- CN
- China
- Prior art keywords
- steering engine
- partition plate
- sorting device
- green
- conveyor belt
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/16—Sorting according to weight
- B07C5/24—Sorting according to weight using moving weighing mechanisms, e.g. moving along a circular path
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
- B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/363—Sorting apparatus characterised by the means used for distribution by means of air
- B07C5/365—Sorting apparatus characterised by the means used for distribution by means of air using a single separation means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/38—Collecting or arranging articles in groups
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C2501/00—Sorting according to a characteristic or feature of the articles or material to be sorted
- B07C2501/009—Sorting of fruit
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/90—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in food processing or handling, e.g. food conservation
Abstract
The invention discloses a green plum sorting device and a green plum sorting method, which comprise a sorting module, wherein the sorting module comprises a first-stage sorting device, a second-stage sorting device, a camera and a conveyor belt, the camera is positioned above the first-stage sorting device, the first-stage sorting device and the second-stage sorting device are both positioned above the conveyor belt, and the first-stage sorting device is positioned in front of the second-stage sorting device; the first-stage sorting device comprises four steering engines and four partition plates, and the second-stage sorting device comprises four steering engines and four partition plates; five grading partition plates are respectively arranged above the tail ends of the conveyor belts, the planes above the tail ends of the conveyor belts are divided into four parts by the five grading partition plates to form four grading channels, and the tail end of each grading channel is provided with a rear fruit receiving basket. The green plums can be sorted based on dual standards of quality and weight, and a sorting basis is provided for further fine and further processing of the green plums.
Description
Technical Field
The invention belongs to the field of forest fruit sorting, and particularly relates to a green plum sorting device and a green plum sorting method.
Background
The green plums are used as Chinese characteristic fruits, are rich in resources and have high nutritional value. With the development of economy, the capacity demand of the green plums in the market of China is continuously increased, and the contradiction between the increase of the green plum demand and the laggard green plum industry capacity is increasingly deepened.
The traditional manual green plum sorting mode has the problems of high cost, low efficiency, large labor occupation and the like.
Adopt the green plum system of selecting separately based on machine vision, can utilize spectrum technology and image processing technique to select separately fast the green plum quality, this not only can overcome the low efficiency, low accuracy and the high cost problem of artifical detection green plum defect, has important meaning to the intellectuality of green plum enterprise and the sustainable development of green plum industry moreover.
Therefore, a green plum sorting device and a green plum sorting method based on machine vision are needed at present, and the spectrum technology and the image processing technology are combined to quickly sort the quality of green plums, so that the traditional manual green plum sorting mode is replaced.
Disclosure of Invention
The green plum sorting device and the green plum sorting method can sort green plums based on dual standards of quality and weight, provide a sorting basis for further deep processing of the green plums, and accordingly improve the economic value of the green plums, and are high in sorting efficiency, high in accuracy and low in labor cost.
In order to achieve the technical purpose, the technical scheme adopted by the invention is as follows:
a green plum sorting device comprises a sorting module, wherein the sorting module comprises a first-stage sorting device, a second-stage sorting device, a camera and a conveyor belt, the camera is positioned above the first-stage sorting device, the first-stage sorting device and the second-stage sorting device are both positioned above the conveyor belt, and the first-stage sorting device is positioned in front of the second-stage sorting device;
the first-stage sorting device comprises four steering engines which are respectively a first steering engine, a second steering engine, a third steering engine and a fourth steering engine, wherein the first steering engine is connected with a first partition plate, the second steering engine is connected with a second partition plate, the third steering engine is connected with a third partition plate, the fourth steering engine is connected with a fourth partition plate, the second steering engine and the third steering engine are positioned between the first steering engine and the fourth steering engine, the opening directions of the first partition plate and the fourth partition plate are opposite to the moving direction of the conveyor belt, the opening directions of the second partition plate and the third partition plate are the same as the moving direction of the conveyor belt, the first partition plate and the fourth partition plate are both connected with an air blowing device, a left partition plate and a right partition plate are respectively arranged above two sides of;
the second-stage sorting device comprises four steering engines which are respectively a fifth steering engine, a sixth steering engine, a seventh steering engine and an eighth steering engine, wherein the fifth steering engine is connected with a fifth partition plate, the sixth steering engine is connected with a sixth partition plate, the seventh steering engine is connected with a seventh partition plate, the eighth steering engine is connected with an eighth partition plate, the opening orientations of the fifth partition plate, the sixth partition plate, the seventh partition plate and the eighth partition plate are the same as the moving direction of the conveyor belt, five grading partition plates are respectively arranged above the tail end of the conveyor belt, planes above the tail end of the conveyor belt are evenly divided into four grades by the five grading partition plates to.
According to the technical scheme, a first steering engine, a second steering engine, a third steering engine and a fourth steering engine of the first-stage sorting device are connected to a first horizontal supporting plate, and a camera, the first horizontal supporting plate, a left partition plate and a right partition plate are supported above a conveyor belt through supports.
According to the technical scheme, a fifth steering engine, a sixth steering engine, a seventh steering engine and an eighth steering engine of the second-stage sorting device are connected to a second horizontal supporting plate, and the second horizontal supporting plate and the five grading partition plates are supported above the conveyor belt through supports.
As a further improved technical scheme of the invention, the first-stage sorting device further comprises a partition plate nine and a partition plate ten, the partition plate nine is positioned in front of the partition plate II, the partition plate ten is positioned in front of the partition plate III, and the partition plate nine and the partition plate ten are both supported above the conveyor belt through a support.
The technical scheme is further improved by the invention, the pneumatic control system further comprises a lower computer, the camera is electrically connected with the lower computer, the lower computer is electrically connected with a control valve, a first steering engine, a second steering engine, a third steering engine, a fourth steering engine, a fifth steering engine, a sixth steering engine, a seventh steering engine and an eighth steering engine in the two pneumatic devices respectively, and the lower computer is electrically connected with the upper computer.
The weighing and conveying device comprises a weighing and conveying belt, wherein the weighing and conveying belt is used for weighing each green plum and sending the quality information of the green plum to an upper computer, and the weighing and conveying belt is also used for conveying each weighed green plum to a conveying belt in a sorting module.
In order to achieve the technical purpose, the invention adopts another technical scheme as follows:
a green plum sorting method comprises a green plum defect detection method and an upper computer control method;
the green plum defect detection method comprises the following steps:
(1) dividing a three-channel color image acquired by a camera into R, G, B single-channel monochromatic images, converting the three monochromatic images into HSV color space, and extracting green plums from an original image after S-channel component extraction, Gaussian filtering, feature extraction and division on the converted image;
(2) extracting a defect image from a single-channel gray image of the green plums by a threshold segmentation method according to the gray value difference of the surface defect characteristics of the green plums;
(3) extracting six characteristic parameters of the defect image: r, G, B color component values, defect roundness, squareness, and closeness;
(4) establishing a Gaussian mixture model according to six characteristic parameters of the defect image sample;
(5) inputting six characteristic parameters in a defect image to be detected into a Gaussian mixture model for matching, and completing defect identification and classification;
the upper computer control method comprises the following steps:
(a) the upper computer receives the quality information of each green plum uploaded by the weighing conveyer belt;
(b) when the green plums enter the first-stage sorting device through the conveyor belt, the camera works and sends images to the lower computer, and the lower computer sequentially carries out defect identification and classification on the green plums according to a green plum defect detection method and positions the green plums in the images;
(c) the lower computer transmits the defect identification classification result and the positioning information to the upper computer;
(d) the upper computer marks the defect identification classification result and the positioning information as labels on each corresponding green plum with weight information;
(e) the upper computer transmits the defect identification and classification result, the positioning information and the weight information of each green plum to the lower computer, and the lower computer controls a first steering engine or a fourth steering engine according to the positioning information transferred by the upper computer and the movement speed of the conveyor belt, further controls the direction of the air blowing device, blows the defective green plum and blows the defective green plum into a left fruit receiving basket or a right fruit receiving basket on two sides of the conveyor belt;
(f) the lower computer controls a second steering engine and a third steering engine according to the weight information of the green plums transferred by the upper computer, and further controls the second partition plate and the third partition plate to respectively steer so as to adjust the conveying direction of the green plums without defects on the conveying belt, and the green plums are conveyed into the second-stage sorting device under the driving of the conveying belt;
(g) the lower computer controls two adjacent steering engines in the second-stage sorting device to work according to the weight information of the green plums placed by the upper computer, and then controls certain two of the five partition plates, the six partition plates, the seven partition plates and the eight partition plates to turn and ensures that the directions of the two partition plates are consistent with the directions of the second partition plate and the third partition plate, the green plums pass through the two partition plates and enter a certain grading channel under the conveying of the conveying belt, and finally fall into a rear fruit receiving basket corresponding to the tail end of the grading channel.
The invention has the beneficial effects that:
(1) the green plums are sorted from two standards of green plum quality and weight by using machine vision and machine learning, rather than one characteristic; the sorting efficiency is high, the accuracy is high, and the labor cost is low; the method provides a sorting basis for further fine and further processing the green plums, so that the economic value of the green plums is improved, and the method has important significance for the intellectualization of green plum enterprises and the sustainable development of the green plum industry.
