CN117422708A - Medicine boxing detection method, device, electronic equipment and storage medium - Google Patents
Medicine boxing detection method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117422708A CN117422708A CN202311647491.4A CN202311647491A CN117422708A CN 117422708 A CN117422708 A CN 117422708A CN 202311647491 A CN202311647491 A CN 202311647491A CN 117422708 A CN117422708 A CN 117422708A
- Authority
- CN
- China
- Prior art keywords
- medicine
- information
- video
- detection
- 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.)
- Pending
Links
- 239000003814 drug Substances 0.000 title claims abstract description 578
- 229940079593 drug Drugs 0.000 title claims abstract description 195
- 238000001514 detection method Methods 0.000 title claims abstract description 142
- 238000000034 method Methods 0.000 claims abstract description 20
- 230000002159 abnormal effect Effects 0.000 claims abstract description 11
- 238000000605 extraction Methods 0.000 claims description 32
- 230000004927 fusion Effects 0.000 claims description 27
- 238000012856 packing Methods 0.000 claims description 19
- 230000006870 function Effects 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 16
- 238000002372 labelling Methods 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 10
- 238000007689 inspection Methods 0.000 claims description 7
- 238000004806 packaging method and process Methods 0.000 claims description 4
- 239000000825 pharmaceutical preparation Substances 0.000 claims description 3
- 229940127557 pharmaceutical product Drugs 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 abstract description 5
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 3
- 238000012015 optical character recognition Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000009512 pharmaceutical packaging Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
- G06V10/806—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30204—Marker
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Medical Preparation Storing Or Oral Administration Devices (AREA)
Abstract
The invention discloses a medicine boxing detection method, a medicine boxing detection device, electronic equipment and a storage medium, comprising the following steps: the method comprises the steps of controlling a first camera to acquire a first video from a first angle in a region when medicines are boxed, controlling a second camera to acquire a second video from a second angle in the region when medicines are boxed, inputting the first video and the second video into first medicine information of medicines identified to be boxed in a medicine detection tracking model, acquiring a medicine order, acquiring second medicine information according to the medicine order, and judging whether the first medicine information and the second medicine information are matched; if yes, determining that the boxed medicine is correct; if not, determining that the packaged medicine is wrong, generating abnormal prompt information, realizing detection of medicine packages before the package through visual identification, saving a large amount of manpower, improving the detection efficiency of the medicine packages, and collecting videos from different angles through the first camera and the second camera so as to prevent the medicine from being shielded and being unable to be identified, and improving the accuracy of medicine detection.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a medicine boxing detection method, a medicine boxing detection device, electronic equipment and a storage medium.
Background
In the medical e-commerce industry, order transactions are realized on line, after medicines are packaged into packages on line, the packages are sent to buyers through logistics, and a large number of medicine packages can be sent out by a medical e-commerce warehouse every day. Because of the specificity of the medicines, the accuracy requirements on the types and the amounts of the sent medicines are very high, medicines in packages need to be checked before the medicines are sent, at present, the medicines are checked mainly by manually executing the medicine details on a paper list before the packages are packaged, a large amount of manpower is required, the efficiency is low, and errors are easy to occur.
Disclosure of Invention
The invention provides a medicine boxing detection method, a medicine boxing detection device, electronic equipment and a storage medium, which are used for solving the problems that manual inspection is needed before medicine boxing, a large amount of manpower is needed, the efficiency is low and mistakes are easy to occur.
In a first aspect, the present invention provides a method for detecting a pharmaceutical case, comprising:
when medicines are packaged, a first camera is controlled to acquire a first video from a first angle in a region when the medicines are packaged, and a second camera is controlled to acquire a second video from a second angle in the region when the medicines are packaged;
Inputting the first video and the second video into first medicine information for identifying the boxed medicines in a medicine detection tracking model;
acquiring a medicine order, and acquiring second medicine information according to the medicine order;
judging whether the first medicine information and the second medicine information are matched;
if yes, determining that the boxed medicine is correct;
if not, determining that the packaged medicine is wrong, and generating abnormal prompt information.
In a second aspect, the present invention provides a medicine packing detection device comprising:
the video acquisition module is used for controlling the first camera to acquire a first video from a first angle to a region when the medicines are boxed and controlling the second camera to acquire a second video from a second angle to the region when the medicines are boxed;
the first medicine information identification module is used for inputting the first video and the second video into a medicine detection tracking model to identify first medicine information of the boxed medicines;
the second medicine information acquisition module is used for acquiring a medicine order and acquiring second medicine information according to the medicine order;
the judging module is used for judging whether the first medicine information and the second medicine information are matched, if yes, executing the first result determining module, and if not, executing the second result determining module;
The first result determining module is used for determining that the packaged medicines are correct;
and the second result determining module is used for determining that the packaged medicines are wrong and generating abnormal prompt information.
In a third aspect, the present invention provides an electronic device, including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the pharmaceutical packaging detection method of any one of the first aspects of the invention.
