CN112387626A - Apple raw material quality identification method based on lightweight neural network - Google Patents
Apple raw material quality identification method based on lightweight neural network Download PDFInfo
- Publication number
- CN112387626A CN112387626A CN202011168871.6A CN202011168871A CN112387626A CN 112387626 A CN112387626 A CN 112387626A CN 202011168871 A CN202011168871 A CN 202011168871A CN 112387626 A CN112387626 A CN 112387626A
- Authority
- CN
- China
- Prior art keywords
- holes
- neural network
- apples
- raw material
- lightweight neural
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
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
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
- B07C5/362—Separating or distributor mechanisms
-
- A—HUMAN NECESSITIES
- A23—FOODS OR FOODSTUFFS; TREATMENT THEREOF, NOT COVERED BY OTHER CLASSES
- A23N—MACHINES OR APPARATUS FOR TREATING HARVESTED FRUIT, VEGETABLES OR FLOWER BULBS IN BULK, NOT OTHERWISE PROVIDED FOR; PEELING VEGETABLES OR FRUIT IN BULK; APPARATUS FOR PREPARING ANIMAL FEEDING- STUFFS
- A23N15/00—Machines or apparatus for other treatment of fruits or vegetables for human purposes; Machines or apparatus for topping or skinning flower bulbs
-
- 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
-
- 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
- B07C5/02—Measures preceding sorting, e.g. arranging articles in a stream orientating
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- A—HUMAN NECESSITIES
- A23—FOODS OR FOODSTUFFS; TREATMENT THEREOF, NOT COVERED BY OTHER CLASSES
- A23N—MACHINES OR APPARATUS FOR TREATING HARVESTED FRUIT, VEGETABLES OR FLOWER BULBS IN BULK, NOT OTHERWISE PROVIDED FOR; PEELING VEGETABLES OR FRUIT IN BULK; APPARATUS FOR PREPARING ANIMAL FEEDING- STUFFS
- A23N15/00—Machines or apparatus for other treatment of fruits or vegetables for human purposes; Machines or apparatus for topping or skinning flower bulbs
- A23N2015/008—Sorting of fruit and vegetables
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N2021/845—Objects on a conveyor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N2021/8466—Investigation of vegetal material, e.g. leaves, plants, fruits
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Food Science & Technology (AREA)
- Polymers & Plastics (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Sorting Of Articles (AREA)
Abstract
The invention relates to the technical field of apple raw material quality detection, and discloses an apple raw material quality identification method based on a lightweight neural network. The two cameras are arranged for detecting the image state of the apples in real time, after the images are transmitted to a lightweight neural network system in the controller for comparing data, once the apples in the object placing holes on the screening conveyor belt are identified to be unqualified, the controller controls the air cylinders connected with the corresponding movable supporting plates below the object placing holes to work, so that the air cylinders work to drive the movable supporting plates to move leftwards, the falling holes in the movable supporting plates are aligned with the through holes, the unqualified apples are screened, and the automation degree is high.
Description
Technical Field
The invention relates to the technical field of apple raw material quality detection, in particular to an apple raw material quality identification method based on a lightweight neural network.
Background
At present, the construction of a large-scale deep neural network usually requires strong expert knowledge, and a great deal of time and energy are consumed by researchers generally, especially in the field of remote sensing image processing. Meanwhile, these artificially designed networks are usually high in computational complexity and large in memory overhead, and also pose a great challenge to deployment on edge computing devices. The neural structure search is an automatic design method specially aiming at the deep neural network, the method can effectively reduce the degree of manual participation, and the deep neural network is automatically built under the machine view angle.
The fruit yield of China is always stably located in the first position of the world, the fruit planting area is increasing year by year, but in the era of rapid development of the fruit planting area, apples need to be packaged after being picked, the apples need to be rotten and damaged and are separated out before being packaged, but the current mode is operated by adopting a manual screening mode, time and labor are wasted, and the whole detection efficiency is low.
Disclosure of Invention
The invention aims to provide an apple raw material quality identification method based on a lightweight neural network, and solves the problems in the background art.
In order to achieve the purpose, the invention provides the following technical scheme: a light-weight neural network-based apple raw material quality identification method comprises a bottom plate, wherein four corners of the bottom plate are vertically and downwards fixedly connected with a support, a collecting tank is vertically and upwards arranged in the middle of the upper portion of the bottom plate, and front and rear side walls of the collecting tank are both downwards inclined and fixedly communicated with a diversion box; the transmission rollers are horizontally and longitudinally fixedly arranged at the left part and the right part of the bottom plate, the two transmission rollers are in transmission connection through a screening conveyer belt, the bearing supporting plate is horizontally and fixedly arranged at the upper part of the bottom plate, and a plurality of through holes which are distributed at equal intervals are vertically arranged at the left part and the right part of the middle part of the bearing supporting plate;
a plurality of object placing holes which are distributed at equal intervals are vertically arranged on the screening and conveying belt along the width direction of the screening and conveying belt; a plurality of cylinders which are distributed at equal intervals are horizontally and fixedly installed on the left part and the right part of the bottom surface of the bearing supporting plate in an opposite mode, the end part of a piston rod of each cylinder is fixedly connected with a movable supporting plate, the number of the movable supporting plates is equal to the number of the vertical rows of the object placing holes distributed on the screening conveying belt, and a plurality of dropping holes which are distributed at equal intervals are vertically formed in the movable supporting plate; the camera is characterized in that side plates are vertically and upwards fixedly mounted on the front side wall and the rear side wall of the bottom plate, a transverse plate is horizontally and fixedly connected to the upper portion of the middle position between the two side plates, cameras are fixedly mounted on the left portion and the right portion of the bottom surface of the transverse plate, and a controller is vertically and upwards fixedly mounted on the front side of the upper portion of the transverse plate.
As a preferred embodiment of the invention, the bottom of the inner cavity of the collecting tank is distributed in a way that the middle is high and the front side and the rear side are low.
As a preferred embodiment of the present invention, the number of the object placing holes is equal to the number of the through holes, and the object placing holes and the through holes are vertically aligned.
As a preferred embodiment of the invention, the aperture of the drop hole on the moving supporting plate increases from inside to outside.
As a preferred embodiment of the present invention, the number of the longitudinally distributed dropping holes is equal to the number of the through holes, and the dropping hole with the smallest aperture is equal to the aperture of the through hole.
As a preferred embodiment of the present invention, the two cameras are respectively aligned with the two flow guiding boxes distributed on the left and right of the bottom plate in the vertical direction.
As a preferred embodiment of the invention, a sponge cushion is fixedly paved at the bottom of the inner cavity of the collecting tank.
As a preferred embodiment of the present invention, an apple raw material quality identification method based on a lightweight neural network includes the following operation steps:
s1: firstly, inputting qualified image information of apples of different varieties into a lightweight neural network system of a controller by an operator;
s2: the method comprises the following steps that an operator puts picked apples or apples of different types on a screening conveying belt in batches, and each apple is guaranteed to be independently distributed in a placement hole of the screening conveying belt;
s3: when the screening transmission belt works, apples on the distribution transmission belt are subjected to real-time detection on the image state of the apples through two cameras at the bottom of the transverse plate, after the images are transmitted to a lightweight neural network system in the controller for comparison data, once the apples in the object placing holes on the screening transmission belt are identified to be unqualified, the controller controls the air cylinders connected with the corresponding movable supporting plates below the object placing holes to work, so that the air cylinders are controlled to work to drive the movable supporting plates to move leftwards, the falling holes in the movable supporting plates are aligned with the through holes, and then the unqualified apples are screened out, the screening mode is rapid and convenient, and the automation degree is high;
s4: the apple that falls from the downthehole falls and cushions on the sponge pad on the collecting vat and discharge from the water conservancy diversion box under the effect of dead weight, convenient and fast.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, the image state of the apples is detected in real time through the two arranged cameras, after the images are transmitted to a lightweight neural network system in the controller for comparison data, once the apples in the object placing holes on the screening conveyor belt are identified to be unqualified, the controller controls the air cylinders connected with the corresponding movable supporting plates below the object placing holes to work, so that the air cylinders work to drive the movable supporting plates to move leftwards, the falling holes on the movable supporting plates are aligned with the through holes, and then the unqualified apples are screened.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is a schematic overall structure diagram of an apple raw material quality identification method based on a lightweight neural network according to the present invention;
FIG. 2 is a schematic diagram of a right-view structure of the apple raw material quality identification method based on the lightweight neural network of the present invention;
FIG. 3 is a schematic structural diagram of a movable supporting plate of the apple raw material quality identification method based on the lightweight neural network of the present invention;
FIG. 4 is a structural diagram of the distribution positions of through holes on a bearing supporting plate in the method for identifying the quality of apple raw materials based on a lightweight neural network;
fig. 5 is a schematic view of a sponge mat distributed in a collecting tank and overlooked in the method for identifying the quality of the apple raw material based on the lightweight neural network.
In the figure: 1. a base plate; 2. a support; 3. a driving roller; 4. screening a conveying belt; 5. a placing hole; 6. a side plate; 7. a camera; 8. a controller; 9. a transverse plate; 10. a through hole; 11. collecting tank; 12. a flow guiding box; 13. moving the supporting plate; 14. a cylinder; 15. a load bearing pallet; 16. dropping holes; 17. a spongy cushion.
The apparatus of the present invention is commercially available and custom made.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention easy to understand, the invention is further described with the specific embodiments.
In the description of the present invention, it is to be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are only for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed in a particular orientation, and be operated, and thus, should not be construed as limiting the present invention; in the description of the present invention, it should be noted that unless otherwise explicitly stated or limited, the terms "mounted," "connected," and "disposed" are to be construed broadly and can, for example, be fixedly connected, disposed, detachably connected, disposed, or integrally connected and disposed. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Referring to fig. 1-5, the present invention provides a technical solution: a light weight neural network-based apple raw material quality identification method comprises a bottom plate 1, wherein four corners of the bottom plate 1 are vertically and downwards fixedly connected with a support 2, a collecting tank 11 is vertically and upwards arranged in the middle of the upper part of the bottom plate 1, and two side walls of the front and rear parts of the collecting tank 11 are downwards inclined and fixedly communicated with a diversion box 12; the transmission rollers 3 are horizontally and longitudinally fixedly arranged at the left part and the right part of the bottom plate 1, the two transmission rollers 3 are in transmission connection through a screening conveyer belt 4, the bearing supporting plate 15 is horizontally and fixedly arranged at the upper part of the bottom plate 1, and a plurality of through holes 10 which are distributed at equal intervals are vertically arranged at the left part and the right part of the middle part of the bearing supporting plate 15;
a plurality of equally-distributed object placing holes 5 are vertically formed in the screening conveying belt 4 along the width direction of the screening conveying belt; a plurality of cylinders 14 which are distributed at equal intervals are horizontally and oppositely and fixedly arranged at the left part and the right part of the bottom surface of the bearing supporting plate 15, the end part of a piston rod of each cylinder 14 is fixedly connected with a movable supporting plate 13, the number of the movable supporting plates 13 is equal to the number of the longitudinal rows of the placing holes 5 distributed on the screening conveying belt 4, and a plurality of falling holes 16 which are distributed at equal intervals are vertically arranged on the movable supporting plates 13; the bottom plate 1 is characterized in that side plates 6 are vertically and upwards fixedly mounted on the front side wall and the rear side wall of the bottom plate 1, two side plates are located between the side plates 6, a transverse plate 9 is horizontally and fixedly connected to the upper portion of the middle position of the.
In this embodiment (see fig. 1), the bottom of the inner cavity of the collecting tank 11 is distributed in a manner that the middle is high and the front and the rear sides are low, so as to ensure that the fallen apples can fall under the action of self-weight.
In this embodiment (see fig. 1), the number of the storage holes 5 is equal to the number of the through holes 10, and the storage holes 5 are vertically aligned with the through holes 10.
In this embodiment, the aperture of the dropping hole 16 on the movable supporting plate 13 increases from inside to outside.
In this embodiment (see fig. 1), the number of the falling holes 16 distributed longitudinally is equal to the number of the through holes 10, and the falling hole 16 with the smallest aperture is equal to the aperture of the through hole 10.
In this embodiment (see fig. 1), the two cameras 7 are respectively aligned with the two diversion boxes 12 distributed on the left and right sides of the bottom plate 1 in the vertical direction, and the diversion boxes 12 can guide the fallen apples.
In this embodiment (see fig. 5), a sponge pad 17 is fixedly laid at the bottom of the inner cavity of the collecting tank 11, so as to ensure that the fallen apples are buffered and damped.
In this embodiment, an apple raw material quality identification method based on a lightweight neural network includes the following operation steps:
s1: firstly, inputting qualified image information of apples of different varieties into a lightweight neural network system of a controller 8 by an operator;
s2: the method comprises the following steps that an operator puts picked apples or apples of different types on a screening conveyor belt 4 in batches, and each apple is guaranteed to be independently distributed in a placement hole 5 of the screening conveyor belt 4;
s3: when the screening transmission belt 4 works, apples on the distribution transmission belt pass through the two cameras 7 at the bottom of the transverse plate 9 to detect the image state of the apples in real time, after the images are transmitted to a lightweight neural network system in the controller 8 for comparison data, once the apples in the object placing holes 5 on the screening transmission belt 4 are identified to be unqualified, the controller 8 controls the air cylinders 14 connected with the corresponding movable supporting plates 13 below the object placing holes 5 to work, so that the air cylinders 14 are controlled to work to drive the movable supporting plates 13 to move leftwards, and the unqualified apples are screened after the falling holes 16 on the movable supporting plates 13 are aligned with the through holes 10;
s4: the apples falling from the falling hole 16 fall on the sponge mat 17 on the collecting tank 11 for buffering and are discharged from the diversion box 12 under the action of self weight, and the device is convenient and fast.
When the method for identifying the quality of the apple raw material based on the lightweight neural network is used, it should be noted that the method for identifying the quality of the apple raw material based on the lightweight neural network is provided, all parts are universal standard parts or parts known by a person skilled in the art, and the structure and the principle of the method can be known by the person skilled in the art through technical manuals or conventional experimental methods.
While there have been shown and described what are at present considered the fundamental principles and essential features of the invention and its advantages, it will be apparent to those skilled in the art that the invention is not limited to the details of the foregoing exemplary embodiments, but is capable of other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (8)
1. A method for identifying the quality of apple raw materials based on a lightweight neural network is characterized by comprising the following steps: the device comprises a bottom plate (1), wherein four corners of the bottom plate (1) are vertically and downwards fixedly connected with a support (2), a collecting tank (11) is vertically and upwards arranged in the middle of the upper part of the bottom plate (1), and front and rear side walls of the collecting tank (11) are both downwards inclined and fixedly communicated with a flow guide box (12); the transmission rollers (3) are horizontally and longitudinally fixedly arranged at the left part and the right part of the bottom plate (1), the two transmission rollers (3) are in transmission connection through a screening conveyer belt (4), the bearing supporting plate (15) is horizontally and fixedly arranged at the upper part of the bottom plate (1), and a plurality of through holes (10) which are distributed at equal intervals are vertically arranged at the left part and the right part of the middle part of the bearing supporting plate (15);
a plurality of equally-distributed object placing holes (5) are vertically formed in the screening conveying belt (4) along the width direction of the screening conveying belt; a plurality of cylinders (14) which are distributed at equal intervals are horizontally and oppositely and fixedly arranged at the left part and the right part of the bottom surface of the bearing supporting plate (15), the end part of a piston rod of each cylinder (14) is fixedly connected with a movable supporting plate (13), the number of the movable supporting plates (13) is equal to the number of the vertical rows of the object placing holes (5) distributed on the screening conveying belt 4, and a plurality of dropping holes (16) which are distributed at equal intervals are vertically arranged on the movable supporting plates (13); equal vertical upwards fixed mounting of both sides wall has curb plate (6) around bottom plate (1), is located two horizontal fixedly connected with diaphragm (9) in intermediate position upper portion between curb plate (6), the equal fixed mounting in both sides has camera (7) about diaphragm (9) bottom surface, is located the vertical upwards fixed mounting in front side on diaphragm (9) upper portion has controller (8).
2. The apple raw material quality identification method based on the lightweight neural network as claimed in claim 1, wherein: the bottom of the inner cavity of the collecting tank (11) is distributed in a way that the middle is high and the front side and the rear side are low.
3. The apple raw material quality identification method based on the lightweight neural network as claimed in claim 1, wherein: the number of the object placing holes (5) is equal to that of the through holes (10), and the object placing holes (5) are vertically aligned with the through holes (10).
4. The apple raw material quality identification method based on the lightweight neural network as claimed in claim 1, wherein: the aperture of the dropping hole (16) on the movable supporting plate (13) is gradually increased from inside to outside.
5. The apple raw material quality identification method based on the lightweight neural network as claimed in claim 1, wherein: the number of the longitudinally distributed dropping holes (16) is equal to that of the through holes (10), and the diameter of the dropping hole (16) with the smallest diameter is equal to that of the through hole (10).
6. The apple raw material quality identification method based on the lightweight neural network as claimed in claim 1, wherein: the two cameras (7) are respectively aligned with the two flow guide boxes (12) distributed at the left part and the right part of the bottom plate (1) in the vertical direction.
7. The apple raw material quality identification method based on the lightweight neural network as claimed in claim 1, wherein: a spongy cushion (17) is fixedly paved at the bottom of the inner cavity of the collecting tank (11).
8. The apple raw material quality identification method based on the lightweight neural network as claimed in claim 1, characterized by comprising the following operation steps:
s1: firstly, inputting qualified image information of apples of different varieties into a lightweight neural network system of a controller (8) by an operator;
s2: the method comprises the following steps that an operator puts picked apples or apples of different types on a screening conveyor belt (4) in batches, and each apple is guaranteed to be independently distributed in a placement hole (5) of the screening conveyor belt (4);
s3: when the screening transmission belt 4 works, apples on the distribution transmission belt are subjected to real-time detection on the image state of the apples through two cameras (7) at the bottom of the transverse plate (9), after the images are transmitted to a lightweight neural network system in the controller (8) for comparison data, once the apples in the object placing holes (5) on the screening transmission belt (4) are identified to be unqualified, the controller (8) controls the air cylinders (14) connected with the corresponding movable supporting plates (13) below the object placing holes (5) to work, so that the air cylinders (14) are controlled to work to drive the movable supporting plates (13) to move leftwards, the falling holes (16) on the movable supporting plates (13) are aligned with the through holes (10), and then the unqualified apples are screened out, the screening mode is rapid and convenient, and the automation degree is high;
s4: the apples falling from the falling hole (16) fall on the sponge mat (17) on the collecting tank (11) for buffering and are discharged from the diversion box (12) under the action of self weight, so that the apple storage box is convenient and fast.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011168871.6A CN112387626A (en) | 2020-10-28 | 2020-10-28 | Apple raw material quality identification method based on lightweight neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011168871.6A CN112387626A (en) | 2020-10-28 | 2020-10-28 | Apple raw material quality identification method based on lightweight neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112387626A true CN112387626A (en) | 2021-02-23 |
Family
ID=74597978
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011168871.6A Pending CN112387626A (en) | 2020-10-28 | 2020-10-28 | Apple raw material quality identification method based on lightweight neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112387626A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102527650A (en) * | 2011-12-05 | 2012-07-04 | 浙江佳丽珍珠首饰有限公司 | Pearl falling and automatic sorting device |
| CN103567157A (en) * | 2013-11-12 | 2014-02-12 | 浙江省农业科学院 | Device for sorting membrane-removed satsuma mandarin segments by segments |
| PL405047A1 (en) * | 2013-08-12 | 2015-02-16 | International Tobacco Machinery Poland Spółka Z Ograniczoną Odpowiedzialnością | Assembly for separation and method of separation of selected defective objects from the group of objects used in tobaco industry |
| CN106829082A (en) * | 2017-03-10 | 2017-06-13 | 胡珂 | A kind of apple automatic boxing machine that can detect apple integrity degree |
| CN108906642A (en) * | 2018-08-24 | 2018-11-30 | 深圳科易设计服务有限公司 | Detect sorted and packaged mechanism |
| CN210618577U (en) * | 2019-08-29 | 2020-05-26 | 郑州轻工业学院 | Fruit sorting and size grading packaging system based on machine vision and PLC control |
| CN214289462U (en) * | 2020-10-09 | 2021-09-28 | 扬州润吉智能设备科技有限公司 | Apple raw material quality identification and detection device based on lightweight neural network |
-
2020
- 2020-10-28 CN CN202011168871.6A patent/CN112387626A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102527650A (en) * | 2011-12-05 | 2012-07-04 | 浙江佳丽珍珠首饰有限公司 | Pearl falling and automatic sorting device |
| PL405047A1 (en) * | 2013-08-12 | 2015-02-16 | International Tobacco Machinery Poland Spółka Z Ograniczoną Odpowiedzialnością | Assembly for separation and method of separation of selected defective objects from the group of objects used in tobaco industry |
| CN103567157A (en) * | 2013-11-12 | 2014-02-12 | 浙江省农业科学院 | Device for sorting membrane-removed satsuma mandarin segments by segments |
| CN106829082A (en) * | 2017-03-10 | 2017-06-13 | 胡珂 | A kind of apple automatic boxing machine that can detect apple integrity degree |
| CN108906642A (en) * | 2018-08-24 | 2018-11-30 | 深圳科易设计服务有限公司 | Detect sorted and packaged mechanism |
| CN210618577U (en) * | 2019-08-29 | 2020-05-26 | 郑州轻工业学院 | Fruit sorting and size grading packaging system based on machine vision and PLC control |
| CN214289462U (en) * | 2020-10-09 | 2021-09-28 | 扬州润吉智能设备科技有限公司 | Apple raw material quality identification and detection device based on lightweight neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN206705277U (en) | Self-feeding machine people's system integration | |
| CN206701743U (en) | A kind of materials-sorting system | |
| CN207106970U (en) | A kind of automatic detection circulating plate machine | |
| CN112605001A (en) | High-precision rapid detection equipment | |
| CN108323028B (en) | Integrated production line and integrated operation method for cleaning PCB finished products | |
| CN102680102A (en) | Automatic detection method of solar silicon chip colors based on machine vision | |
| CN110877015A (en) | Flexible letter sorting production line of intelligence commodity circulation | |
| CN105548198A (en) | Method for automatically detecting quality of complex product based on cloud platform | |
| CN214289462U (en) | Apple raw material quality identification and detection device based on lightweight neural network | |
| CN108455150A (en) | Circulation formula automatic sorting access device in one kind | |
| CN111438072A (en) | Product letter sorting equipment weighs | |
| CN209337611U (en) | A kind of lift-on/lift-off type high speed pick-and-place material platform | |
| CN112387626A (en) | Apple raw material quality identification method based on lightweight neural network | |
| CN206269766U (en) | Product plane degree detection means | |
| CN112551136A (en) | Portable timber is selected separately pile up neatly system | |
| CN109351655A (en) | A kind of improvement device of jujube pickout apparatus | |
| CN211926765U (en) | Detection apparatus for be used for new forms of energy battery full size to measure | |
| CN109526878B (en) | Full-automatic quantitative box separating machine | |
| CN203206916U (en) | Egg collecting and classifying integrated equipment | |
| CN117007519A (en) | Appearance detection equipment of semiconductor chip frame | |
| CN209271938U (en) | A kind of improvement device of jujube pickout apparatus | |
| CN209139210U (en) | A kind of axis products detection device | |
| CN102205319A (en) | Length classification method and device for shellfish aquatic product and strip-and-stem-shaped vegetable and fruit | |
| CN115606623A (en) | Crayfish sorting device based on machine vision | |
| CN114535107B (en) | Back-checking sorting and blanking device and blanking method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210223 |
|
| RJ01 | Rejection of invention patent application after publication |