(2) The first-stage sorting device is combined with the variable-angle air blowing device, so that the rotten green plums and the green plums with scars can be removed from a horizontal multi-angle mode.
(3) According to the method, the quality and weight information of each green plum is marked by machine vision and machine learning, so that the weight information of each green plum can be accurately determined after the green plums with defective characteristics are removed, and the green plums capable of being deeply processed are subjected to secondary sorting according to the weight information.
Drawings
Fig. 1 is a schematic structural diagram of a sorting module according to this embodiment.
Fig. 2 is a top view of the sorting module of the present embodiment.
Fig. 3 is a schematic structural diagram of the sorting module according to this embodiment in operation.
Fig. 4 is a top view of the sorting module of this embodiment in operation.
Fig. 5 is a schematic structural diagram of the weighing conveyer belt and the sorting module according to the embodiment.
Fig. 6 is a schematic structural diagram of the weighing conveyer belt of the embodiment.
Fig. 7 is a schematic structural diagram of a weighing module in the weighing conveyer belt of the embodiment.
FIG. 8 is a cross-sectional view of a weighing module in the weighing conveyer of this embodiment.
Detailed Description
The following further describes embodiments of the present invention with reference to fig. 1 to 8:
a green plum sorting device comprises a sorting module B, as shown in figure 1, the sorting module B comprises a first-stage sorting device 7, a second-stage sorting device 8, a camera 1 and a conveyor belt 4, the camera 1 is positioned above the first-stage sorting device 7, the first-stage sorting device 7 and the second-stage sorting device 8 are both positioned above the conveyor belt 4, and the first-stage sorting device 7 is positioned in front of the second-stage sorting device 8;
the first-stage sorting device 7 comprises four steering gears, as shown in fig. 2, a first steering gear 7-12, a second steering gear 7-8, a third steering gear 7-5 and a fourth steering gear 7-1 are respectively arranged, the first steering gear 7-12 is connected with a first partition plate 7-11, the second steering gear 7-8 is connected with a second partition plate 7-9, the third steering gear 7-5 is connected with a third partition plate 7-4, and the fourth steering gear 7-1 is connected with a fourth partition plate 7-2. The second steering engine 7-8 and the third steering engine 7-5 are located between the first steering engine 7-12 and the fourth steering engine 7-1, the opening directions of the first partition plate 7-11 and the fourth partition plate 7-2 are opposite to the moving direction of the conveyor belt 4, the opening directions of the second partition plate 7-9 and the third partition plate 7-4 are the same as the moving direction of the conveyor belt 4, the end parts of the first partition plate 7-11 and the fourth partition plate 7-2 are connected with air blowing devices (respectively comprising a first air blowing device 7-10 and a second air blowing device 7-3), a left partition plate 3 and a right partition plate 5 (shown in figure 1) are respectively arranged above two sides of the front end of the conveyor belt 4, a left fruit receiving basket 2 is arranged at the front end of the left partition plate 3, and a right fruit receiving basket 6 is arranged at the front.
The second-stage sorting device 8 comprises four steering engines, as shown in figure 2, namely a fifth steering engine 8-3, a sixth steering engine 8-5, a seventh steering engine 8-7 and an eighth steering engine 8-9, wherein the fifth steering engine 8-3 is connected with a fifth partition plate 8-2, the sixth steering engine 8-5 is connected with a sixth partition plate 8-4, the seventh steering engine 8-7 is connected with a seventh partition plate 8-6, the eighth steering engine 8-9 is connected with an eighth partition plate 8-8, the fifth partition plate 8-2, the sixth partition plate 8-4, the seventh partition plate 8-6 and the eighth partition plate 8-8 have openings facing the same direction as the moving direction of the conveyor belt 4, five grading partition plates 9 are respectively arranged above the tail end of the conveyor belt 4, the plane above the tail end of the conveyor belt 4 is divided into four parts by the five grading partition plates 9 to form four grading channels 10, and a rear fruit receiving basket 11 is arranged at the tail end of each grading channel 10.
As shown in fig. 2, the first steering engine 7-12, the second steering engine 7-8, the third steering engine 7-5 and the fourth steering engine 7-1 of the first-stage sorting device 7 are all connected to the first horizontal support plate 7-13, and the camera 1, the first horizontal support plate 7-13, the left partition plate 3 and the right partition plate 5 are all supported above the conveyor belt 4 through a support (not shown in the figure).
As shown in fig. 2, a fifth steering engine 8-3, a sixth steering engine 8-5, a seventh steering engine 8-7 and an eighth steering engine 8-9 of the second-stage sorting device 8 are all connected to a second horizontal support plate 8-1, and the second horizontal support plate 8-1 and five grading partition plates 9 are all supported above the conveyor belt 4 through a support (not shown in the figure).