In a fourth aspect, the present invention provides a computer readable storage medium storing computer instructions for causing a processor to perform the method of pharmaceutical product packaging detection of any one of the first aspects of the present invention.
According to the embodiment of the invention, the first video and the second video are acquired from different angles for the medicines in the container through the first camera and the second camera, the first video and the second video are input into the medicine detection tracking model to obtain the first medicine information of the medicines in the container, the medicine order is obtained, the second medicine information is obtained according to the medicine order, whether the first medicine information and the second medicine information are matched is further judged, if yes, the medicine in the container is determined to be correct, if not, the medicine in the container is determined to be wrong, and abnormal prompt information is generated, the first medicine information such as the name, the manufacturer, the number and the like of the medicine in the container is identified after the video is acquired through the camera, the first medicine information is matched with the second medicine information in the order, so that whether the medicine in the container is correct or not is judged, the medicine package before the package is detected through visual identification is realized, a large amount of manpower is saved, the medicine package detection efficiency is improved, and the video can be acquired from different angles through the first camera and the medicine package is prevented from being unrecognized, and the accuracy of medicine detection is improved.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for detecting medicine packing according to an embodiment of the present invention;
fig. 2 is a flowchart of a medicine packing detection method according to a second embodiment of the present invention;
FIG. 3 is a schematic diagram of a network structure of a drug detection tracking model;
fig. 4 is a schematic structural diagram of a medicine packing detection device according to a third embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
Example 1
Fig. 1 is a flowchart of a medicine packing detection method according to a first embodiment of the present invention, where the method may be applied to detect whether a medicine packed in a container is correct, and the method may be performed by a medicine packing detection device, where the medicine packing detection device may be implemented in a form of hardware and/or software and may be configured in an electronic device. As shown in fig. 1, the medicine packing detection method includes:
s101, when medicines are packaged, a first camera is controlled to acquire a first video from a first angle to a region when the medicines are packaged, and a second camera is controlled to acquire a second video from a second angle to a region when the medicines are packaged.
This embodiment can set up first camera and second camera in the region of medicine vanning to when receiving medicine detection instruction, first camera and second camera are synchronous after, first camera is followed first angle and is gathered first video to the region of medicine vanning, and second camera is followed the region of second angle when packing into the medicine. The first angle and the second angle are angles with a center point of a medicine boxing area as an origin of coordinates, and the first angle and the second angle are unequal, preferably, the first angle and the second angle may be opposite two angles, for example, a left side of the area when the medicine is boxed by the first camera, a right side of the area when the medicine is boxed by the second camera, so that images of different angles of the medicine in the box can be acquired.
S102, inputting the first video and the second video into a medicine detection tracking model to identify first medicine information of the packaged medicines.
In one embodiment, a medicine detection tracking model may be trained in advance, which may detect medicines from the first video and the second video and track the detected medicines, thereby identifying information of medicine names, manufacturers, medicine numbers, and the like of the medicines in the box as first medicine information.
S103, acquiring a medicine order, and acquiring second medicine information according to the medicine order.
In this embodiment, a logistics list may be printed or attached to a carton when a medicine is packaged, a two-dimensional code, a bar code and other graphic codes on the logistics list may be scanned by a code scanning device to obtain a medicine order, and the medicine name, manufacturer, quantity and the like of the medicine purchased by the medicine order are searched in a database of an electronic commerce platform through the medicine order to be used as second medicine information.
S104, judging whether the first medicine information and the second medicine information are matched.
Specifically, it may be determined whether or not the first medicine information identified by the medicine detection tracking model and the second medicine information obtained by the medicine order are identical in name, manufacturer, number, and the like, and if so, S105 is executed, and if not, S106 is executed.
S105, determining that the packaged medicine is correct.
If the information of the names, manufacturers, numbers and the like of the medicines in the first medicine information and the second medicine information are completely matched, the medicines which are sorted and packaged according to the medicine orders, namely the packaged medicines, are determined to be correct.
S106, determining that the boxed medicine is wrong, and generating abnormal prompt information.
If the information of the names, manufacturers, the quantity and the like of the medicines in the first medicine information and the second medicine information are not completely matched, determining that the medicines in the current container are wrong, generating abnormal prompt information, such as multiple-container, fewer-container, neglected-container and the like, and sending the prompt information to a related terminal for manual review.
According to the embodiment of the invention, the first video and the second video are acquired from different angles for the medicines in the container through the first camera and the second camera, the first video and the second video are input into the medicine detection tracking model to obtain the first medicine information of the medicines in the container, the medicine order is obtained, the second medicine information is obtained according to the medicine order, whether the first medicine information and the second medicine information are matched is further judged, if yes, the medicine in the container is determined to be correct, if not, the medicine in the container is determined to be wrong, and abnormal prompt information is generated, the first medicine information such as the name, the manufacturer, the number and the like of the medicine in the container is identified after the video is acquired through the camera, the first medicine information is matched with the second medicine information in the order, so that whether the medicine in the container is correct or not is judged, the medicine package before the package is detected through visual identification is realized, a large amount of manpower is saved, the medicine package detection efficiency is improved, and the video can be acquired from different angles through the first camera and the medicine package is prevented from being unrecognized, and the accuracy of medicine detection is improved.
