CN112718548A - General type agricultural product intelligence sorter of degree of depth study - Google Patents
General type agricultural product intelligence sorter of degree of depth study Download PDFInfo
- Publication number
- CN112718548A CN112718548A CN202011433911.5A CN202011433911A CN112718548A CN 112718548 A CN112718548 A CN 112718548A CN 202011433911 A CN202011433911 A CN 202011433911A CN 112718548 A CN112718548 A CN 112718548A
- Authority
- CN
- China
- Prior art keywords
- sorting
- machine
- agricultural product
- images
- flat
- 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
- 230000005540 biological transmission Effects 0.000 claims abstract description 24
- 238000013135 deep learning Methods 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 11
- 230000008569 process Effects 0.000 claims abstract description 8
- 238000012360 testing method Methods 0.000 claims abstract description 7
- 238000013508 migration Methods 0.000 claims abstract description 5
- 230000005012 migration Effects 0.000 claims abstract description 5
- 238000003062 neural network model Methods 0.000 claims abstract description 3
- 238000001514 detection method Methods 0.000 claims description 6
- 238000007670 refining Methods 0.000 claims description 4
- 238000013526 transfer learning Methods 0.000 claims description 4
- 230000006386 memory function Effects 0.000 claims description 2
- 238000011161 development Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 244000000626 Daucus carota Species 0.000 description 2
- 235000002767 Daucus carota Nutrition 0.000 description 2
- 235000007688 Lycopersicon esculentum Nutrition 0.000 description 2
- 244000141359 Malus pumila Species 0.000 description 2
- 240000003768 Solanum lycopersicum Species 0.000 description 2
- 244000061456 Solanum tuberosum Species 0.000 description 2
- 235000002595 Solanum tuberosum Nutrition 0.000 description 2
- 244000269722 Thea sinensis Species 0.000 description 2
- 235000021016 apples Nutrition 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 235000012015 potatoes Nutrition 0.000 description 2
- 230000008054 signal transmission Effects 0.000 description 2
- 235000013616 tea Nutrition 0.000 description 2
- 208000032544 Cicatrix Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 231100000241 scar Toxicity 0.000 description 1
- 230000037387 scars Effects 0.000 description 1
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
- B07C5/34—Sorting according to other particular properties
-
- 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
- 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
- B07C5/363—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
-
- 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
Abstract
The invention discloses a deep learning general type agricultural product intelligent sorting machine which comprises a flat throwing type sorting machine, a 5G transmission and cloud storage module and a deep learning algorithm decision system. The sorting process is divided into two stages, namely a machine training and debugging stage and a machine testing working stage, wherein in the machine training stage, agricultural product materials which are manually sorted are sequentially placed into a flat-throw type sorting machine in the training stage, the images are collected by a camera and then uploaded to a cloud storage module through a 5G transmission module, and the material images are sequentially subjected to lifetime learning through migration learning to obtain a decision neural network model. In the working stage of the machine, materials to be sorted are directly placed into the flat throw type sorting machine, the camera acquires images and uploads the images to the cloud, a sorting instruction is obtained through the decision system, the images are descended to the flat throw sorting machine to control the air gun array, and therefore sorting is completed.
Description
Technical Field
The invention discloses a deep learning universal agricultural product intelligent sorting machine, and particularly relates to an automatic device which combines 5G cloud decision and migration lifetime learning and realizes sorting of universal agricultural products through a flat throwing sorting machine structure.
Background
With the improvement of living standard of people, the graded sale of agricultural products is a necessary trend of development, which is more obvious particularly in some foreign trade industries, and at present, instrument type, electronic type and image type sorting machines appear at home and abroad. The mechanical sorting of agricultural products is realized according to the size of meshes or supporting roller spaces, the electronic sorting machine can accurately weigh the weight of materials through the online pressure sensor, however, the two sorting machines can intelligently distinguish the sizes and cannot detect defective products, and the image sorting machine can see scars and the like of the materials, so that the online sorting of the defective products is realized, and the sorting model has no learning capacity, so that the machine has multiple purposes and cannot realize the sorting of general agricultural products.
Aiming at the defects, the development of a universal sorting machine is possible along with the development of deep learning, 5G technology, cloud storage and cloud computing in recent years, and the automatic device for sorting the universal agricultural products is realized by combining 5G cloud decision and migration lifetime learning and by means of a flat throwing sorting machine structure.
Disclosure of Invention
The invention aims to overcome the defects of the problems and discloses a deep learning universal type agricultural product intelligent sorting machine.
The above purpose is realized by the following technical scheme:
the device comprises a flat throwing type sorting machine, a 5G transmission and cloud storage module and a deep learning algorithm decision system; the sorting process is divided into two stages, namely a machine training and debugging stage and a machine testing working stage, wherein in the machine training stage, agricultural product materials which are manually sorted are sequentially placed into a flat-throw type sorting machine in the training stage, images are collected by a camera and then uploaded to a cloud storage module through a 5G transmission module, and the material images are sequentially subjected to lifetime learning through migration learning to obtain a decision neural network model; and in the working stage of the machine, the materials to be sorted are directly placed into the flat throw type sorting machine, the camera acquires images and uploads the images to the cloud, a sorting instruction is obtained through the decision system, and the images are descended to the flat throw sorting machine to control the air gun array, so that sorting is completed.
Wherein:
(1) the flat throwing type sorting machine comprises a material homogenizing device, a flat belt, a detection system, a collection box, a rack and a power system, wherein the material homogenizing device is arranged at the front end of the flat belt, the detection system is arranged at the tail end of the flat belt, the collection box is arranged below the detection device, the power system provides power for the flat belt, and the power system is particularly a stepping motor; the detection system comprises a pair of industrial linear array cameras, a light source, a background plate, an air gun array and a control module which are symmetrically distributed, the industrial linear array cameras, the light source, the background plate, the air gun array and the control module are symmetrically distributed at two ends of a parabola through which materials pass, the air gun array is arranged at the lower end of the cameras, and particularly, a pattern with plain patterns can be selected according to material properties.
(2) The 5G transmission and cloud storage module consists of a 5G transmission module and a cloud storage; wherein 5G transmission module links to each other with camera, air gun control module, and the photo that the linear array camera was shot on line can be uploaded to high-end memory at a high speed through 5G transmission module, and the signal of high-end decision-making system decision-making also can be passed to air gun control module at a high speed through 5G transmission module, and then control the air gun switching to send the material of different grades into in the hierarchical collecting box of different grades.
(3) A deep learning algorithm decision system is characterized in that the core of the deep learning algorithm decision system is a lifelong learning algorithm based on transfer learning, the algorithm firstly pre-trains a network through an ImageNet data set by adopting one of transfer learning models (Alexnet, GoogleNet and VGGNet), and then finely adjusts the network weight based on a batch of image data of a certain agricultural product material actually measured through a conveyor belt to obtain a sorting model which can adapt to the agricultural product, and the model can be applied to sorting the agricultural product; when another agricultural product is added for model fine adjustment, firstly, the influence of the network weight on the recognition result is measured through a cross entropy method, the weight coefficient is adjusted according to the influence, the adjustment with the large weight is small or not adjusted as much as possible, the influence is small and can be adjusted greatly, and therefore a network structure is obtained through training, and the network can be suitable for sorting of a second agricultural product and is also suitable for sorting of a first agricultural product; when increasing more agricultural product varieties, analogize in proper order because have the memory function to make the network through constantly studying, can realize the sorting of multiple agricultural product, along with the constantly increasing of agricultural product variety, combine the powerful storage capacity of cloud storage, can realize the sorting of general agricultural product.
(4) In the machine training and debugging stage, firstly, agricultural products to be classified are classified into 2-3 grades through an artificial classification standard, then, flat belts are placed according to batches, classification labels are made, a linear array camera is controlled to shoot images of all materials on line, and the images are uploaded to a cloud end to obtain a decision model; the machine training is good and can get into the working phase, machine test working phase, just pour the material of treating categorised into the refining device, machine automatic classification's process, the camera is real-time to shoot the photo on line, uploads to the high in the clouds decision-making module through 5G transmission module, and the decision-making result passes through 5G transmission module again and gives air gun control module and then control the air gun and select separately.
It should be noted that: the 5G and cloud computing are only one mode, and certainly, under the condition that cluster application and cost are not considered, a mode of wired signal transmission and airborne computer operation can be adopted, cables are adopted to replace 5G signal transmission, and airborne computers are adopted to replace cloud computing.
The invention has the following effects: the technology of the invention realizes the universal sorting process of various agricultural products, the machine has lifelong learning capability, can be used for multiple purposes and multiple functions, can be widely applied to sorting crops such as apples, tomatoes, potatoes, carrots, tea leaves and the like, has obvious economic benefit, and has high technological content by 5G transmission, cloud storage, cloud computing and artificial intelligence, improves the added value of the agricultural products and has obvious social benefit.
Drawings
FIG. 1 is a general schematic diagram of an intelligent agricultural product sorting machine for deep learning and general purpose of the invention.
Wherein: 1 agricultural product material, 2 refining devices, 3 flat belt conveyor belts, 4 lamp boxes, 5 light sources, 6 cameras, 7 air guns, 8 collecting boxes and 9 motors.
Fig. 2 is a schematic diagram of two stages of the sorting process.
Detailed Description
Specific embodiments of the present apparatus and method are described below in conjunction with the appended drawings.
In the case of the example 1, the following examples are given,
referring to fig. 1, the general schematic diagram of the deep learning general agricultural product intelligent sorting machine of the present invention includes a flat-throw sorting machine, a 5G transmission and cloud storage module, and a deep learning algorithm decision system;
referring to fig. 2, the sorting process is divided into two stages, a machine training and debugging stage and a machine testing and working stage. In the machine training and debugging stage, agricultural products to be classified are classified into 2-3 grades through an artificial classification standard, then flat belts are placed according to batches, classification labels are made, the linear array camera is controlled to shoot images of all materials on line, and the images are uploaded to the cloud end to obtain a decision model. The machine training is good and can work, the machine test working stage is that the material to be classified is poured into the refining device, the automatic classification process of the machine, the camera shoots photos on line in real time, the photos are uploaded to the cloud decision module through the 5G transmission module, and the decision result is then transmitted to the air gun control module through the 5G transmission module so as to control the air gun to be sorted.
The invention can be widely applied to sorting crops such as apples, tomatoes, potatoes, carrots, tea leaves and the like, and sorting other objects, and is also applicable to the protection scope of the invention as long as the basic idea of the invention is not violated, and the protection scope of the invention is defined by the claims.
Claims (5)
1. The utility model provides a general type agricultural product intelligence sorter of degree of deep learning, characterized by: the system comprises a flat throwing type sorting machine, a 5G transmission and cloud storage module and a deep learning algorithm decision system; the sorting process is divided into two stages, namely a machine training and debugging stage and a machine testing working stage, wherein in the machine training stage, agricultural product materials which are manually sorted are sequentially placed into a flat-throw type sorting machine in the training stage, images are collected by a camera and then uploaded to a cloud storage module through a 5G transmission module, and the material images are sequentially subjected to lifetime learning through migration learning to obtain a decision neural network model; and in the working stage of the machine, the materials to be sorted are directly placed into the flat throw type sorting machine, the camera acquires images and uploads the images to the cloud, a sorting instruction is obtained through the decision system, and the images are descended to the flat throw sorting machine to control the air gun array, so that sorting is completed.
2. The intelligent agricultural product sorting machine for deep learning and general purpose according to claim 1, wherein: the flat throwing type sorting machine comprises a material homogenizing device, a flat belt, a detection system, a collection box, a rack and a power system, wherein the material homogenizing device is arranged at the front end of the flat belt; the detection system comprises a pair of industrial linear array cameras, a light source, a background plate, an air gun array and a control module which are symmetrically distributed, the industrial linear array cameras, the light source, the background plate, the air gun array and the control module are symmetrically distributed at two ends of a parabola through which materials pass, the air gun array is arranged at the lower end of the cameras, and particularly, a pattern with plain patterns can be selected according to material properties.
3. The intelligent agricultural product sorting machine for deep learning and general purpose according to claim 1, wherein: the 5G transmission and cloud storage module consists of a 5G transmission module and a cloud storage; wherein 5G transmission module links to each other with camera, air gun control module, and the photo that the linear array camera was shot on line can be uploaded to high-end memory at a high speed through 5G transmission module, and the signal of high-end decision-making system decision-making also can be passed to air gun control module at a high speed through 5G transmission module, and then control the air gun switching to send the material of different grades into in the hierarchical collecting box of different grades.
4. The intelligent agricultural product sorting machine for deep learning and general purpose according to claim 1, wherein: the core of the deep learning algorithm decision system is a lifelong learning algorithm based on transfer learning, the algorithm firstly pre-trains a network through an ImageNet data set by adopting one of transfer learning models (Alexnet, GoogleNet and VGG), and then finely adjusts the network weight based on a batch of image data of a certain agricultural product material actually measured by a conveyor belt to obtain a sorting model which can adapt to the agricultural product, and the model can be applied to sorting the agricultural product; when another agricultural product is added for model fine adjustment, firstly, the influence of the network weight on the recognition result is measured through a cross entropy method, the weight coefficient is adjusted according to the influence, the adjustment with the large weight is small or not adjusted as much as possible, the influence is small and can be adjusted greatly, and therefore a network structure is obtained through training, and the network can be suitable for sorting of a second agricultural product and is also suitable for sorting of a first agricultural product; when increasing more agricultural product varieties, analogize in proper order because have the memory function to make the network through constantly studying, can realize the sorting of multiple agricultural product, along with the constantly increasing of agricultural product variety, combine the powerful storage capacity of cloud storage, can realize the sorting of general agricultural product.
5. The intelligent agricultural product sorting machine for deep learning and general purpose according to claim 1, wherein: the machine training and debugging stage comprises the steps of firstly dividing agricultural products to be classified into 2-3 grades through an artificial classification standard, then putting flat belts according to batches, making classification labels, controlling a linear array camera to shoot images of all the materials on line, uploading the images to a cloud end to obtain a decision model, and entering a working stage after the machine is trained; the machine testing working stage is that materials to be classified are poured into the refining device, the machine automatically classifies the materials, the camera shoots pictures on line in real time, the pictures are uploaded to the cloud decision module through the 5G transmission module, and the decision results are then transmitted to the air gun control module through the 5G transmission module so as to control the air gun to be sorted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011433911.5A CN112718548A (en) | 2020-12-10 | 2020-12-10 | General type agricultural product intelligence sorter of degree of depth study |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011433911.5A CN112718548A (en) | 2020-12-10 | 2020-12-10 | General type agricultural product intelligence sorter of degree of depth study |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112718548A true CN112718548A (en) | 2021-04-30 |
Family
ID=75598776
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011433911.5A Pending CN112718548A (en) | 2020-12-10 | 2020-12-10 | General type agricultural product intelligence sorter of degree of depth study |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112718548A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101234381A (en) * | 2008-03-07 | 2008-08-06 | 天津市华核科技有限公司 | Granular material sorting classifying method based on visual sense recognition |
| CN101439335A (en) * | 2008-12-26 | 2009-05-27 | 天津市华核科技有限公司 | Multifunctional color selection method using colorful charge coupled device |
| CN204018236U (en) * | 2014-07-10 | 2014-12-17 | 北京农业智能装备技术研究中心 | Small-sized agricultural product separation system |
| CN104646315A (en) * | 2015-03-02 | 2015-05-27 | 青岛农业大学 | Intelligent agricultural product sorting machine with aflatoxin detection function |
| CN104680177A (en) * | 2015-03-03 | 2015-06-03 | 赵天奇 | Universal type intelligent learning method and device for agricultural product detection and classification |
| CN109086826A (en) * | 2018-08-06 | 2018-12-25 | 中国农业科学院农业资源与农业区划研究所 | Wheat Drought recognition methods based on picture depth study |
| CN110245252A (en) * | 2019-06-10 | 2019-09-17 | 中国矿业大学 | Machine learning model automatic generation method based on genetic algorithm |
| CN111165176A (en) * | 2020-03-20 | 2020-05-19 | 青岛农业大学 | Tea artificial intelligence picking robot |
| CN111507379A (en) * | 2020-03-24 | 2020-08-07 | 武汉理工大学 | Ore automatic identification and rough sorting system based on deep learning |
| US20200320379A1 (en) * | 2019-04-02 | 2020-10-08 | International Business Machines Corporation | Training transfer-focused models for deep learning |
-
2020
- 2020-12-10 CN CN202011433911.5A patent/CN112718548A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101234381A (en) * | 2008-03-07 | 2008-08-06 | 天津市华核科技有限公司 | Granular material sorting classifying method based on visual sense recognition |
| CN101439335A (en) * | 2008-12-26 | 2009-05-27 | 天津市华核科技有限公司 | Multifunctional color selection method using colorful charge coupled device |
| CN204018236U (en) * | 2014-07-10 | 2014-12-17 | 北京农业智能装备技术研究中心 | Small-sized agricultural product separation system |
| CN104646315A (en) * | 2015-03-02 | 2015-05-27 | 青岛农业大学 | Intelligent agricultural product sorting machine with aflatoxin detection function |
| CN104680177A (en) * | 2015-03-03 | 2015-06-03 | 赵天奇 | Universal type intelligent learning method and device for agricultural product detection and classification |
| CN109086826A (en) * | 2018-08-06 | 2018-12-25 | 中国农业科学院农业资源与农业区划研究所 | Wheat Drought recognition methods based on picture depth study |
| US20200320379A1 (en) * | 2019-04-02 | 2020-10-08 | International Business Machines Corporation | Training transfer-focused models for deep learning |
| CN110245252A (en) * | 2019-06-10 | 2019-09-17 | 中国矿业大学 | Machine learning model automatic generation method based on genetic algorithm |
| CN111165176A (en) * | 2020-03-20 | 2020-05-19 | 青岛农业大学 | Tea artificial intelligence picking robot |
| CN111507379A (en) * | 2020-03-24 | 2020-08-07 | 武汉理工大学 | Ore automatic identification and rough sorting system based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107437094B (en) | Wood board sorting method and system based on machine learning | |
| Li et al. | Computer vision based system for apple surface defect detection | |
| CN108686978B (en) | ARM-based fruit category and color sorting method and system | |
| CN107832780B (en) | Artificial intelligence-based wood board sorting low-confidence sample processing method and system | |
| CN107486415A (en) | Thin bamboo strip defect on-line detecting system and detection method based on machine vision | |
| CN201041551Y (en) | A real time detection and classification system for pearl based on machine vision | |
| CN104034638B (en) | The diamond wire online quality detecting method of granule based on machine vision | |
| CN110348503A (en) | A kind of apple quality detection method based on convolutional neural networks | |
| CN209935300U (en) | Intelligent sorting system based on computer vision | |
| Alikhanov et al. | Design and performance of an automatic egg sorting system based on computer vision | |
| CN113838034A (en) | Candy packaging surface defect rapid detection method based on machine vision | |
| CN114778561A (en) | Tobacco shred quality tracing method and system based on machine vision | |
| CN112718549A (en) | General spherical fruit intelligence sorter of computer vision | |
| Al-Sammarraie et al. | Comparison of the effect using color sensor and pixy2 camera on the classification of pepper crop | |
| CN112718548A (en) | General type agricultural product intelligence sorter of degree of depth study | |
| Ramirez et al. | Agroindustrial plant for the classification of hass avocados in real-time with ResNet-18 architecture | |
| CN109794436A (en) | Disposable paper urine pants intelligent sorting system based on computer vision | |
| CN115953568A (en) | Intelligent mineral sorting method based on lightweight target detection framework | |
| Quan et al. | Design and testing of an on-line omnidirectional inspection and sorting system for soybean seeds | |
| CN111257339B (en) | Preserved egg crack online detection method and detection device based on machine vision | |
| CN108262164B (en) | Selection method of dried aquatic products | |
| KR20210085795A (en) | Agricultural Products Classification Apparatus Using Artificial Intelligence | |
| CN113267506A (en) | Wood board AI visual defect detection device, method, equipment and medium | |
| Alim | Identification of diseases in tomato leaves using convolutional neural network and transfer learning method | |
| Tan et al. | Detection of wrong components in patch component based on transfer learning |
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 |