CN111337496A - Chinese herbal medicine picking device and picking method - Google Patents
Chinese herbal medicine picking device and picking method Download PDFInfo
- Publication number
- CN111337496A CN111337496A CN202010284646.2A CN202010284646A CN111337496A CN 111337496 A CN111337496 A CN 111337496A CN 202010284646 A CN202010284646 A CN 202010284646A CN 111337496 A CN111337496 A CN 111337496A
- Authority
- CN
- China
- Prior art keywords
- mildewed
- medicinal materials
- image
- computer
- camera
- 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
- 238000000034 method Methods 0.000 title claims abstract description 17
- 241000411851 herbal medicine Species 0.000 title claims abstract description 13
- 239000000463 material Substances 0.000 claims abstract description 64
- 238000007599 discharging Methods 0.000 claims abstract description 10
- 239000003814 drug Substances 0.000 claims description 12
- 238000004519 manufacturing process Methods 0.000 claims description 9
- 238000002372 labelling Methods 0.000 claims description 8
- 229920000728 polyester Polymers 0.000 claims description 3
- 240000007651 Rubus glaucus Species 0.000 claims description 2
- 235000011034 Rubus glaucus Nutrition 0.000 claims description 2
- 235000009122 Rubus idaeus Nutrition 0.000 claims description 2
- 230000000007 visual effect Effects 0.000 abstract description 2
- 238000012216 screening Methods 0.000 abstract 2
- 238000005516 engineering process Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 238000009394 selective breeding Methods 0.000 description 1
Images
Classifications
-
- 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
-
- 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
- B07C5/3422—Sorting according to other particular properties according to optical properties, e.g. colour using video scanning devices, e.g. TV-cameras
-
- 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
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Medical Preparation Storing Or Oral Administration Devices (AREA)
Abstract
A Chinese herbal medicine picking device and a picking method belong to the technical field of visual identification and aim to solve the problems that the traditional Chinese herbal medicines are manually selected, the existing efficiency is low, the mildewed medicinal materials are not easy to identify, and screening leakage and wrong screening are not easy to realize. The invention discloses a Chinese medicinal material picking device which comprises a manipulator, a camera, a controller, a support, a computer and a material outlet box, wherein the material outlet box and the camera are arranged on the support, the camera is connected with a USB port on a computer host through a data cable, a network port on the computer host is connected with a network port of the controller through a network cable, and a signal output end of the controller is connected with a signal input end of the manipulator through a cable. According to the invention, the images are collected, the mildewed medicinal materials are identified through a computer to obtain the centroid coordinates of the mildewed Chinese medicinal materials, and then the mildewed Chinese medicinal materials are grabbed and placed into the discharging box by the manipulator with the centroid coordinate input to realize the identification and selection of the mildewed Chinese medicinal materials.
Description
Technical Field
The invention particularly relates to a Chinese medicinal material picking device and a picking method, and belongs to the technical field of Chinese medicinal material identification.
Background
The Chinese medicinal material picking technology is a Chinese medicinal material pretreatment technology, and is a technology for evaluating whether medicinal materials meet standards or not and picking out medicinal materials which do not meet the production standards (mildew, damage and the like) before the medicinal materials are formally produced and processed. This technique adopts the manual work at present, goes to judge with the naked eye whether this medicinal material accords with the production standard, picks out the mode that does not accord with the production standard through the manual follow of operative employee in waiting to process the medicinal material and realizes, has following problem:
1. manual picking requires human eyes to discriminate whether the medicinal materials are damaged, mildewed, unqualified in size and the like, and manual picking is required in the discrimination process, so that a large amount of time and energy are consumed;
2. the artificial selection has subjectivity, whether the medicinal materials meet the standard or not does not have strict standard, and the judgment is subjective, so that the conditions of missed judgment and misjudgment exist, and the hidden danger of medication safety exists.
Disclosure of Invention
In order to solve the above problems, the present invention provides a device and a method for picking Chinese herbal medicines.
The technical scheme adopted by the invention for solving the technical problems is as follows:
the first scheme is as follows: the utility model provides a device is selected to chinese-medicinal material includes manipulator, camera, controller, support, computer and goes out the magazine, is provided with out magazine and camera on the support, and the camera passes through the data cable to be connected with the USB port on the host computer, and the network port on the host computer passes through the net twine to be connected with the network port of controller, and controller signal output part passes through the cable with the signal input port of manipulator and is connected.
Scheme II: a Chinese medicinal material selection method comprises the following steps:
firstly, image acquisition is carried out by utilizing a camera: photographing a single medicinal material, simulating an actual production environment, and photographing a plurality of medicinal materials to obtain a plurality of images;
secondly, labeling the moldy Chinese medicinal material image by using labelme open source software in a computer;
inputting the marked images into a Cascade Mask-RCNN network architecture in a computer for training and learning so as to identify moldy Chinese medicinal material images;
fourthly, photographing the medicinal materials in production, detecting and segmenting mildewed Chinese medicinal materials on the images through a Cascade Mask-RCNN model, and calculating mass center coordinates of the mildewed Chinese medicinal materials;
fifthly, the generated centroid coordinates are input into a control plate of the manipulator through a controller to grab the mildewed traditional Chinese medicinal materials.
Further, the method for labeling the moldy Chinese medicinal material image by using labelme open source software in the second step comprises the following steps:
a1, transmitting a plurality of images into a computer through a camera, opening labelme open source software, clicking an OpenDir button, selecting a folder where the image to be marked is located, and loading all the images;
a2, clicking a button of 'Create polyesters' to label the image along the edge of the Chinese herbal medicine;
a3, after the current Image is labeled, clicking a Next Image button, entering a Next Image interface and generating a corresponding json file, wherein the json file stores the corresponding information of the label until the last Image is labeled, and the labeling of the Image is finished.
Further, the centroid coordinates in step four are obtained by:
b1, detecting the mildewed traditional Chinese medicine on the segmented image through a Cascade Mask-RCNN network architecture model, and obtaining coordinates of midpoint pixels of a mildew traditional Chinese medicine Mask classmask, coordinates (x1, y1) of opposite corners of a mildew traditional Chinese medicine surrounding frame and coordinates (x2, y2) through the Cascade Mask-RCNN model;
b2, calculating the centroid coordinate (cx, cy) of the mildewed traditional Chinese medicinal material by the following centroid coordinate formula:
cx＝M10/M00；
cy＝M01/M00；
m00, M10 and M00 are parameter variables, and the values of M00, M10 and M00 can be calculated by the following formula:
wherein i, j is an independent variable x, y represents the abscissa and ordinate of the dot pixel in the mask classmask,
when i is 0 and j is 1, substituting the abscissa and the ordinate of the point pixel in the mask classmask into the formula to obtain the value of M10; when i is 1 and j is 0, the value of M01 is calculated in the same way; when i is 0 and j is 0, the value of M00 is calculated in the same way;
and finally substituting M00, M10 and M00 into a mass center coordinate formula to obtain the mass center coordinates (cx, cy) of the mildewed traditional Chinese medicinal materials.
Compared with the prior art, the invention has the following beneficial effects:
according to the method, the images are collected, the mildewed medicinal materials are identified through the computer, so that the centroid coordinates of the mildewed Chinese medicinal materials are obtained, the mildewed Chinese medicinal materials are grabbed by the manipulator with the centroid coordinate input and placed into the discharging box, and identification and selection of the mildewed Chinese medicinal materials are achieved.
Drawings
FIG. 1 is an isometric view of the present invention;
FIG. 2 is a front view of the present invention;
fig. 3 is a diagram of the connection relationship among the camera 2, the manipulator 1, the controller 3, and the computer 5.
Detailed Description
The invention will be described in further detail below with reference to the accompanying drawings: the present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation is given, but the scope of the present invention is not limited to the following embodiments.
Example 1: as shown in fig. 1-3, the device is selected to chinese-medicinal material of this embodiment, including manipulator 1, camera 2, controller 3, support 4, computer 5 and ejection of compact box 6, be provided with ejection of compact box 6 and camera 2 on support 4, camera 2 is connected with the USB port on the computer 5 host computer through the data cable, and the network port on the computer 5 host computer passes through the net twine and is connected with the network port of controller 3, and controller 3 signal output part passes through the cable with the signal input port of manipulator 1 and is connected.
Specifically, the controller 3 is a raspberry group control main board, the material discharging box 6 is an L-shaped shell, a feeding hole 6-1 is formed in the top of the L-shaped shell, a discharging hole 6-2 is formed in the bottom of one side of the L-shaped shell, and the discharging hole 6-2 is connected with the feeding hole 6-1 through an inclined plate 7.
Example 2: the embodiment of the invention provides a Chinese herbal medicine selecting method, which comprises the following steps:
firstly, image acquisition is carried out by using a camera 2: the method comprises the steps of taking a picture of a single medicinal material, simulating an actual production environment, taking pictures of a plurality of medicinal materials to obtain a plurality of images, placing the single medicinal material and the plurality of medicinal materials on A4 paper before taking the pictures, and taking the pictures through a high-definition camera, wherein the total number of the taken pictures is 30000;
secondly, labeling the moldy Chinese medicinal material image by using labelme open source software in the computer 5:
a1, transmitting a plurality of images into a computer 5 through a camera 2, then opening labelme open source software, clicking an OpenDir button, selecting a folder where the image to be marked is located, and loading all the images;
a2, clicking a button of 'Create polyesters' to label the image along the edge of the Chinese herbal medicine;
a3, after the current Image is labeled, clicking a Next Image button, entering a Next Image interface and generating a corresponding json file, wherein the json file stores the corresponding information of the label until the last Image is labeled, and the labeling of the Image is finished;
inputting the marked images into a Cascade Mask-RCNN network architecture in a computer 5 to train and generate a segmentation model so as to identify mildewed traditional Chinese medicine images;
fourthly, photographing the medicinal materials in production, detecting and segmenting moldy Chinese medicinal materials on the images through a Cascade Mask-RCNN model, solving mass center coordinates of the moldy Chinese medicinal materials, and obtaining the mass center coordinates of the moldy Chinese medicinal materials through the following steps:
b1, detecting the mildewed traditional Chinese medicine on the segmented image through a Cascade Mask-RCNN network architecture model, and obtaining coordinates of midpoint pixels of a mildew traditional Chinese medicine Mask classmask, coordinates (x1, y1) of opposite corners of a mildew traditional Chinese medicine surrounding frame and coordinates (x2, y2) through the Cascade Mask-RCNN model;
b2, calculating the centroid coordinate (cx, cy) of the mildewed traditional Chinese medicinal material by the following centroid coordinate formula:
cx＝M10/M00；
cy＝M01/M00；
m00, M10 and M00 are parameter variables, and the values of M00, M10 and M00 can be calculated by the following formula:
wherein i, j is an independent variable x, y represents the abscissa and ordinate of the dot pixel in the mask classmask,
when i is 0 and j is 1, substituting the abscissa and the ordinate of the point pixel in the mask classmask into the formula to obtain the value of M10; when i is 1 and j is 0, the value of M01 is calculated in the same way; when i is 0 and j is 0, the value of M00 is calculated in the same way;
finally substituting M00, M10 and M00 into a mass center coordinate formula to obtain a mass center coordinate (cx, cy) of the mildewed traditional Chinese medicinal material;
fifthly, the generated centroid coordinates are input into a control plate of the manipulator 1 through the controller 3 to grab the mildewed traditional Chinese medicinal materials.
In the embodiment, coordinates are obtained by shooting with a camera and are transmitted to a manipulator, which belongs to the prior art, and refer to a patent with publication number CN105066984A, "a visual positioning method and system", in which a centroid coordinate is equivalent to a workpiece coordinate recorded in the patent.
The training of images in step three of the embodiment in the Cascade Mask-RCNN network architecture belongs to the prior art.
Claims (6)
1. The utility model provides a device is selected to chinese-medicinal material which characterized in that: the mechanical arm comprises a mechanical arm (1), a camera (2), a controller (3), a support (4), a computer (5) and a discharging box (6), wherein the discharging box (6) and the camera (2) are arranged on the support (4), the camera (2) is connected with a USB port on a host of the computer (5) through a data cable, a network port on the host of the computer (5) is connected with a network port of the controller (3) through a network cable, and a signal output end of the controller (3) is connected with a signal input port of the mechanical arm (1) through a cable.
2. The device for selecting Chinese herbal medicines according to claim 1, characterized in that: the controller (3) is a raspberry pi control mainboard.
3. The device for selecting Chinese herbal medicines according to claim 1, characterized in that: the discharging box (6) is an L-shaped shell, a feeding hole (6-1) is formed in the top of the L-shaped shell, a discharging hole (6-2) is formed in the bottom of one side of the L-shaped shell, and the discharging hole (6-2) is connected with the feeding hole (6-1) through an inclined plate 7.
4. A method for selecting a chinese herb based on the apparatus for selecting a chinese herb according to any one of claims 1 to 3, comprising: it comprises the following steps:
image acquisition by means of a camera (2): photographing a single medicinal material, simulating an actual production environment, mixing mildewed and normal medicinal materials together, and photographing for multiple times to obtain multiple images;
secondly, labeling the moldy Chinese medicinal material image by using labelme open source software in the computer (5);
inputting the marked images into a Cascade Mask-RCNN network architecture in a computer (5) for training and learning so as to identify moldy Chinese medicinal material images;
fourthly, photographing the medicinal materials in production, detecting and segmenting mildewed Chinese medicinal materials on the images through a Cascade Mask-RCNN model, and calculating mass center coordinates of the mildewed Chinese medicinal materials;
fifthly, the generated centroid coordinates are input into a control plate of the manipulator (1) through the controller (3) to grab the mildewed traditional Chinese medicinal materials.
5. The method for selecting Chinese herbal medicines according to claim 4, characterized in that: in the second step, the method for labeling the mildewed traditional Chinese medicine material image by using labelme open source software comprises the following steps:
a1, transmitting a plurality of images into a computer (5) through a camera (2), then opening labelme open source software, clicking an OpenDir button, selecting a folder where the images to be labeled are located, and loading all the images;
a2, clicking a button of 'Create polyesters' to label the image along the edge of the Chinese herbal medicine;
a3, after the current Image is labeled, clicking a Next Image button, entering a Next Image interface and generating a corresponding json file, wherein the json file stores the corresponding information of the label until the last Image is labeled, and the labeling of the Image is finished.
6. The method for selecting Chinese herbal medicines according to claim 4, characterized in that: the centroid coordinates in step four are obtained by:
b1, detecting the mildewed traditional Chinese medicine on the segmented image through a Cascade Mask-RCNN network architecture model, and obtaining coordinates of midpoint pixels of a mildew traditional Chinese medicine Mask classmask, coordinates (x1, y1) of opposite corners of a mildew traditional Chinese medicine surrounding frame and coordinates (x2, y2) through the Cascade Mask-RCNN model;
b2, and the centroid coordinate (cx, cy) of the traditional Chinese medicinal material can be calculated by the following centroid coordinate formula:
cx＝M10/M00；
cy＝M01/M00；
m00, M10 and M00 are parameter variables, and the values of M00, M10 and M00 can be calculated by the following formula:
wherein i, j is an independent variable x, y represents the abscissa and ordinate of the dot pixel in the mask classmask,
when i is 0 and j is 1, substituting the abscissa and the ordinate of the point pixel in the mask classmask into the formula to obtain the value of M10; when i is 1 and j is 0, the value of M01 is calculated in the same way; when i is 0 and j is 0, the value of M00 is calculated in the same way;
and finally substituting M00, M10 and M00 into a mass center coordinate formula to obtain the mass center coordinates (cx, cy) of the mildewed traditional Chinese medicinal materials.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010284646.2A CN111337496A (en) | 2020-04-13 | 2020-04-13 | Chinese herbal medicine picking device and picking method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010284646.2A CN111337496A (en) | 2020-04-13 | 2020-04-13 | Chinese herbal medicine picking device and picking method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111337496A true CN111337496A (en) | 2020-06-26 |
Family
ID=71182807
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010284646.2A Pending CN111337496A (en) | 2020-04-13 | 2020-04-13 | Chinese herbal medicine picking device and picking method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111337496A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111985416A (en) * | 2020-08-24 | 2020-11-24 | 国网河北省电力有限公司 | Construction safety isolation facility compliance monitoring method based on image recognition |
| CN113731836A (en) * | 2021-08-04 | 2021-12-03 | 华侨大学 | Urban solid waste online sorting system based on deep learning |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104588325A (en) * | 2014-12-25 | 2015-05-06 | 安徽华润金蟾药业股份有限公司 | Automatic picking device and method for traditional Chinese medicine formula particle medicinal material |
| CN106023224A (en) * | 2016-05-30 | 2016-10-12 | 天水师范学院 | PCNN automatic segmentation method for microscopic image of traditional Chinese medicine |
| CN106204560A (en) * | 2016-07-02 | 2016-12-07 | 上海大学 | Colony picker automatic calibration method |
| CN106874914A (en) * | 2017-01-12 | 2017-06-20 | 华南理工大学 | A kind of industrial machinery arm visual spatial attention method based on depth convolutional neural networks |
| CN108171748A (en) * | 2018-01-23 | 2018-06-15 | 哈工大机器人（合肥）国际创新研究院 | A kind of visual identity of object manipulator intelligent grabbing application and localization method |
| CN108229665A (en) * | 2018-02-02 | 2018-06-29 | 上海建桥学院 | A kind of the System of Sorting Components based on the convolutional neural networks by depth |
| CN109615010A (en) * | 2018-12-13 | 2019-04-12 | 济南大学 | Chinese traditional medicinal materials recognition method and system based on double scale convolutional neural networks |
| CN110246124A (en) * | 2019-05-24 | 2019-09-17 | 西安交通大学 | Target size measurement method and system based on deep learning |
| CN110302981A (en) * | 2019-06-17 | 2019-10-08 | 华侨大学 | A kind of solid waste sorts online grasping means and system |
| CN110634131A (en) * | 2019-08-29 | 2019-12-31 | 南京理工大学 | Crack image identification and modeling method |
| CN110648364A (en) * | 2019-09-17 | 2020-01-03 | 华侨大学 | Multi-dimensional space solid waste visual detection positioning and identification method and system |
| CN212255094U (en) * | 2020-04-13 | 2020-12-29 | 黑龙江北草堂中药材有限责任公司 | Chinese-medicinal material picking device |
-
2020
- 2020-04-13 CN CN202010284646.2A patent/CN111337496A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104588325A (en) * | 2014-12-25 | 2015-05-06 | 安徽华润金蟾药业股份有限公司 | Automatic picking device and method for traditional Chinese medicine formula particle medicinal material |
| CN106023224A (en) * | 2016-05-30 | 2016-10-12 | 天水师范学院 | PCNN automatic segmentation method for microscopic image of traditional Chinese medicine |
| CN106204560A (en) * | 2016-07-02 | 2016-12-07 | 上海大学 | Colony picker automatic calibration method |
| CN106874914A (en) * | 2017-01-12 | 2017-06-20 | 华南理工大学 | A kind of industrial machinery arm visual spatial attention method based on depth convolutional neural networks |
| CN108171748A (en) * | 2018-01-23 | 2018-06-15 | 哈工大机器人（合肥）国际创新研究院 | A kind of visual identity of object manipulator intelligent grabbing application and localization method |
| CN108229665A (en) * | 2018-02-02 | 2018-06-29 | 上海建桥学院 | A kind of the System of Sorting Components based on the convolutional neural networks by depth |
| CN109615010A (en) * | 2018-12-13 | 2019-04-12 | 济南大学 | Chinese traditional medicinal materials recognition method and system based on double scale convolutional neural networks |
| CN110246124A (en) * | 2019-05-24 | 2019-09-17 | 西安交通大学 | Target size measurement method and system based on deep learning |
| CN110302981A (en) * | 2019-06-17 | 2019-10-08 | 华侨大学 | A kind of solid waste sorts online grasping means and system |
| CN110634131A (en) * | 2019-08-29 | 2019-12-31 | 南京理工大学 | Crack image identification and modeling method |
| CN110648364A (en) * | 2019-09-17 | 2020-01-03 | 华侨大学 | Multi-dimensional space solid waste visual detection positioning and identification method and system |
| CN212255094U (en) * | 2020-04-13 | 2020-12-29 | 黑龙江北草堂中药材有限责任公司 | Chinese-medicinal material picking device |
Non-Patent Citations (3)
| Title |
|---|
| 刘振宇;李中生;冯柏润;郭名坤;赵雪;: "机器视觉在工业生产线上的应用实现", 微型机与应用, no. 17, 10 September 2013 (2013-09-10) * |
| 郑健红;鲍官军;张立彬;荀一;陈教料;: "结合深度学习与支持向量机的金属零件识别", 中国图象图形学报, no. 12, 16 December 2019 (2019-12-16) * |
| 陈茜: "非结构化环境中的对象识别与机器人抓取研究", 中国优秀硕士学位论文全文数据库工程科技辑, no. 2020, 15 January 2020 (2020-01-15), pages 2 - 1 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111985416A (en) * | 2020-08-24 | 2020-11-24 | 国网河北省电力有限公司 | Construction safety isolation facility compliance monitoring method based on image recognition |
| CN113731836A (en) * | 2021-08-04 | 2021-12-03 | 华侨大学 | Urban solid waste online sorting system based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110726735A (en) | Full-automatic circuit board defect detection system and method based on deep learning | |
| CN111337496A (en) | Chinese herbal medicine picking device and picking method | |
| CN108121996A (en) | A kind of hard pressing plate state identification method of power screen cabinet based on machine vision | |
| CN107483917A (en) | The method of display screen bad point on-line measuring device and display screen bad point on-line checking | |
| CN109949266A (en) | The system and method for spot in display for identification | |
| CN108960067A (en) | Real-time train driver motion recognition system and method based on deep learning | |
| JPH01270177A (en) | Cellular picture segmenting and storing processor and method | |
| CN110570422B (en) | Capsule defect visual detection method based on matrix analysis | |
| CN212255094U (en) | Chinese-medicinal material picking device | |
| CN109919007A (en) | A method of generating infrared image markup information | |
| CN109932370A (en) | Utilize the improved pretreated system and method for white stigma detection | |
| CN209476729U (en) | Express delivery end-o f-pipe -control device based on image recognition and inkjet printing | |
| CN108182682A (en) | A kind of detection method based on Computer Image Processing and pattern-recognition | |
| CN203803804U (en) | Rapid identification card sorting instrument | |
| CN112200058A (en) | System and method for intelligently correcting auxiliary data | |
| CN110838086A (en) | Outdoor image splicing method based on correlation template matching | |
| CN110956147A (en) | Method and device for generating training data | |
| TW202331655A (en) | Label integrity self-adaptive detection method and system | |
| WO2024067006A1 (en) | Disordered wire sorting method, apparatus, and system | |
| CN113996545A (en) | Quick sorting production line for main roots of panax notoginseng based on computer vision | |
| CN111353432B (en) | Rapid clean selection method and system for honeysuckle medicinal materials based on convolutional neural network | |
| CN102023163B (en) | System and method for detecting connector based on digital signal processor (DSP) | |
| CN112116037A (en) | AI image recognition and scoring system of intelligent garbage can | |
| CN113420839B (en) | Semi-automatic labeling method and segmentation positioning system for stacking planar target objects | |
| CN112288819B (en) | Multi-source data fusion vision-guided robot grabbing and classifying system and 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 |