Example two
Fig. 2 is a flowchart of a medicine packing detection method provided in a second embodiment of the present invention, where the medicine packing detection method includes:
s201, when medicines are packaged, a first camera is controlled to acquire a first video from a first angle in a region when the medicines are packaged, and a second camera is controlled to acquire a second video from a second angle in a region when the medicines are packaged.
According to the embodiment, the first camera and the second camera can be arranged in the medicine boxing area, the first camera is aligned to the boxing area at the first angle, the second camera is aligned to the boxing area at the second angle, when a medicine detection instruction is received, the first camera and the second camera are controlled to be synchronous, and the first camera and the second camera are controlled to acquire videos according to the same frame rate, so that the first video and the second video are obtained.
S202, inputting the first video into a first feature extraction network, and extracting a first feature map from the first video in the first feature extraction network.
As shown in fig. 3, the drug detection tracking model of the present embodiment includes a first feature extraction network, a second feature extraction network, a feature fusion network, a first detection head and a second detection head, where output layers of the first feature extraction network and the second feature extraction network are connected with input layers of the feature fusion network, and output layers of the feature fusion network are connected with input layers of the first detection head and the second detection head, respectively.
The drug detection tracking model of the present embodiment can be trained by the following steps:
s2021, acquiring a first image and a second image of the same medicine shot from different angles as training images, wherein the first image is marked with first medicine marking information, and the second image is marked with second medicine marking information.
According to the embodiment, the first image and the second image can be acquired from different angles for a plurality of medicines in a boxing scene, the first medicine labeling information is labeled for the first image, and the second medicine labeling information is labeled for the second image.
The first drug labeling information includes a first drug name, a first drug name text box, a first detection box, a first correspondence between the first detection box and a second detection box in the second image, and the second drug labeling information includes a second drug name, a second drug name text box, a second detection box, a second correspondence between the second detection box and the first detection box in the first image, where the drug name text box may be a text box of a text identified in the video, and the detection box may be a detection box of a drug identified in the video, and the first correspondence and the second correspondence represent representations that the first detection box and the second detection box belong to the same drug.
For example, assuming that the first image is L, the second image is R, three medicines in the first image are visible, the first image is marked with three detection frames L1, L2, and L3, four medicines in the second image are visible, and four detection frames R1, R2, R3, and R4 are marked, the first correspondence of the first image is that L1 corresponds to R1, L2 corresponds to R2, and L3 corresponds to R3, the second correspondence of the second image is that R1 corresponds to L1, R2 corresponds to L2, and R3 corresponds to L3, the correspondence may be represented by 1, and no correspondence of R4 may be marked as 0.
The second medicine name text box is the coordinates of four corner points of the text box, and can also be the coordinates of the upper left corner point and the length and the height of the text box.
S2022, inputting the first image and the second image into the medicine detection tracking model to obtain third medicine identification information of the first image and fourth medicine identification information of the second image.
After the first image and the second image are marked as training images, the first image and the second image can be input into a medicine detection tracking model to obtain third medicine identification information of the first image and fourth medicine identification information of the second image, and similarly, the third medicine identification information comprises a third corresponding relation of a third medicine name, a third medicine name text box, a third detection box and a fourth detection box in the second image, and the third medicine identification information comprises a fourth corresponding relation of the fourth medicine name, the fourth medicine name text box, the fourth detection box and the fourth detection box in the first image.
Specifically, as shown in fig. 3, the first image may be input into a first feature extraction network, the second image may be input into a second feature extraction network, and feature images output by the first feature extraction network and the second feature extraction network are input into a fusion feature network to obtain fusion features, and after the fusion features are respectively input into the first detection head and the second detection head, third medicine identification information of the first image is output from the first detection head, and fourth medicine identification information of the second image is output from the second detection head.
S2023, calculating the loss rate by using the first medicine labeling information, the second medicine labeling information, the third medicine identification information and the fourth medicine identification information.
In one embodiment, the first drug identification loss rate of the first image may be calculated using a first drug name, a first drug name text box, a third drug name, and a third drug name text box, the second drug identification loss rate of the second image may be calculated using a second drug name, a second drug name text box, a fourth drug name, and a fourth drug name text box, the first drug matching loss rate of the first image may be calculated using a first correspondence and a third correspondence, the second drug matching loss rate of the second image may be calculated using a second correspondence and a fourth correspondence, and a sum of the first drug identification loss rate, the second drug identification loss rate, the first drug matching loss rate, and the second drug matching loss rate may be calculated as the total loss rate.
The first drug identification loss rate and the second drug identification loss rate may be loss rates of drug detection and identification by the drug detection tracking model, and the first drug identification loss rate and the second drug identification loss rate may be calculated by using the following functions:
loss1＝a×MSE(box1，box2)+b×CCE(name1，name2)；
MSE(box1，box2)＝MSE(box1_corner，box2_corner)+(1-IoU(box1，box2))；
where a and b are weight coefficients, MSE (Mean Square Error ) is a mean square error function, box1 is a first drug name text box or a second drug name text box, box1 is a first drug name text box, box2 is a third drug name text box, box1 is a second drug name text box, box2 is a fourth drug name text box, CCE (categorical cross entropy, cross entropy loss function) is a cross entropy function, name1 is a first drug name or a second drug name, name2 is a third drug name when name1 is a first drug name, name2 is a fourth drug name when name1 is a second drug name, box 1_corer is a position in an upper left corner of the first drug name text box or the second drug name text box, and box 2_corer is a position in an upper left corner of the third drug name text box or the fourth drug name text box, ioU (Intersection overUnion, cross-over) is a cross-over function.
The drug detection tracking model enhances the performance of the model by the function from image information and text multi-mode information, the picture information is drug appearance packaging characteristics in the image, the text refers to text on the outer package extracted through OCR (Optical Character Recognition ), and due to the fact that the text is partially blocked during drug boxing, the OCR has the problems of text missing and blocking, the function is considered to combine the image and the detected text to enhance the detection effect, and the function design comprises two parts of position location loss MSE (box 1, box 2) of a drug name text box and correct probability loss CCE (name 1, name 2) of the output text, so that the model is more focused on a drug name area, and meanwhile the missing name part is complemented and corrected by combining the image characteristics, so that the accuracy of drug detection can be improved.
For the medicine matching loss rate, the ratio of the number of medicines with matching errors to the total number of medicines can be calculated as the matching loss rate, and for a first image, the total number of medicines is 3, the marked first corresponding relation is L1 corresponding to R1, L2 corresponding to R2 and L3 corresponding to R3, the third corresponding relation of the first image obtained after the medicine detection tracking model is input is L1 corresponding to R2, L2 corresponding to R1 and L3 corresponding to R3, and after the third corresponding relation is compared with the first corresponding relation, the number of medicine matching errors is determined to be 2, and the matching loss rate is 2/3.
The Total Loss rate Total Loss is as follows:
Total Loss＝loss1_L+loss1_R+Loss_Match_L+Loss_Match_R；
the Loss rate of the first medicine identification and the Loss rate of the second medicine identification are respectively defined as Loss1_ L, loss _R, and the Loss rate of the first medicine matching and the Loss rate of the second medicine matching are respectively defined as Loss rate of the second medicine matching and the Loss rate of the first medicine matching.
S2024, judging whether preset training conditions are met.
The training condition may be that the loss rate is smaller than the threshold, or that the number of iterative training reaches a preset number, and when the training condition is satisfied, S2025 is executed, otherwise S2026 is executed.
S2025, determining that the drug detection tracking model is trained.
When the training conditions are met, the accuracy of the drug detection tracking model is high enough, training can be stopped, and the trained drug detection tracking model is obtained.
S2026, adjusting model parameters of the drug detection tracking model according to the loss rate.
When the training condition is not satisfied, determining that the accuracy of the drug detection tracking model is still low, calculating a gradient according to the loss rate, performing gradient descent on the model parameters to update the model parameters, and returning to S2022 for continuous training, wherein the model parameters can refer to various gradient descent algorithms in the prior art, which are not described in detail herein.
After the drug detection tracking model is trained and deployed, when the first video and the second video are acquired, the first video is input into a first feature extraction network of the drug detection tracking model, and a first feature map is extracted from the first video in the first feature extraction network, as shown in fig. 3.
S203, inputting the second video into a second feature extraction network, and extracting a second feature map from the second video in the second feature extraction network.
As shown in fig. 3, when the first video and the second video are acquired, the second video is input into a second feature extraction network of the medicine detection tracking model, and a second feature map is extracted from the second video in the second feature extraction network.
S204, fusing the first feature map and the second feature map in the feature fusion network to obtain fusion features.
As shown in fig. 3, the feature fusion network may be a feature fusion network based on Attention mechanism (Attention), and after the first feature extraction network outputs a first feature map and the second feature extraction network outputs a second feature map, the feature fusion network fuses the first feature map and the second feature map to obtain a fused feature.
S205, respectively identifying the fusion characteristics at the first detection head and the second detection head to obtain medicine information of the first video and medicine information of the second video, wherein the medicine information of the first video and the medicine information of the second video comprise medicine names, manufacturers and numbers.
After the fusion characteristics are respectively input into a first detection head and a second detection head, the first detection head recognizes the fusion characteristics to obtain information such as the medicine name, manufacturer, quantity and the like of medicines packaged in the first video as medicine information of the first video, and the second detection head recognizes the fusion characteristics to obtain information such as the medicine name, manufacturer, quantity and the like of medicines packaged in the second video as medicine information of the second video.
S206, performing duplication elimination processing on the medicine names in the medicine information of the first video and the medicine information of the second video to obtain the medicine names, manufacturers and numbers of the boxed medicines as the first medicine information.
Because the first video and the second video are videos acquired from different angles for medicines in the same container, the names of the identified medicines are the same, and after the information of the same medicines is de-duplicated, the medicine names, manufacturers and numbers of the obtained medicines are the first medicine information.
S207, the graphic code on the outer package during medicine boxing is scanned through the code scanning equipment to obtain a medicine order number, and medicine detail information matched with the order number is searched for serving as second medicine information.
In this embodiment, a logistics list may be printed or attached to a carton when a medicine is packaged, a two-dimensional code, a bar code and other graphic codes on the logistics list may be scanned by a code scanning device to obtain a medicine order, and the medicine name, manufacturer, quantity and the like of the medicine purchased by the medicine order are searched in a database of an electronic commerce platform through the medicine order to be used as second medicine information.
S208, judging whether the medicine names, manufacturers and the quantity in the first medicine information and the second medicine information are identical.
Specifically, it may be first determined whether the names of the medicines are identical, if so, it is further determined whether the manufacturer and the number of each medicine are identical, S209 is performed when the names of the medicines, the manufacturer and the number of the medicines are identical, and S210 is performed when one of them is not identical.
S209, determining that the boxed medicine is correct.
If the information of the names, manufacturers, numbers and the like of the medicines in the first medicine information and the second medicine information are completely matched, the medicines which are sorted and packaged according to the medicine orders, namely the packaged medicines, are determined to be correct.
S210, determining that the boxed medicine is wrong, and generating abnormal prompt information.
If the information of the names, manufacturers, the quantity and the like of the medicines in the first medicine information and the second medicine information are not completely matched, determining that the medicines in the current container are wrong, generating abnormal prompt information, such as multiple-container, fewer-container, neglected-container and the like, and sending the prompt information to a related terminal for manual review.
After the first video and the second video are acquired, the first video is input into a first feature extraction network to extract a first feature image of the first video, the second video is input into a second feature extraction network to extract a second feature image of the second video, the first feature image and the second feature image are fused in a feature fusion network to obtain fusion features, the fusion features are respectively identified at a first detection head and a second detection head to obtain medicine information of the first video and medicine information of the second video, the medicine information of the first video and the medicine information of the second video comprise medicine names, manufacturers and numbers, medicine names in the medicine information of the first video and medicine names in the medicine information of the second video are subjected to duplication removal processing to obtain medicine names, manufacturers and numbers of medicines in a boxing, a graphic code on the outer packaging when the medicine is scanned by a code scanning device is used as first medicine information, medicine list number is searched for medicine detail information matched with the list number to be used as second medicine information, whether the medicine names, the medicine names in the first medicine information and the second medicine information are identical to the manufacturer and the second medicine list number is judged, and if the medicine names, the medicine names and the medicine names in the second medicine list are identical to the medicine list are generated, and the medicine list is completely contained in the boxing is generated, and if the medicine list is incorrect is generated, the medicine list is incorrect is determined, and the medicine box is not incorrect is determined if the medicine is generated is completely correct. The method has the advantages that the medicine package before the package is detected through visual identification, a large amount of manpower is saved, the detection efficiency of the medicine package is improved, feature fusion is carried out on the feature images of the videos collected by the first camera and the second camera, the videos shot at a plurality of angles can be fused to detect and track the medicine, the medicine is prevented from being shielded and can not be identified, and the accuracy of medicine detection is improved.
Example III
Fig. 4 is a schematic structural diagram of a medicine packing detection device according to a third embodiment of the present invention. As shown in fig. 4, the medicine packing detection device includes:
the video acquisition module 401 is used for controlling the first camera to acquire a first video from a first angle to an area when the medicine is boxed and controlling the second camera to acquire a second video from a second angle to the area when the medicine is boxed;
a first medicine information identification module 402, configured to input the first video and the second video into first medicine information for identifying a medicine in a container in a medicine detection tracking model;
a second medicine information obtaining module 403, configured to obtain a medicine order, and obtain second medicine information according to the medicine order;
a judging module 404, configured to judge whether the first drug information and the second drug information are matched, if yes, execute a first result determining module 405, and if not, execute a second result determining module 406;
a first result determining module 405 for determining that the packaged drug is correct;
the second result determining module 406 is configured to determine that the medicine in the case is wrong, and generate an abnormality notification.
Optionally, the drug detection tracking model includes a first feature extraction network, a second feature extraction network, a feature fusion network, a first detection head and a second detection head;
The first medicine information identification module 402 is specifically configured to:
inputting a first video into a first feature extraction network, and extracting a first feature map from the first video in the first feature extraction network;
inputting a second video into a second feature extraction network, and extracting a second feature map from the second video in the second feature extraction network;
fusing the first feature map and the second feature map in the feature fusion network to obtain fusion features;
identifying the fusion characteristics at the first detection head and the second detection head respectively to obtain medicine information of a first video and medicine information of a second video, wherein the medicine information of the first video and the medicine information of the second video comprise medicine names, manufacturers and numbers;
and performing duplicate removal processing on the medicine names in the medicine information of the first video and the medicine information of the second video to obtain the medicine names, manufacturers and numbers of the boxed medicines as the first medicine information.
Optionally, the drug detection tracking model is trained by:
the training image acquisition module is used for acquiring a first image and a second image shot by the same medicine from different angles as training images, wherein the first image is marked with first medicine marking information, and the second image is marked with second medicine marking information;
The image input module is used for inputting the first image and the second image into a medicine detection tracking model to obtain third medicine identification information of the first image and fourth medicine identification information of the second image;
the loss rate calculation module is used for calculating the loss rate by adopting the first medicine labeling information, the second medicine labeling information, the third medicine identification information and the fourth medicine identification information;
the training condition judging module is used for judging whether preset training conditions are met, if yes, the training complete determining module is executed, and if not, the model parameter adjusting module is executed;
the training complete determination module is used for determining that the drug detection tracking model is trained;
and the model parameter adjustment module is used for adjusting the model parameters of the drug detection tracking model according to the loss rate and returning the model parameters to the image input module.
Optionally, the first drug labeling information includes a first correspondence between a first drug name, a first drug name text box, a first detection box and a second detection box in the second image, the second drug labeling information includes a second correspondence between a second drug name, a second drug name text box, a second detection box and a first detection box in the first image, the third drug identification information includes a third drug name, a third drug name text box, a third detection box, a third correspondence between a third detection box and a fourth detection box in the second image, and the third drug identification information includes a fourth drug name, a fourth drug name text box, a fourth detection box and a fourth correspondence between a fourth detection box and a third detection box in the first image;
The loss rate calculation module is specifically configured to:
calculating a first medicine identification loss rate of the first image by adopting the first medicine name, the first medicine name text box, the third medicine name and the third medicine name text box;
calculating a second medicine identification loss rate of the second image by adopting the second medicine name, the second medicine name text box, the fourth medicine name and the fourth medicine name text box;
calculating a first medicine matching loss rate of the first image by adopting the first corresponding relation and the third corresponding relation;
calculating a second medicine matching loss rate of a second image by adopting the second corresponding relation and the fourth corresponding relation;
and calculating the sum of the first medicine identification loss rate, the second medicine identification loss rate, the first medicine matching loss rate and the second medicine matching loss rate as a total loss rate.
Optionally, the loss rate calculation module is specifically further configured to:
calculating a first drug identification loss rate and a second drug identification loss rate using the following functions:
loss1＝a×MSE(box1，box2)+b×CCE(name1，name2)；
MSE(box1，box2)＝MSE(box1_corner，box2_corner)+(1-IoU(box1，box2))；
where a and b are weight coefficients, MSE () is a mean square error function, box1 is a first drug name text box or a second drug name text box, box1 is a first drug name text box, box2 is a third drug name text box, box1 is a second drug name text box, box2 is a fourth drug name text box, CCE () is a cross entropy function, name1 is a first drug name or a second drug name, name2 is a third drug name when name1 is a first drug name, name2 is a fourth drug name when name1 is a second drug name, box1_corner is a position at an upper left corner of the first drug name text box or the second drug name text box, box2_corner is a position at an upper left corner of the third drug name text box or the fourth drug name text box, and IoU () is an overlap ratio function.
Optionally, the second medicine information obtaining module 403 is specifically configured to:
the method comprises the steps of scanning graphic codes on an outer package when a medicine is packaged by a code scanning device to obtain a medicine order number;
and searching the medicine detail information matched with the order number to serve as second medicine information.
Optionally, the determining module 404 is specifically configured to:
and judging whether the medicine names, manufacturers and numbers in the first medicine information and the second medicine information are identical.
The medicine boxing detection device provided by the embodiment of the invention can execute the medicine boxing detection method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example IV
Fig. 5 shows a schematic diagram of an electronic device 50 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 5, the electronic device 50 includes at least one processor 51, and a memory, such as a Read Only Memory (ROM) 52, a Random Access Memory (RAM) 53, etc., communicatively connected to the at least one processor 51, in which the memory stores a computer program executable by the at least one processor, and the processor 51 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 52 or the computer program loaded from the storage unit 58 into the Random Access Memory (RAM) 53. In the RAM 53, various programs and data required for the operation of the electronic device 50 can also be stored. The processor 51, the ROM 52 and the RAM 53 are connected to each other via a bus 54. An input/output (I/O) interface 55 is also connected to bus 54.
Various components in the electronic device 50 are connected to the I/O interface 55, including: an input unit 56 such as a keyboard, a mouse, etc.; an output unit 57 such as various types of displays, speakers, and the like; a storage unit 58 such as a magnetic disk, an optical disk, or the like; and a communication unit 59 such as a network card, modem, wireless communication transceiver, etc. The communication unit 59 allows the electronic device 50 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunications networks.
The processor 51 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 51 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 51 performs the various methods and processes described above, such as the pharmaceutical case detection method.
In some embodiments, the pharmaceutical product case detection method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 58. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 50 via the ROM 52 and/or the communication unit 59. When the computer program is loaded into RAM 53 and executed by processor 51, one or more steps of the above-described medicine packing detection method may be performed. Alternatively, in other embodiments, processor 51 may be configured to perform the pharmaceutical case detection method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above can be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A medicine packing detection method, characterized by comprising:
when medicines are packaged, a first camera is controlled to acquire a first video from a first angle in a region when the medicines are packaged, and a second camera is controlled to acquire a second video from a second angle in the region when the medicines are packaged;
inputting the first video and the second video into first medicine information for identifying the boxed medicines in a medicine detection tracking model;
Acquiring a medicine order, and acquiring second medicine information according to the medicine order;
judging whether the first medicine information and the second medicine information are matched;
if yes, determining that the boxed medicine is correct;
if not, determining that the packaged medicine is wrong, and generating abnormal prompt information.
2. The medicine packing inspection method of claim 1, wherein the medicine inspection tracking model includes a first feature extraction network, a second feature extraction network, a feature fusion network, a first inspection head, and a second inspection head;
the inputting the first video and the second video into the medicine detection tracking model to identify first medicine information of the medicine in the container comprises the following steps:
inputting a first video into a first feature extraction network, and extracting a first feature map from the first video in the first feature extraction network;
inputting a second video into a second feature extraction network, and extracting a second feature map from the second video in the second feature extraction network;
fusing the first feature map and the second feature map in the feature fusion network to obtain fusion features;
identifying the fusion characteristics at the first detection head and the second detection head respectively to obtain medicine information of a first video and medicine information of a second video, wherein the medicine information of the first video and the medicine information of the second video comprise medicine names, manufacturers and numbers;
And performing duplicate removal processing on the medicine names in the medicine information of the first video and the medicine information of the second video to obtain the medicine names, manufacturers and numbers of the boxed medicines as the first medicine information.
3. The drug packing detection method of claim 2, wherein the drug detection tracking model is trained by:
acquiring a first image and a second image of the same medicine shot from different angles as training images, wherein the first image is marked with first medicine marking information, and the second image is marked with second medicine marking information;
inputting the first image and the second image into a medicine detection tracking model to obtain third medicine identification information of the first image and fourth medicine identification information of the second image;
calculating a loss rate by using the first medicine marking information, the second medicine marking information, the third medicine identification information and the fourth medicine identification information;
judging whether preset training conditions are met or not;
if yes, determining that the drug detection tracking model is trained;
and if not, adjusting model parameters of the medicine detection tracking model according to the loss rate, and returning to the step of inputting the first image and the second image into the medicine detection tracking model.
4. The medicine-packing detection method according to claim 3, wherein the first medicine labeling information includes a first correspondence of a first medicine name, a first medicine name text box, a first detection box, and a second detection box in the second image, the second medicine labeling information includes a second correspondence of a second medicine name, a second medicine name text box, a second detection box, and a first detection box in the first image, the third medicine identification information includes a third correspondence of a third medicine name, a third medicine name text box, a third detection box, and a fourth detection box in the second image, and the third medicine identification information includes a fourth correspondence of a fourth medicine name, a fourth medicine name text box, a fourth detection box, and a third detection box in the first image;
the calculating the loss rate using the first drug labeling information, the second drug labeling information, the third drug identification information, and the fourth drug identification information includes:
calculating a first medicine identification loss rate of the first image by adopting the first medicine name, the first medicine name text box, the third medicine name and the third medicine name text box;
Calculating a second medicine identification loss rate of the second image by adopting the second medicine name, the second medicine name text box, the fourth medicine name and the fourth medicine name text box;
calculating a first medicine matching loss rate of the first image by adopting the first corresponding relation and the third corresponding relation;
calculating a second medicine matching loss rate of a second image by adopting the second corresponding relation and the fourth corresponding relation;
and calculating the sum of the first medicine identification loss rate, the second medicine identification loss rate, the first medicine matching loss rate and the second medicine matching loss rate as a total loss rate.
5. The medicine-packing-inspection method of claim 4, wherein the first medicine identification loss rate and the second medicine identification loss rate are calculated using the following functions:
loss1＝a×MSE(box1，box2)+b×CCE(name1，name2)；
MSE(box1，box2)＝MSE(box1_corner，box2_corner)+(1-IoU(box1，box2))；
where a and b are weight coefficients, MSE () is a mean square error function, box1 is a first drug name text box or a second drug name text box, box1 is a first drug name text box, box2 is a third drug name text box, box1 is a second drug name text box, box2 is a fourth drug name text box, CCE () is a cross entropy function, name1 is a first drug name or a second drug name, name2 is a third drug name when name1 is a first drug name, name2 is a fourth drug name when name1 is a second drug name, box1_corner is a position at an upper left corner of the first drug name text box or the second drug name text box, box2_corner is a position at an upper left corner of the third drug name text box or the fourth drug name text box, and IoU () is an overlap ratio function.
6. The medicine-packing-inspection method according to claim 1, wherein the acquiring the medicine order and acquiring the second medicine information based on the medicine order includes:
the method comprises the steps of scanning graphic codes on an outer package when a medicine is packaged by a code scanning device to obtain a medicine order number;
and searching the medicine detail information matched with the order number to serve as second medicine information.
7. The medicine-packing-detection method according to any one of claims 1 to 6, wherein the judging whether the first medicine information and the second medicine information match or not includes:
and judging whether the medicine names, manufacturers and numbers in the first medicine information and the second medicine information are identical.
8. A medicine packing detection device, comprising:
the video acquisition module is used for controlling the first camera to acquire a first video from a first angle to a region when the medicines are boxed and controlling the second camera to acquire a second video from a second angle to the region when the medicines are boxed;
the first medicine information identification module is used for inputting the first video and the second video into a medicine detection tracking model to identify first medicine information of the boxed medicines;
The second medicine information acquisition module is used for acquiring a medicine order and acquiring second medicine information according to the medicine order;
the judging module is used for judging whether the first medicine information and the second medicine information are matched, if yes, executing the first result determining module, and if not, executing the second result determining module;
the first result determining module is used for determining that the packaged medicines are correct;
and the second result determining module is used for determining that the packaged medicines are wrong and generating abnormal prompt information.
9. An electronic device, the electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the pharmaceutical case detection method of any one of claims 1-7.
10. A computer readable storage medium storing computer instructions for causing a processor to perform the pharmaceutical product packaging detection method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311647491.4A CN117422708A (en) | 2023-12-04 | 2023-12-04 | Medicine boxing detection method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311647491.4A CN117422708A (en) | 2023-12-04 | 2023-12-04 | Medicine boxing detection method, device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117422708A true CN117422708A (en) | 2024-01-19 |
Family
ID=89532732
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311647491.4A Pending CN117422708A (en) | 2023-12-04 | 2023-12-04 | Medicine boxing detection method, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117422708A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117745187A (en) * | 2024-02-07 | 2024-03-22 | 吉林大学 | Automatic drug delivery system and method based on AGV |
| CN117745187B (en) * | 2024-02-07 | 2024-05-14 | 吉林大学 | Automatic drug delivery system and method based on AGV |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2019211415A (en) * | 2018-06-08 | 2019-12-12 | アズビル株式会社 | Appearance inspection device and method |
| CN114937176A (en) * | 2022-05-20 | 2022-08-23 | 湖南神帆科技有限公司 | Medicine real-time identification method and system based on deep learning |
| CN116824175A (en) * | 2023-02-08 | 2023-09-29 | 清华大学 | Medicine sorting and checking method and device, storage medium and electronic equipment |
-
2023
- 2023-12-04 CN CN202311647491.4A patent/CN117422708A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2019211415A (en) * | 2018-06-08 | 2019-12-12 | アズビル株式会社 | Appearance inspection device and method |
| CN114937176A (en) * | 2022-05-20 | 2022-08-23 | 湖南神帆科技有限公司 | Medicine real-time identification method and system based on deep learning |
| CN116824175A (en) * | 2023-02-08 | 2023-09-29 | 清华大学 | Medicine sorting and checking method and device, storage medium and electronic equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117745187A (en) * | 2024-02-07 | 2024-03-22 | 吉林大学 | Automatic drug delivery system and method based on AGV |
| CN117745187B (en) * | 2024-02-07 | 2024-05-14 | 吉林大学 | Automatic drug delivery system and method based on AGV |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112560862B (en) | Text recognition method and device and electronic equipment | |
| CN107403128B (en) | Article identification method and device | |
| CN114066900A (en) | Image segmentation method and device, electronic equipment and storage medium | |
| CN111783645A (en) | Character recognition method and device, electronic equipment and computer readable storage medium | |
| CN112508109B (en) | Training method and device for image recognition model | |
| CN111597857B (en) | Logistics package detection method, device, equipment and readable storage medium | |
| US11861668B2 (en) | Method, device, electronic apparatus and storage medium for generating order | |
| CN114419035B (en) | Product identification method, model training device and electronic equipment | |
| CN112580637A (en) | Text information identification method, text information extraction method, text information identification device, text information extraction device and text information identification system | |
| CN114724166A (en) | