CN111695578A - Multi-feature fusion artificial intelligent medicine package image recognition system - Google Patents
Multi-feature fusion artificial intelligent medicine package image recognition system Download PDFInfo
- Publication number
- CN111695578A CN111695578A CN201910171449.7A CN201910171449A CN111695578A CN 111695578 A CN111695578 A CN 111695578A CN 201910171449 A CN201910171449 A CN 201910171449A CN 111695578 A CN111695578 A CN 111695578A
- Authority
- CN
- China
- Prior art keywords
- medicine
- image
- database
- image collector
- extracting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
- G06K7/1404—Methods for optical code recognition
- G06K7/1408—Methods for optical code recognition the method being specifically adapted for the type of code
- G06K7/1417—2D bar codes
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Electromagnetism (AREA)
- General Health & Medical Sciences (AREA)
- Toxicology (AREA)
- Medical Preparation Storing Or Oral Administration Devices (AREA)
Abstract
The invention discloses a multi-feature integrated artificial intelligent medicine package image recognition system, which comprises a database, a database and a database, wherein the database is used for storing all medicine package samples, medicine bar codes and medicine detailed information in a medicine dispenser; the PC end controller is used for controlling and starting the image collector and instructing the image collector to collect photographed images of the medicine packages, and extracting corresponding data from the database according to the collected data to perform comparison matching identification; according to the invention, through the cooperation of the bottom conveyor tail end sensor and the PC end controller, the command image collector is started to carry out photographing image collection on the medicine package, and the medicine bar code and the medicine package characteristic information are extracted; the PC-end controller extracts corresponding data from the database according to the acquired data to perform comparison, matching and identification, and outputs a corresponding control command based on a matching and identification result, so that unmanned intelligent audit on the dispensing of prescription drugs dispensed by the automatic dispensing machine is realized.
Description
Technical Field
The invention belongs to the technical field of automatic medicine taking terminals, and particularly relates to an artificial intelligent medicine package image recognition system with multi-feature fusion.
Background
At the current medicine taking window of a hospital, the matched prescription is still subject to manual examination. In order to further change a pharmaceutical service mode, improve the pharmaceutical service level and meet the increasing medical health and health needs of the people, along with the gradual improvement of a novel modern medical mode, self-help medicine taking is an important measure for facilitating people in the future, but the technical barrier faced by self-help medicine taking is how to realize unmanned intelligent audit on the prescription prepared by an automatic medicine dispensing machine.
Disclosure of Invention
The invention aims to provide a multi-feature fusion artificial intelligent medicine package image recognition system.
The technique and method adopted by the present invention to solve the above problems are as follows:
a multi-feature fused artificial intelligent medicine package image recognition system comprises
The database is used for storing all medicine packaging samples, medicine bar codes and medicine detailed information in the dispensing machine;
the bottom conveyor tail end sensor is used for conveying the dispensed medicines to the medicine outlet end, and detecting sensed medicine induction information through the tail end sensor and sending the detected medicine induction information to the PC end controller;
the PC end controller is used for controlling and starting the image collector and instructing the image collector to collect photographed images of the medicine packages, extracting corresponding data from the database according to the collected data to perform comparison matching identification, and outputting corresponding control commands based on matching identification results;
the image collector is used for collecting photographed images of the medicine packages, extracting the medicine bar codes and extracting the characteristic information of the medicine packages according to the collected image information; and the extracted corresponding information is transmitted to the PC end controller;
extracting medicine packaging characteristics, and extracting corresponding data of a color correlation diagram, a color moment, an outline size, characters and a color aggregation vector of the medicine by adopting a multi-characteristic fusion algorithm.
Further, the image recognition system operates as follows:
s1, when the automatic medicine dispensing machine dispenses the prescription medicine and the medicine passes through the tail end sensor of the bottom conveyor, the medicine sensing information sensed by the tail end sensor is sent to the PC end control machine, and the PC end control machine starts and instructs the image collector to take a picture of the medicine package to collect an image;
s2, firstly, extracting the drug bar code according to the image acquired by photographing by the image acquisition device, transmitting the extracted drug bar code data to the PC-end control machine, calling the drug bar code information stored in the database by the PC-end control machine to perform matching algorithm comparison, and if the comparison is consistent, successfully identifying the drug bar code and dispensing the drug; if the comparison is inconsistent, the identification fails, and the medicine is recovered;
s3, if no bar code exists on the medicine package, the image collector extracts medicine package characteristics according to the image collected by photographing, and extracts corresponding data of a color correlation diagram, a color moment, an outline size, characters and a color aggregation vector of the medicine by adopting a multi-characteristic fusion algorithm;
the image collector transmits corresponding data for extracting the medicine packaging characteristics to the PC-end controller, the PC-end controller calls the medicine packaging samples and the medicine detailed information stored in the database, image matching algorithm comparison is carried out one by one, weight analysis is carried out, and if the weight exceeds 80, the identification is correct, and the medicine is dispensed; if the weight does not exceed 80, the identification error is determined, and the medicine is recovered.
Further, the image collector adopts an industrial matrix camera.
Further, the bottom conveyor tail end sensor and the image collector are installed at the bottom in the automatic medicine dispensing machine, and the image collector is installed above the bottom conveyor tail end sensor.
According to the invention, through the cooperation of the bottom conveyor tail end sensor and the PC end controller, the command image collector is started to carry out photographing image collection on the medicine package, and the medicine bar code and the medicine package characteristic information are extracted; the PC-end controller extracts corresponding data from the database according to the acquired data to perform comparison, matching and identification, and outputs a corresponding control command based on a matching and identification result, so that unmanned intelligent audit on the dispensing of prescription drugs dispensed by the automatic dispensing machine is realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts;
fig. 1 is a block diagram of the design structure of the present invention.
FIG. 2 is a schematic flow chart of example 1 of the present invention;
fig. 3 is a schematic flow chart of embodiment 2 of the present invention.
Detailed Description
The following detailed description of the preferred embodiments of the present invention, taken in conjunction with the accompanying drawings, will make the advantages and features of the invention easier to understand by those skilled in the art, and thus will make the scope of the invention more clearly and unequivocally defined;
as shown in FIG. 1, the multi-feature fusion artificial intelligence drug package image recognition system comprises
The database is used for storing all medicine packaging samples, medicine bar codes and medicine detailed information in the dispensing machine;
the bottom conveyor tail end sensor is used for conveying the dispensed medicines to the medicine outlet end, and detecting sensed medicine induction information through the tail end sensor and sending the detected medicine induction information to the PC end controller;
the PC end controller is used for controlling and starting the image collector and instructing the image collector to collect photographed images of the medicine packages, extracting corresponding data from the database according to the collected data to perform comparison matching identification, and outputting corresponding control commands based on matching identification results;
the image collector is used for collecting photographed images of the medicine packages, extracting the medicine bar codes and extracting the characteristic information of the medicine packages according to the collected image information; and the extracted corresponding information is transmitted to the PC end controller;
extracting medicine packaging characteristics, and extracting corresponding data of a color correlation diagram, a color moment, an outline size, characters and a color aggregation vector of the medicine by adopting a multi-characteristic fusion algorithm.
Example 1:
as shown in fig. 2, a multi-feature fused artificial intelligence drug package image recognition system, the image recognition system operating steps are as follows:
s1, when the automatic medicine dispensing machine dispenses the prescription medicine and the medicine passes through the tail end sensor of the bottom conveyor, the medicine sensing information sensed by the tail end sensor is sent to the PC end control machine, and the PC end control machine starts and instructs the image collector to take a picture of the medicine package to collect an image;
s2, firstly, extracting the drug bar code according to the image acquired by photographing by the image acquisition device, transmitting the extracted drug bar code data to the PC-end control machine, calling the drug bar code information stored in the database by the PC-end control machine to perform matching algorithm comparison, and if the comparison is consistent, successfully identifying the drug bar code and dispensing the drug; and (5) comparing the obtained results to obtain inconsistent results, failing to identify the results, and recycling the medicines.
Example 2:
as shown in fig. 3, the image recognition system for multi-feature fused artificial intelligence drug package comprises the following operation steps:
s1, when the automatic medicine dispensing machine dispenses the prescription medicine and the medicine passes through the tail end sensor of the bottom conveyor, the medicine sensing information sensed by the tail end sensor is sent to the PC end control machine, and the PC end control machine starts and instructs the image collector to take a picture of the medicine package to collect an image;
s2, if no bar code exists on the medicine package, the image collector extracts medicine package characteristics according to the image collected by photographing, and extracts corresponding data of a color correlation diagram, a color moment, an outline size, characters and a color aggregation vector of the medicine by adopting a multi-characteristic fusion algorithm;
the image collector transmits corresponding data for extracting the medicine packaging characteristics to the PC-end controller, the PC-end controller calls the medicine packaging samples and the medicine detailed information stored in the database, image matching algorithm comparison is carried out one by one, weight analysis is carried out, and if the weight exceeds 80, the identification is correct, and the medicine is dispensed; if the weight does not exceed 80, the identification error is determined, and the medicine is recovered.
The image collector adopts an industrial matrix camera.
The automatic medicine dispensing machine is characterized in that the bottom conveyor tail end sensor and the image collector are arranged at the bottom in the automatic medicine dispensing machine, and the image collector is arranged above the bottom conveyor tail end sensor.
According to the invention, through the cooperation of the bottom conveyor tail end sensor and the PC end controller, the command image collector is started to carry out photographing image collection on the medicine package, and the medicine bar code and the medicine package characteristic information are extracted; the PC-end controller extracts corresponding data from the database according to the acquired data to perform comparison, matching and identification, and outputs a corresponding control command based on a matching and identification result, so that unmanned intelligent audit on the dispensing of prescription drugs dispensed by the automatic dispensing machine is realized.
The above description is only for the specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto, and any changes or substitutions that are not thought of by the inventive labor should be covered within the protection scope of the present invention, and therefore, the protection scope of the present invention should be subject to the protection scope defined by the claims.
Claims (4)
1. A multi-feature fusion artificial intelligent medicine package image recognition system is characterized by comprising
The database is used for storing all medicine packaging samples, medicine bar codes and medicine detailed information in the dispensing machine;
the bottom conveyor tail end sensor is used for conveying the dispensed medicines to the medicine outlet end, and detecting sensed medicine induction information through the tail end sensor and sending the detected medicine induction information to the PC end controller;
the PC end controller is used for controlling and starting the image collector and instructing the image collector to collect photographed images of the medicine packages, extracting corresponding data from the database according to the collected data to perform comparison matching identification, and outputting corresponding control commands based on matching identification results;
the image collector is used for collecting photographed images of the medicine packages, extracting the medicine bar codes and extracting the characteristic information of the medicine packages according to the collected image information; and the extracted corresponding information is transmitted to the PC end controller;
extracting medicine packaging characteristics, and extracting corresponding data of a color correlation diagram, a color moment, an outline size, characters and a color aggregation vector of the medicine by adopting a multi-characteristic fusion algorithm.
2. The multi-feature fused artificial intelligence pharmaceutical packaging image recognition system of claim 1, wherein: the image recognition system comprises the following operation steps:
s1, when the automatic medicine dispensing machine dispenses the prescription medicine and the medicine passes through the tail end sensor of the bottom conveyor, the medicine sensing information sensed by the tail end sensor is sent to the PC end control machine, and the PC end control machine starts and instructs the image collector to take a picture of the medicine package to collect an image;
s2, firstly, extracting the drug bar code according to the image acquired by photographing by the image acquisition device, transmitting the extracted drug bar code data to the PC-end control machine, calling the drug bar code information stored in the database by the PC-end control machine to perform matching algorithm comparison, and if the comparison is consistent, successfully identifying the drug bar code and dispensing the drug; if the comparison is inconsistent, the identification fails, and the medicine is recovered;
s3, if no bar code exists on the medicine package, the image collector extracts medicine package characteristics according to the image collected by photographing, and extracts corresponding data of a color correlation diagram, a color moment, an outline size, characters and a color aggregation vector of the medicine by adopting a multi-characteristic fusion algorithm;
the image collector transmits corresponding data for extracting the medicine packaging characteristics to the PC-end controller, the PC-end controller calls the medicine packaging samples and the medicine detailed information stored in the database, image matching algorithm comparison is carried out one by one, weight analysis is carried out, and if the weight exceeds 80, the identification is correct, and the medicine is dispensed; if the weight does not exceed 80, the identification error is determined, and the medicine is recovered.
3. The multi-feature fused artificial intelligence pharmaceutical packaging image recognition system of claim 1, wherein: the image collector adopts an industrial matrix camera.
4. The multi-feature fused artificial intelligence pharmaceutical packaging image recognition system of claim 1, wherein: the automatic medicine dispensing machine is characterized in that the bottom conveyor tail end sensor and the image collector are arranged at the bottom in the automatic medicine dispensing machine, and the image collector is arranged above the bottom conveyor tail end sensor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910171449.7A CN111695578A (en) | 2019-03-12 | 2019-03-12 | Multi-feature fusion artificial intelligent medicine package image recognition system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910171449.7A CN111695578A (en) | 2019-03-12 | 2019-03-12 | Multi-feature fusion artificial intelligent medicine package image recognition system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111695578A true CN111695578A (en) | 2020-09-22 |
Family
ID=72474394
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910171449.7A Pending CN111695578A (en) | 2019-03-12 | 2019-03-12 | Multi-feature fusion artificial intelligent medicine package image recognition system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111695578A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112242025A (en) * | 2020-09-30 | 2021-01-19 | 苏州艾隆科技股份有限公司 | Medicine dispensing method and device for medicine dispensing system |
CN113159973A (en) * | 2021-02-25 | 2021-07-23 | 华夏方圆信用评估有限公司 | Intelligent medical insurance fund dynamic supervision method and system |
CN113936781A (en) * | 2021-10-15 | 2022-01-14 | 南京和瑞供应链管理有限公司 | Efficient automatic medicine checking method |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105808965A (en) * | 2016-03-28 | 2016-07-27 | 张相林 | Method and system for medicine blending g detection |
CN106295165A (en) * | 2016-08-05 | 2017-01-04 | 四川大学华西第二医院 | A kind of anti-Drug dispensing mistakes system and method based on image recognition |
CN107729826A (en) * | 2017-09-29 | 2018-02-23 | 苏州安斯特灵智能科技有限公司 | Key works Drug packing image-recognizing method and its device |
-
2019
- 2019-03-12 CN CN201910171449.7A patent/CN111695578A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105808965A (en) * | 2016-03-28 | 2016-07-27 | 张相林 | Method and system for medicine blending g detection |
CN106295165A (en) * | 2016-08-05 | 2017-01-04 | 四川大学华西第二医院 | A kind of anti-Drug dispensing mistakes system and method based on image recognition |
CN107729826A (en) * | 2017-09-29 | 2018-02-23 | 苏州安斯特灵智能科技有限公司 | Key works Drug packing image-recognizing method and its device |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112242025A (en) * | 2020-09-30 | 2021-01-19 | 苏州艾隆科技股份有限公司 | Medicine dispensing method and device for medicine dispensing system |
CN113159973A (en) * | 2021-02-25 | 2021-07-23 | 华夏方圆信用评估有限公司 | Intelligent medical insurance fund dynamic supervision method and system |
CN113936781A (en) * | 2021-10-15 | 2022-01-14 | 南京和瑞供应链管理有限公司 | Efficient automatic medicine checking method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111695578A (en) | Multi-feature fusion artificial intelligent medicine package image recognition system | |
US20210082584A1 (en) | Drug inspection apparatus and method | |
CN104678963B (en) | A kind of system and method for the acquisition instrument facility information based on computer vision | |
CN103619251B (en) | Automatic preparation device for blood collection tube | |
US9846766B2 (en) | Method for monitoring the filling of a medication dispenser, and medication dispenser | |
EP2674181A2 (en) | Supplemental device for determining a set and/or injected dose amount of a syringe or pen injector | |
KR101210272B1 (en) | Medicine-taking service apparatus, medicine box, apparatus and Method for supporting medicine-taking service | |
CN109409291A (en) | The commodity recognition method and system of Intelligent cargo cabinet and the generation method of purchase order | |
CN110333242A (en) | A kind of detection method and its system of PET bottle quality | |
CN108495609A (en) | It is a kind of to be reminded to the device and method of user for sending | |
US9313464B2 (en) | Checking device and method based on image processing | |
KR101224384B1 (en) | Automatic inspection apparatus and the method of prescription drugs | |
CN115670527A (en) | Medical sampling device, equipment and method | |
CN113893958A (en) | Centrifuge tube taking and placing method, device and computer readable storage medium | |
CN110555939A (en) | Automatic vending machine | |
CN105498042B (en) | A kind of non-light-proof automatic alarm for infusion method and device thereof based on video | |
CN111150654A (en) | Intelligent medicine box with medicine administration management function | |
CN111114941B (en) | Full-automatic test tube labeling system and labeling method | |
CN110265129A (en) | A kind of intelligent movable blood sampling management terminal device | |
CN208637144U (en) | Medicament administration confirms that equipment, medicine box and medicament administration confirm system | |
KR102214873B1 (en) | Portable automatic sign inspection system and inspection method using the same | |
CN106096677A (en) | Packaged information detection method and device | |
CN215952629U (en) | Intelligent checking robot | |
KR20160116856A (en) | Apparatus for comparing drag and prescription | |
CN210990247U (en) | Blood pressure detection system |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200922 |