As shown in FIG. 2, the first-stage sorting device 7 further comprises a partition nine 7-7 and a partition ten 7-6, the partition nine 7-7 is positioned in front of the partition two 7-9, the partition ten 7-6 is positioned in front of the partition three 7-4, and the partition nine 7-7 and the partition ten 7-6 are supported above the conveyor belt 4 through a support.
The camera 1 is electrically connected with the lower computer, the lower computer is electrically connected with control valves, a first steering engine 7-12, a second steering engine 7-8, a third steering engine 7-5, a fourth steering engine 7-1, a fifth steering engine 8-3, a sixth steering engine 8-5, a seventh steering engine 8-7 and an eighth steering engine 8-9 in two air blowing devices (a first air blowing device 7-10 and a second air blowing device 7-3 respectively), and the lower computer is electrically connected with the upper computer. And the lower computer controls the control valves in the two air blowing devices to open and close so as to control the two air blowing devices to work.
As shown in fig. 5, the present embodiment further includes a weighing conveyer a, the weighing conveyer a is used for weighing each green plum and sending the quality information of the green plum to an upper computer, and the weighing conveyer a is also used for sending each weighed green plum to the conveyer 4 in the sorting module B.
As shown in fig. 6, the weighing conveyer belt a of the present embodiment includes a conveyer belt device 12 and weighing modules, and a plurality of weighing modules are fixedly connected to the conveyer belt of the conveyer belt device 12. As shown in fig. 7 and 8, the weighing module includes an object stage 14, a movable block 18, a sleeve 13, a sleeve shaft 19, a spring 20 and a force sensor 16, the movable block 18 is connected to both sides of the object stage 14, the bottom of the movable block 18 is connected to the top of the sleeve shaft 19, the sleeve shaft 19 is sleeved on the inner side of the sleeve 13 and can slide up and down in the sleeve 13, the bottom of the sleeve 13 is connected to the force sensor 16, the spring 20 is located on the inner side of the sleeve 13, the top of the spring 20 is connected to the bottom of the sleeve shaft 19, and the bottom of the spring 20 is connected to the force sensor 16.
The two force sensors 16 of the weighing module of the present embodiment are fixedly connected to the conveyor belt of the conveyor belt arrangement 12. The weighing modules in this embodiment are arranged uniformly in the length direction of the conveyor belt 4. In this embodiment, the spherical pit 17 is disposed in the middle of the upper surface of the object stage 14, the spherical pit 17 is used for loading green plums, and each weighing module weighs one green plum at a time. The conveyor means 12 in this embodiment is provided with a guide plate 15 on one side. The conveyor belt device 12 of the weighing conveyor belt a of the present embodiment employs a conveyor belt structure commonly used in the art.
The green plums of this embodiment enter into weighing device, and weighing device can once only weigh the weight of 5 green plums simultaneously. During weighing, a plurality of green plums enter the weighing module from one side of the weighing device with the force sensor, the object stage 14 is a plane with a spherical pit 17 in the middle, and the green plums are located in the spherical pit 17 during weighing. Before weighing each time, the numerical values of the two force sensors 16 are cleared (the weights of the object stage 14, the movable block 18, the sleeve shaft 19 and the spring 20 are cleared), when the green plums fall into the spherical pit 17, the sleeve shaft 19 presses down the spring 20 under the action of gravity, the spring 20 presses the force sensors 16, when the spring 20 is stable, the feedback force of the force sensors 16 is large, and the sum of the readings of the force sensors 16 on two sides of one object stage 14 is the weight of the green plums. The force sensor 16 sends weight information to an upper computer, and the weighed green plums are transmitted along the conveyor belt 4 and finally enter the conveyor belt 4 of the green plum sorting device along the guide plate 15.
The weighed green plums fall to the green plum sorting device, and can be divided into four types of intact green plums, raindrops, ulcerations and scars according to the defect characteristics of the green plums, wherein the perfect green plums and the green plums with the raindrops are all regarded as deep-processed green plums (namely, the perfect green plums and the raindrops are regarded as non-defective green plums), and the ulcerations and scars are all regarded as defective green plums, so that the sorting of the green plums is divided into the sorting of the quality and the weight. Two-stage sorting is arranged on the sorting module B, the first-stage sorting device 7 is used for sorting the quality and is divided into three types of festers, scars and deep processing (including raindrops and perfect green plums), wherein the festers and the scars are regarded as defective green plums, and the perfect green plums and the green plums with the raindrops are regarded as deep processing green plums (namely, the perfect green plums are regarded as the non-defective green plums); the second-stage sorting device 8 is used for sorting the weight of the deep-processed green plums and is divided into four weight intervals. The camera 1 of the present embodiment is used for taking a picture of greengage. When the green plum sorting device works, green plums enter from a conveyor belt 4 on one side provided with a camera 1 according to a weighing sequence, the camera 1 shoots the green plums in real time and sends images to a lower computer, the lower computer detects the quality, air blowing devices arranged on a first partition plate 7-11 and a fourth partition plate 7-2 of a first-stage sorting device 7 respectively blow the detected green plums with festers and scars (generally called as defective green plums) to a left fruit receiving basket 2 and a right fruit receiving basket 6 on two sides of the conveyor belt 4 along a left partition plate 3 and a right partition plate 5 which mutually form an angle on the conveyor belt 4, meanwhile, the second partition 7-9 and the third partition 7-4 in the middle of the first-stage sorting device 7 are turned (as shown in fig. 3 and 4) to turn to one of the four mass sections corresponding to the second-stage sorting device 8, and the second-stage sorting device 8 turns to the two partitions nearest to the mass section. So that the green plums of the weight are fed into the classifying passage 10 between the corresponding classifying partitions 9 and fall into the rear fruit receiving basket 11 corresponding to the end of the classifying partition 9. In the embodiment, the weight of the green plums is divided into four ranges, the weights in the four different ranges correspond to different rear fruit receiving baskets 11, and the lower computer controls the corresponding steering engine to work through the weight information of the green plums, so that the green plums are conveyed into the rear fruit receiving baskets 11 in the corresponding weight intervals.
The embodiment also provides a green plum sorting method, which comprises a green plum defect detection method and an upper computer control method.
The green plum defect detection method comprises the following steps:
(1) the lower computer divides the three-channel color image acquired by the camera 1 into R, G, B single-channel monochromatic images, converts the three monochromatic images into HSV color space, and extracts green plums from the original image after S channel component extraction, Gaussian filtering, feature extraction and division on the converted image;
(2) extracting a defect image from a single-channel gray image of the green plums by a threshold segmentation method according to the gray value difference of the surface defect characteristics of the green plums;
(3) extracting six characteristic parameters of the defect image: r, G, B color component values, defect roundness, squareness, and closeness;
(4) establishing a Gaussian mixture model according to six characteristic parameters of the defect image sample;
(5) inputting six characteristic parameters in a defect image to be detected into a Gaussian mixture model for matching, and completing defect identification and classification;
the upper computer control method comprises the following steps:
(a) the upper computer receives the quality information of each green plum uploaded by the force sensor 16 on the weighing conveyer belt A, marks each green plum according to the weight information and stores the green plum in a storage space of the upper computer;
(b) when the green plums enter the first-stage sorting device 7 through the conveyor belt 4, the camera 1 works and sends images to the lower computer, and the lower computer sequentially carries out defect identification and classification on the green plums according to a green plum defect detection method and positions the positions of the green plums in the images (the positioning method is the prior art);
(c) the lower computer transmits the defect identification classification result (ulceration, scar and deep processing) and the positioning information to the upper computer;
(d) the upper computer marks the defect identification classification result (ulceration, scar and deep processing) and the positioning information as labels on each corresponding green plum with weight information, and each green plum at the moment has three types of information of weight, classification result and positioning;
(e) the upper computer transmits the defect identification classification result, the positioning information and the weight information of each green plum to the lower computer, the lower computer controls a first steering engine 7-12 or a fourth steering engine 7-1 according to the positioning information transferred by the upper computer and the movement speed of the conveyor belt 4, further controls the direction of the air blowing devices (the direction is selected to be the optimal position of the two air blowing devices selected according to the positions of the green plums needing to be air-blown), air-blows the green plums with defects (namely the green plums with festers and scars) (the two air blowing devices do not work simultaneously and are prevented from interfering with each other), and blows the green plums into the left fruit receiving basket 2 or the right fruit receiving basket 6 on the two sides of the conveyor belt 4;
(f) while blowing air, the lower computer controls a second steering engine 7-8 and a third steering engine 7-5 according to the weight information of the green plums placed downwards by the upper computer, and further controls a second partition plate 7-9 and a third partition plate 7-4 to turn respectively so as to adjust the conveying direction of the green plums without defects (namely the deep-processed green plums) on the conveying belt 4, and the green plums are conveyed into a second-stage sorting device 8 under the driving of the conveying belt 4;
(g) the lower computer controls two adjacent steering engines in the second-stage sorting device 8 to work according to the weight information of green plums placed down by the upper computer, further controls certain two partition plates of the five partition plates 8-2, the six partition plates 8-4, the seven partition plates 8-6 and the eight partition plates 8-8 to turn and ensures that the directions of the two partition plates are consistent with the directions of the two partition plates 7-9 and the three partition plates 7-4, and the green plums pass through the two partition plates and enter a certain grading channel 10 under the conveying of the conveying belt 4 and finally fall into a rear fruit receiving basket 11 corresponding to the tail end of the grading channel 10.
Specifically, the present embodiment can classify the green plums into festers, scars, and the like according to their surface defect characteristics. The biggest difference between the defect part and the normal surface is the difference in surface color, the color of the defect part is mostly brownish or even black, the gray value of the defect part can be inferred to be low, the gray value of the normal surface is high, and the defect is extracted from a single-channel gray image through threshold segmentation by utilizing the difference.
After channel decomposition, gray level binarization and other operations are performed on the green plum image, the embodiment finds that after the image of six color channel (R, G, B, H, S, V) components of the green plum fruit is subjected to threshold segmentation, because the shape, size, color and other characteristics of each defect are different, it is difficult to adopt a uniform extraction standard to extract the defect from the image subjected to threshold segmentation, and the green plum defect detection work becomes complicated.
In the embodiment, the edge detection method is adopted to detect the edge of the green plum fruit and expand the edge by multiple times to be used as a mask area, and the area covered by the mask is removed from the image after the H channel threshold segmentation, so that a defect area is left. Performing defect detection on the green plums containing festers and scars by adopting an edge method, wherein the area of the fester defect is large, and the proportion of the fester defect in the total area of the fruits is large; many raindrops are spots (the green plums with raindrops detected in this embodiment are also regarded as deep-processable green plums), and the number of raindrops is large and the area occupied by isolated spots is small. In addition, the colors of the peels corresponding to the fester, the scar and the raindrop are different from each other according to the corresponding color images of the fruits.
The Gaussian Mixture Model (GMM) classification process is: the gaussian mixture model is used to classify the intersections in the region of interest, and the following 6 features are extracted to establish the gaussian mixture model. Through comparison of three defects of green plum fruits, the color of the peel corresponding to each defect is different, and the shape and size characteristics are also different, so that R, G, B color component values, defect roundness, rectangle degree and compactness of the green plum fruit defect are determined to be adopted as input signals of a Gaussian mixture model, and the output signals are fester, scar, raindrop and intact green plum.
The detection accuracy rate of the green plums with the defect characteristic of ulceration is 100%, the detection accuracy rate of the green plums with the scar defect is 97.22%, the detection accuracy rate of the green plums with the defect characteristic of raindrop is 92.31%, and the detection accuracy rate of the intact green plums is 94.44%.
The scope of the present invention includes, but is not limited to, the above embodiments, and the present invention is defined by the appended claims, and any alterations, modifications, and improvements that may occur to those skilled in the art are all within the scope of the present invention.
Claims (7)
1. The green plum sorting device is characterized in that: the sorting device comprises a sorting module, wherein the sorting module comprises a first-stage sorting device, a second-stage sorting device, a camera and a conveyor belt, the camera is positioned above the first-stage sorting device, the first-stage sorting device and the second-stage sorting device are both positioned above the conveyor belt, and the first-stage sorting device is positioned in front of the second-stage sorting device;
the first-stage sorting device comprises four steering engines which are respectively a first steering engine, a second steering engine, a third steering engine and a fourth steering engine, wherein the first steering engine is connected with a first partition plate, the second steering engine is connected with a second partition plate, the third steering engine is connected with a third partition plate, the fourth steering engine is connected with a fourth partition plate, the second steering engine and the third steering engine are positioned between the first steering engine and the fourth steering engine, the opening directions of the first partition plate and the fourth partition plate are opposite to the moving direction of the conveyor belt, the opening directions of the second partition plate and the third partition plate are the same as the moving direction of the conveyor belt, the first partition plate and the fourth partition plate are both connected with an air blowing device, a left partition plate and a right partition plate are respectively arranged above two sides of;
the second-stage sorting device comprises four steering engines which are respectively a fifth steering engine, a sixth steering engine, a seventh steering engine and an eighth steering engine, wherein the fifth steering engine is connected with a fifth partition plate, the sixth steering engine is connected with a sixth partition plate, the seventh steering engine is connected with a seventh partition plate, the eighth steering engine is connected with an eighth partition plate, the opening orientations of the fifth partition plate, the sixth partition plate, the seventh partition plate and the eighth partition plate are the same as the moving direction of the conveyor belt, five grading partition plates are respectively arranged above the tail end of the conveyor belt, planes above the tail end of the conveyor belt are evenly divided into four grades by the five grading partition plates to.
2. The green plum sorting apparatus according to claim 1, wherein: the first-stage sorting device is characterized in that a first steering engine, a second steering engine, a third steering engine and a fourth steering engine are all connected to a first horizontal supporting plate, and a camera, the first horizontal supporting plate, a left partition plate and a right partition plate are all supported above the conveyor belt through a support.
3. The green plum sorting apparatus according to claim 2, wherein: and a fifth steering engine, a sixth steering engine, a seventh steering engine and an eighth steering engine of the second-stage sorting device are all connected to a second horizontal support plate, and the second horizontal support plate and the five grading partition plates are all supported above the conveyor belt through supports.
4. The green plum sorting apparatus according to claim 3, wherein: the first-stage sorting device further comprises a partition plate nine and a partition plate ten, the partition plate nine is located in front of the partition plate two, the partition plate ten is located in front of the partition plate three, and the partition plate nine and the partition plate ten are supported above the conveying belt through supports.
5. The green plum sorting apparatus according to claim 1, wherein: the device is characterized by further comprising a lower computer, the camera is electrically connected with the lower computer, the lower computer is electrically connected with control valves, a first steering engine, a second steering engine, a third steering engine, a fourth steering engine, a fifth steering engine, a sixth steering engine, a seventh steering engine and an eighth steering engine in the two air blowing devices respectively, and the lower computer is electrically connected with an upper computer.
6. The green plum sorting apparatus according to claim 5, wherein: the green plum weighing and sorting device is characterized by further comprising a weighing conveyor belt, wherein the weighing conveyor belt is used for weighing each green plum and sending the quality information of the green plum to an upper computer, and the weighing conveyor belt is also used for conveying each weighed green plum to a conveyor belt in the sorting module.
7. The green plum sorting method according to claim 6, comprising a green plum defect detection method and an upper computer control method;
the green plum defect detection method comprises the following steps:
(1) dividing a three-channel color image acquired by a camera into R, G, B single-channel monochromatic images, converting the three monochromatic images into HSV color space, and extracting green plums from an original image after S-channel component extraction, Gaussian filtering, feature extraction and division on the converted image;
(2) extracting a defect image from a single-channel gray image of the green plums by a threshold segmentation method according to the gray value difference of the surface defect characteristics of the green plums;
(3) extracting six characteristic parameters of the defect image: r, G, B color component values, defect roundness, squareness, and closeness;
(4) establishing a Gaussian mixture model according to six characteristic parameters of the defect image sample;
(5) inputting six characteristic parameters in a defect image to be detected into a Gaussian mixture model for matching, and completing defect identification and classification;
the upper computer control method comprises the following steps:
(a) the upper computer receives the quality information of each green plum uploaded by the weighing conveyer belt;
(b) when the green plums enter the first-stage sorting device through the conveyor belt, the camera works and sends images to the lower computer, and the lower computer sequentially carries out defect identification and classification on the green plums according to a green plum defect detection method and positions the green plums in the images;
(c) the lower computer transmits the defect identification classification result and the positioning information to the upper computer;
(d) the upper computer marks the defect identification classification result and the positioning information as labels on each corresponding green plum with weight information;
(e) the upper computer transmits the defect identification and classification result, the positioning information and the weight information of each green plum to the lower computer, and the lower computer controls a first steering engine or a fourth steering engine according to the positioning information transferred by the upper computer and the movement speed of the conveyor belt, further controls the direction of the air blowing device, blows the defective green plum and blows the defective green plum into a left fruit receiving basket or a right fruit receiving basket on two sides of the conveyor belt;
(f) the lower computer controls a second steering engine and a third steering engine according to the weight information of the green plums transferred by the upper computer, and further controls the second partition plate and the third partition plate to respectively steer so as to adjust the conveying direction of the green plums without defects on the conveying belt, and the green plums are conveyed into the second-stage sorting device under the driving of the conveying belt;
(g) the lower computer controls two adjacent steering engines in the second-stage sorting device to work according to the weight information of the green plums placed by the upper computer, and then controls certain two of the five partition plates, the six partition plates, the seven partition plates and the eight partition plates to turn and ensures that the directions of the two partition plates are consistent with the directions of the second partition plate and the third partition plate, the green plums pass through the two partition plates and enter a certain grading channel under the conveying of the conveying belt, and finally fall into a rear fruit receiving basket corresponding to the tail end of the grading channel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911020420.5A CN110586502B (en) | 2019-10-25 | 2019-10-25 | Green plum sorting device and sorting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911020420.5A CN110586502B (en) | 2019-10-25 | 2019-10-25 | Green plum sorting device and sorting method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110586502A true CN110586502A (en) | 2019-12-20 |
| CN110586502B CN110586502B (en) | 2023-08-11 |
Family
ID=68850283
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911020420.5A Active CN110586502B (en) | 2019-10-25 | 2019-10-25 | Green plum sorting device and sorting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110586502B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111337513A (en) * | 2020-04-08 | 2020-06-26 | 南京林业大学 | All-round collection system of green plum fruit surface image |
| CN112657862A (en) * | 2021-01-23 | 2021-04-16 | 郑州科技学院 | Industrial robot |
| CN113145497A (en) * | 2021-04-20 | 2021-07-23 | 清远职业技术学院 | Surface defect detection device based on machine vision |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104668199A (en) * | 2014-12-02 | 2015-06-03 | 浙江大学 | Automatic fruit grading device based on machine vision and bio-speckle |
| CN204727169U (en) * | 2015-07-03 | 2015-10-28 | 厦门分分钟食品有限公司 | A kind of carrot multipass sort device |
| CN107350168A (en) * | 2017-08-28 | 2017-11-17 | 宁夏大学 | A kind of potato Fast nondestructive evaluation self-grading device and method |
| US20180001353A1 (en) * | 2016-06-29 | 2018-01-04 | John Bean Technologies Corporation | Sorter |
| CN109848066A (en) * | 2019-02-28 | 2019-06-07 | 南京林业大学 | Green plum sorting unit and method |
| CN210730217U (en) * | 2019-10-25 | 2020-06-12 | 南京林业大学 | Green plum sorting device |
-
2019
- 2019-10-25 CN CN201911020420.5A patent/CN110586502B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104668199A (en) * | 2014-12-02 | 2015-06-03 | 浙江大学 | Automatic fruit grading device based on machine vision and bio-speckle |
| CN204727169U (en) * | 2015-07-03 | 2015-10-28 | 厦门分分钟食品有限公司 | A kind of carrot multipass sort device |
| US20180001353A1 (en) * | 2016-06-29 | 2018-01-04 | John Bean Technologies Corporation | Sorter |
| CN107350168A (en) * | 2017-08-28 | 2017-11-17 | 宁夏大学 | A kind of potato Fast nondestructive evaluation self-grading device and method |
| CN109848066A (en) * | 2019-02-28 | 2019-06-07 | 南京林业大学 | Green plum sorting unit and method |
| CN210730217U (en) * | 2019-10-25 | 2020-06-12 | 南京林业大学 | Green plum sorting device |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111337513A (en) * | 2020-04-08 | 2020-06-26 | 南京林业大学 | All-round collection system of green plum fruit surface image |
| CN112657862A (en) * | 2021-01-23 | 2021-04-16 | 郑州科技学院 | Industrial robot |
| CN113145497A (en) * | 2021-04-20 | 2021-07-23 | 清远职业技术学院 | Surface defect detection device based on machine vision |
| CN113145497B (en) * | 2021-04-20 | 2022-08-26 | 清远职业技术学院 | Surface defect detection device based on machine vision |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110586502B (en) | 2023-08-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107486415B (en) | Thin bamboo strip defect online detection system and detection method based on machine vision | |
| CN110586502B (en) | Green plum sorting device and sorting method | |
| 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 | |
| CN103406286B (en) | Online grading method for external quality of fruit based on LabVIEW | |
| CN108287010B (en) | Crab multi-index grading device and method | |
| CN107952696A (en) | A kind of detection grading plant and detection method suitable for fresh tobacco leaf | |
| CN112893159B (en) | Coal gangue sorting method based on image recognition | |
| CN110584164B (en) | Green plum sorting production line and sorting method | |
| CN210730217U (en) | Green plum sorting device | |
| Thong et al. | Mango classification system uses image processing technology and artificial intelligence | |
| CN113333327B (en) | Automatic conveying and sorting system based on industrial robot | |
| CN112676195B (en) | Color sorting device and method for solid wood floor based on linear array CMOS camera | |
| CN217165388U (en) | Unqualified glove classifying screen device | |
| CN110918501A (en) | Intelligent fruit optimization device and detection method | |
| CN113560214B (en) | Intelligent sorting system for pearls and application method thereof | |
| CN213529709U (en) | Fruit sorting machine | |
| CN112474415B (en) | Fruit sorting machine | |
| CN113128502A (en) | Single piece separation system, method and device based on deep learning and machine vision | |
| CN211217614U (en) | Intelligent fruit optimization equipment with grade fine sorting function | |
| Thong et al. | Mango sorting mechanical system uses machine vision and artificial intelligence | |
| CN111723861A (en) | Coal gangue percentage identification method for coal mine control baffle | |
| Liu et al. | Intelligent bamboo part sorting system design via machine vision | |
| CN220479470U (en) | Stone grading device | |
| Dumanay et al. | A New Design of Olive Fruit Sorting Machine Using Color Image Processing |
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 |