CN108875845A - A kind of classifying drugs device - Google Patents
A kind of classifying drugs device Download PDFInfo
- Publication number
- CN108875845A CN108875845A CN201810834149.8A CN201810834149A CN108875845A CN 108875845 A CN108875845 A CN 108875845A CN 201810834149 A CN201810834149 A CN 201810834149A CN 108875845 A CN108875845 A CN 108875845A
- Authority
- CN
- China
- Prior art keywords
- drug
- classification
- unit
- conveyer belt
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Sorting Of Articles (AREA)
Abstract
The invention discloses a kind of classifying drugs device, including transmission unit, camera, processing unit, classification execution unit and housing unit, processing unit is connected separately camera and classification execution unit；Transmission unit is transmitted for drug to be placed on assembly line, and camera obtains drug image, and processing unit carries out identification classification according to drug image, and controls the classification execution unit correspondence and drug is pushed to the housing unit.A kind of classifying drugs device of the invention, the assembly line of drug and transmission unit road is transmitted by the way that transmission unit is arranged, full characteristic image acquisition is carried out to every drug in real time by camera, processing unit is by carrying out discriminance analysis to image, judge which classification drug belongs to, and drug is pushed to the housing unit of corresponding classification by control tactics execution unit, realize the full-automation of drug detection classification, the human error for avoiding artificial detection classification from occurring, human cost is saved, classifying drugs efficiency is helped to improve.
Description
Technical field
The present invention relates to image recognition processing field more particularly to a kind of classifying drugs devices.
Background technique
With the reform and opening-up of country, market economy is grown rapidly, at the same time, fake and inferior product phenomenon frequency
Out, as market development gradually penetrates into the every aspect of human lives.It destroys social normal market order and investment
Environment has encroached on the just rights and interests of lawful operation person and consumer, brings high risks for social development.Drug is the mankind
Indispensable a part in life, qualified drug play an important role to the sound development for ensureing the mankind.Drug detection point
The quality of class controls, and is connection drug development, produces and the sale that comes into the market, the bridge used.As it can be seen that the quality of drug with
The physical and mental health and life security of the common people, which has, to be directly affected.
Currently, whether traditional classifying drugs mode, in order to damaged incomplete to drug is examined, and classify to drug,
It must be carried out by the relevant staff of specified testing agency.Its partition test is backward in technique, almost manual operation, classification week
Phase is longer, and it is high to put into human cost.Further, since inspection-classification staff quality is irregular, largely constrain
The working efficiency of drug inspection classification.
And with the progress of image recognition processing technology, the drug inspection classification method based on image recognition already at
For a kind of relatively advanced convenient and fast drug detection technique.It uses convolutional neural networks algorithm, is based on deep learning by establishing
Drug identification model lead to by the Training of the convolutional layer of extraction feature and down-sampling layer in deep learning model
The important feature in classifier extraction drug image is crossed, realizes higher recognition accuracy.Based on this, how image recognition is utilized
Processing technique, to realize the problem of drug is classified based on the Automated inspection of assembly line, is current urgent need to resolve.
Summary of the invention
It for overcome the deficiencies in the prior art, can be automatic the purpose of the present invention is to provide a kind of classifying drugs device
Change identification classification drug.
The purpose of the present invention adopts the following technical scheme that realization：
A kind of classifying drugs device, including transmission unit, camera, processing unit, classification execution unit and housing unit,
The processing unit is connected separately the camera and the classification execution unit；The transmission unit is for setting drug
In transmitting on assembly line, the camera obtains drug image, and the processing unit carries out identification classification according to drug image, and
It controls the classification execution unit correspondence and drug is pushed into the housing unit；
The processing unit executes following method：The full characteristic image of drug taken is obtained, image grayscale figure is sought, is passed through
The outer rim position for crossing edge detection and outline border processing positioning drug, obtains drug characteristic, root by convolutional neural networks algorithm
Classification belonging to determining drug is compared according to the classifying drugs model pre-established.
Further, the transmission unit includes bed body and conveyer belt, and the conveyer belt is set to the top of the bed body, institute
It states conveyer belt and rotation is driven by rotation axis.
Further, the transmission unit further includes input port, and the input port is set to one end of the conveyer belt.
Further, the transmission unit further includes baffle, and it is described defeated that the baffle is set to docking at the top of the conveyer belt
One end at inbound port, the baffle are used to adjust the transmission route of drug.
Further, the classification execution unit is several air guns, and the air gun is arranged at intervals at the conveyer belt
The side of conveying circuit, the muzzle of the air gun is towards the conveyer belt.
Further, the air gun is additionally provided with air gun fixing seat.
Further, the housing unit includes several first storage boxes, and first storage box is arranged at intervals at institute
The other side of the conveying circuit of conveyer belt is stated, first storage box is correspondingly arranged with the air gun.
Further, the housing unit further includes the second storage box, and second storage box is correspondingly arranged in described defeated
Send the conveying circuit end of band.
Compared with prior art, the beneficial effects of the present invention are：
A kind of classifying drugs device of the invention makes the assembly line of drug and transmission unit road by the way that transmission unit is arranged
Transmission carries out full characteristic image acquisition to every drug in real time by camera, processing unit by carrying out discriminance analysis to image,
Judge which classification drug belongs to, and drug is pushed to the housing unit of corresponding classification by control tactics execution unit, realizes medicine
The full-automation of classification is surveyed in product examine, and the human error for avoiding desk checking classification from occurring saves human cost, helps to improve medicine
Product classification effectiveness.
Detailed description of the invention
Fig. 1 is to invent a kind of classifying drugs apparatus structure schematic diagram.
In figure：11, bed body；12, conveyer belt；13, rotation axis；14, input port；15, baffle；2, camera；3, it handles
Unit；41, air gun；42, air gun pedestal；51, the first storage box；52, the second storage box.
Specific embodiment
In the following, being described further in conjunction with attached drawing and specific embodiment to the present invention, it should be noted that not
Under the premise of conflicting, new implementation can be formed between various embodiments described below or between each technical characteristic in any combination
Example.
A kind of classifying drugs device as shown in Figure 1, a kind of classifying drugs device, including transmission unit, camera 2, place
Unit 3, classification execution unit and housing unit are managed, which is connected separately the camera 2 and the classification executes list
Member；The transmission unit is transmitted for drug to be placed on assembly line, which obtains drug image, 3 basis of processing unit
Drug image carries out identification classification, and controls classification execution unit correspondence and drug is pushed to the housing unit.It should be noted that
, for the assorting process of each drug, after the shooting of camera 2 and 3 analysis of processing unit processing should all be first passed through, ability
Classification execution unit is transferred to execute classification.
Specifically, which includes bed body 11 and conveyer belt 12, and conveyer belt 12 is set to the top of bed body 11, conveyer belt
12 drive rotation by rotation axis 13.Bed body 11 is mainly used for support rotation axis 13 and conveyer belt 12, provides for drug conveying flat
Steady workbench.Conveyer belt 12 provides the conveying circuit of drug, and rotation axis 13 is powered after rotation, and driving conveying belt 12 rotates, medicine
Product are put into from one end of conveyer belt 12, and the conveying circuit along conveyer belt 12 moves, and camera 2 is first passed through in moving process and shoots medicine
The full characteristic image of product, after 3 analysis of processing unit processing, control tactics execution unit executes corresponding sort operation.The transmission list
Member further includes input port 14, which is set to one end of the conveyer belt 12.Input port 14 is parallel to conveyer belt 12
And it is positioned above.It is mainly used for drug to be sorted to be transported on conveyer belt 12.Camera 2 specifically may be disposed at bed body 11
Edge close to one end of input port 14, be fixedly installed by screw, shooting area be locked in input port 14 and conveying
Region with 12 docking, facilitates processing unit 3 to obtain drug characteristic image at the first time.It should be noted that input port 14
Shape design, need meet roll drug during transportation, so that camera 2 captures comprehensive external feature.In addition,
In order to which the transmission unit further includes baffle 15, which is set at the top of the conveyer belt 12 one docked at the input port 14
End, the baffle 15 are used to adjust the transmission route of drug.Baffle 15 has smooth plate face, 15 vertical display of baffle, and plate face is formed
Transmission route and output port drug transmission route it is at an angle so that drug when baffle 15 along plate face by passing
It is defeated.Due to the corrective action of baffle 15, after baffle 15, drug can be transmitted linearly.Avoid subsequent classification execution unit
The fault of drug offset landline when pushing drug.
In addition, the classification execution unit is several air guns 41, which is arranged at intervals at the conveying of the conveyer belt 12
The side of route, the muzzle of the air gun 41 is towards the conveyer belt 12.The air gun 41 is additionally provided with air gun pedestal 42, to fix air gun
41 injection direction.The housing unit includes several first storage boxes 51, which is arranged at intervals at the conveying
The other side with 12 conveying circuit, first storage box 51 are correspondingly arranged with the air gun 41.The housing unit further includes second
Storage box 52, second storage box 52 are correspondingly arranged in the conveying circuit end of the conveyer belt 12.It should be noted that a medicine
Category does not need one air gun 41 of binding, then drug is blowed to corresponding first by the injection of air gun 41 when the similar drug passes through the air gun 41
Storage box 51.Horizontal distance based on drug Yu 41 position of air gun, processing unit 3 need to carry out drug classification and the binding of air gun 41
Initialize installation.The current location of conveyer belt 12 is dropped into as starting point A from input port 14 using drug, and drug is with conveyer belt 12
Direction conveying from conveying circuit one end to the other end, terminal is in the current location being overlapped using drug with first 41 position of air gun
B, is based on horizontal vertical distance AB, and processing unit 3 binds the drug and distance AB of the first classification.Then, with drug and
The current location that two 41 positions of air gun are overlapped is terminal C；Based on horizontal vertical distance AC, processing unit 3 is second of classification
Drug and distance AC bind.And so on, it is finished until all drug classification bindings corresponding with air gun 41.Later, locate
Unit 3 is managed based on the determination of drug generic and the binding relationship of drug classification and air gun 41, with drug from input port
14 current locations for dropping into conveyer belt 12 are starting point, when the horizontal vertical distance of drug and a certain 41 position of air gun meets binding
Relationship, processing unit 3 are powered by the above-mentioned air gun 41 of wire pair, make its injection, drug is pushed to generic first and is stored
In box 51.The quantity of air gun 41 need to be identical as the first storage box 51, and the two is correspondingly arranged at the two sides of conveyer belt 12.Air gun 41 exists
After receiving electric current, energization self electromagnetism valve completes injection, drug is pushed in generic storage box.In view of existing not
Belong to all drugs classification is arranged, so a kind of classifying drugs device of the present embodiment is additionally provided with the second storage box 52,
It is mainly used for storing non-classification drug or damaged incomplete unqualified drug, is arranged in conveying circuit end.In addition it needs
It should be noted that the processing unit 3 of the present embodiment, when to getting drug characteristic image progress identifying processing, using convolution
Neural network algorithm first seeks image grayscale figure, passes through convolutional neural networks algorithm meter after edge detection and outline border processing
Output recognition result is calculated, classification belonging to determining drug is compared according to the classifying drugs database pre-established.Its specific side
Method is as follows：
1, grayscale image is sought
In pretreatment stage, since the information content that color image includes is very big, this can seriously affect the speed of image procossing,
Therefore, we first carry out gray processing processing to image.Color image may also be referred to as RGB image, there is each pixel on image
R, this 3 components of G, B, the present embodiment distribute different power to 3 components of each pixel using weighted mean method
Value, then calculates their weighted average, formula is as follows
In formula：WR, WG, WB are respectively the weight of R, G, B, by repeatedly testing verifying, in the existing drug of hospital pharmacy
In the picture library of packaging, it has been found that in complicated image background, work as WR=0.291, when WG=0.592, WB=0.117 obtains
Be grayscale image the most reasonable.
2, edge detection and outline border processing
During transportation due to drug, in the picture accounting and position is indefinite, in order to make next processing speed
Further promotion, image recognition are more accurate, it is necessary first to position the outer rim position of drug, next processing can collect
In in the part that we need, and exclude the interference of a large amount of background image, also further mitigate identification operation burden, improve detection
Speed.Firstly, we carry out edge detection process to gained figure again, make character zone more prominent in this way after gray processing processing
It shows out.For the present embodiment using the edge detection for being based on Laplce-Gauss (LOG), it utilizes the second dervative of signal
The first derivative maximum principle of amplitude when equal to zero determines the edge of image by the zero point of the second dervative of searching image.
Using Laplce's Gauss operator when carrying out edge detection, image and Gaussian function are subjected to convolution algorithm first, obtain height
This function treated smoothed image.
H (x, y)=f (x, y) × G (x, y)
σ is Gaussian function variance, directly proportional to smoothness；Then Laplce's change is carried out to smoothed out image h (x, y)
It changes, obtains Laplce's Gauss operator edge-detected image.
3, model is constructed
Each network layer of CNN (convolutional neural networks) and the initial parameter of classifier are set, by above-mentioned by pre-processing
Drug characteristics of image of the image input CNN to be needed.Model is constituted by seven layers, and layer0 is data Layer, is that we are pre-
Image data that treated；Layer1 be definition a new convolutional layer conv1, input be layer0 output；
Layer2 is a new down-sampling layer pool1 of definition；Layer3 is a new convolutional layer conv2 of definition, input
It is the output of layer2；Layer4 is a new down-sampling layer pool2 of definition；Layer5 is full articulamentum, is above connect
The characteristic pattern that same figure in upper layer comes out through different convolution kernels is merged into one-dimensional vector, layer6 by the output of layer4
It is classification layer, error amount is finally calculated using loss function, training error is exported.We use back kick by error amount
The mode led corrects weight, achievees the purpose that trained network.According to amendment weight, model parameter is updated, to existing Hospital Drugs
Training sample image be repeated as many times and train, the currently model parameter that learns, parameter and classifier including CNN are determined with this
Parameter.Classifier is composed of 2 layers of full articulamentum series connection and SOFTMAX.After completing above-mentioned preparation, that is, it can recognize pretreatment
Target image afterwards, classifier export recognition result according to the identification model (classifying drugs database) pre-established.
Drug recognition methods based on convolutional neural networks algorithm is the prior art, is just seldom repeated here.It should be noted that
, in drug inspection assorting process, for damaged incomplete unqualified drug, processing unit 3 does not control air gun 41 and executes point
Generic operation, damaged drug directly push in the second storage box 52.
A kind of classifying drugs device of the present embodiment makes the flowing water route of drug and transmission unit by the way that transmission unit is arranged
Upper transmission carries out full characteristic image acquisition to every drug in real time by camera 2, and processing unit 3 is by identifying image
Analysis, judges which classification drug belongs to, and drug is pushed to the housing unit of corresponding classification by control tactics execution unit, real
The full-automation of existing drug detection classification, the human error for avoiding artificial detection classification from occurring save human cost, help to mention
High classifying drugs efficiency.
The above embodiment is only the preferred embodiment of the present invention, and the scope of protection of the present invention is not limited thereto,
The variation and replacement for any unsubstantiality that those skilled in the art is done on the basis of the present invention belong to institute of the present invention
Claimed range.
Claims (8)
1. a kind of classifying drugs device, it is characterised in that：Including transmission unit, camera, processing unit, classification execution unit and
Housing unit, the processing unit are connected separately the camera and the classification execution unit；The transmission unit is used
It is transmitted in drug to be placed on assembly line, the camera obtains drug image, and the processing unit is carried out according to drug image
Identification classification, and control the classification execution unit correspondence and drug is pushed into the housing unit；
The processing unit executes following method：The full characteristic image of drug taken is obtained, image grayscale figure is sought, by side
The outer rim position of edge detection and outline border processing positioning drug, obtains drug characteristic by convolutional neural networks algorithm, according to pre-
Classification belonging to determining drug is compared in the classifying drugs model first established.
2. a kind of classifying drugs device as described in claim 1, it is characterised in that：The transmission unit includes bed body and conveying
Band, the conveyer belt are set to the top of the bed body, and the conveyer belt is driven by rotation axis and rotated.
3. a kind of classifying drugs device as claimed in claim 2, it is characterised in that：The transmission unit further includes input terminal
Mouthful, the input port is set to one end of the conveyer belt.
4. a kind of classifying drugs device as claimed in claim 3, it is characterised in that：The transmission unit further includes baffle, institute
It states baffle and is set at the top of the conveyer belt one end docked at the input port, the baffle is used to adjust the transmission road of drug
Line.
5. a kind of classifying drugs device as claimed in claim 2, it is characterised in that：The classification execution unit is several gas
Rifle, the air gun are arranged at intervals at the side of the conveying circuit of the conveyer belt, and the muzzle of the air gun is towards the conveyer belt.
6. a kind of classifying drugs device as claimed in claim 5, it is characterised in that：The air gun is additionally provided with air gun and fixes
Seat.
7. a kind of classifying drugs device as claimed in claim 5, it is characterised in that：The housing unit include several first
Storage box, first storage box are arranged at intervals at the other side of the conveying circuit of the conveyer belt, first storage box with
The air gun is correspondingly arranged.
8. a kind of classifying drugs device as claimed in claim 7, it is characterised in that：The housing unit further includes the second storage
Box, second storage box are correspondingly arranged in the conveying circuit end of the conveyer belt.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810834149.8A CN108875845B (en) | 2018-07-26 | 2018-07-26 | Medicine sorting device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810834149.8A CN108875845B (en) | 2018-07-26 | 2018-07-26 | Medicine sorting device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108875845A true CN108875845A (en) | 2018-11-23 |
| CN108875845B CN108875845B (en) | 2024-02-20 |
Family
ID=64305405
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810834149.8A Active CN108875845B (en) | 2018-07-26 | 2018-07-26 | Medicine sorting device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108875845B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110665826A (en) * | 2019-08-30 | 2020-01-10 | 杭州金凯包装材料有限公司 | Medical product sorting system and sorting method thereof |
| CN110781298A (en) * | 2019-09-18 | 2020-02-11 | 平安科技（深圳）有限公司 | Medicine classification method and device, computer equipment and storage medium |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010151444A (en) * | 2008-12-23 | 2010-07-08 | Mitsubishi Electric Corp | Method and apparatus for sorting resin |
| JP2010182287A (en) * | 2008-07-17 | 2010-08-19 | Steven C Kays | Intelligent adaptive design |
| CN103551742A (en) * | 2013-10-30 | 2014-02-05 | 马志敏 | High-speed controlled-release tablet perforating machine |
| CN204134916U (en) * | 2014-08-27 | 2015-02-04 | 台虹科技股份有限公司 | sorting device |
| CN104634790A (en) * | 2015-02-09 | 2015-05-20 | 杭州乔戈里科技有限公司 | Capsule detection method and high-speed fully-automatic detection device |
| WO2015170761A1 (en) * | 2014-05-09 | 2015-11-12 | 株式会社湯山製作所 | Drug assortment device and drug assortment method |
| CN205087576U (en) * | 2014-01-07 | 2016-03-16 | 陆洪瑞 | Transmission carrier and pneumatic pipeline transmission system |
| CN105973892A (en) * | 2016-05-04 | 2016-09-28 | 成都贝森伟任科技有限责任公司 | Automatic medicine tablet packaging quality monitoring system |
| CN206184783U (en) * | 2016-09-05 | 2017-05-24 | 贵州鼎圣药业有限公司 | Can error correcting letter sorting system |
| CN107451592A (en) * | 2017-06-30 | 2017-12-08 | 广东数相智能科技有限公司 | A kind of ethical goods checking method and device |
| CN107545150A (en) * | 2017-10-13 | 2018-01-05 | 张晨 | Medicine identifying system and its recognition methods based on deep learning |
| CN108311414A (en) * | 2018-01-10 | 2018-07-24 | 陈德言 | A kind of tablet press machine tablet automatic detection device |
| CN208460038U (en) * | 2018-07-26 | 2019-02-01 | 广东数相智能科技有限公司 | A kind of classifying drugs device |
| US20210205179A1 (en) * | 2018-06-19 | 2021-07-08 | Yuyama Mfg. Co., Ltd. | Medicine sorting device |
-
2018
- 2018-07-26 CN CN201810834149.8A patent/CN108875845B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010182287A (en) * | 2008-07-17 | 2010-08-19 | Steven C Kays | Intelligent adaptive design |
| JP2010151444A (en) * | 2008-12-23 | 2010-07-08 | Mitsubishi Electric Corp | Method and apparatus for sorting resin |
| CN103551742A (en) * | 2013-10-30 | 2014-02-05 | 马志敏 | High-speed controlled-release tablet perforating machine |
| CN205087576U (en) * | 2014-01-07 | 2016-03-16 | 陆洪瑞 | Transmission carrier and pneumatic pipeline transmission system |
| WO2015170761A1 (en) * | 2014-05-09 | 2015-11-12 | 株式会社湯山製作所 | Drug assortment device and drug assortment method |
| CN204134916U (en) * | 2014-08-27 | 2015-02-04 | 台虹科技股份有限公司 | sorting device |
| CN104634790A (en) * | 2015-02-09 | 2015-05-20 | 杭州乔戈里科技有限公司 | Capsule detection method and high-speed fully-automatic detection device |
| CN105973892A (en) * | 2016-05-04 | 2016-09-28 | 成都贝森伟任科技有限责任公司 | Automatic medicine tablet packaging quality monitoring system |
| CN206184783U (en) * | 2016-09-05 | 2017-05-24 | 贵州鼎圣药业有限公司 | Can error correcting letter sorting system |
| CN107451592A (en) * | 2017-06-30 | 2017-12-08 | 广东数相智能科技有限公司 | A kind of ethical goods checking method and device |
| CN107545150A (en) * | 2017-10-13 | 2018-01-05 | 张晨 | Medicine identifying system and its recognition methods based on deep learning |
| CN108311414A (en) * | 2018-01-10 | 2018-07-24 | 陈德言 | A kind of tablet press machine tablet automatic detection device |
| US20210205179A1 (en) * | 2018-06-19 | 2021-07-08 | Yuyama Mfg. Co., Ltd. | Medicine sorting device |
| CN208460038U (en) * | 2018-07-26 | 2019-02-01 | 广东数相智能科技有限公司 | A kind of classifying drugs device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110665826A (en) * | 2019-08-30 | 2020-01-10 | 杭州金凯包装材料有限公司 | Medical product sorting system and sorting method thereof |
| CN110781298A (en) * | 2019-09-18 | 2020-02-11 | 平安科技（深圳）有限公司 | Medicine classification method and device, computer equipment and storage medium |
| CN110781298B (en) * | 2019-09-18 | 2023-06-20 | 平安科技（深圳）有限公司 | Medicine classification method, apparatus, computer device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108875845B (en) | 2024-02-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Grid-based pavement crack analysis using deep learning | |
| CN103226088B (en) | A kind of particle counting method | |
| CN105738294B (en) | The spike fruit automatic detection device and method of imaging are regarded based on monocular more | |
| CN108520274A (en) | Highly reflective surface defect detection method based on image processing and neural network classification | |
| CN110231340A (en) | Equipment, method, deep learning method and the media of strengthening workpiece optical signature | |
| CN101685006A (en) | Automatic detection system for vision of contact part feature machine | |
| CN115049879B (en) | Recognition and classification method of plant leaf disease severity and type based on convolutional Swin Transformer | |
| CN108564563A (en) | A kind of tire X-ray defect detection method based on Faster R-CNN | |
| CN108197636A (en) | A kind of paddy detection and sorting technique based on depth multiple views feature | |
| CN101441721A (en) | Device and method for counting overlapped circular particulate matter | |
| CN115078392A (en) | Semiconductor chip defect detection equipment and method | |
| CN108416775A (en) | A kind of ore grain size detection method based on deep learning | |
| CN109472774A (en) | A tongue image quality detection method based on deep learning | |
| CN108876765A (en) | The target locating set and method of industrial sorting machine people | |
| CN108875845A (en) | A kind of classifying drugs device | |
| CN115236490A (en) | Integrated circuit pin detection system | |
| CN114985275A (en) | Logistics storage automatic sorting, conveying, regulating and controlling management system based on intelligence | |
| CN115376074A (en) | Method and system for evaluating recognition effect of power transmission line monitoring device | |
| CN110201909A (en) | A kind of thread of small-sized MIM product detects separation system automatically | |
| Zhao et al. | Casting defect detection and classification of convolutional neural network based on recursive attention model | |
| Zhou et al. | Circle detection with model fitting in polar coordinates for glass bottle mouth localization | |
| CN111612662A (en) | Electric measurement experiment detection platform and method based on AR technology | |
| CN108427971A (en) | The method and system of tobacco leaf grading based on mobile terminal | |
| CN106019145A (en) | System and method for recognizing external load switches of electric energy meter | |
| CN208460038U (en) | A kind of classifying drugs device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |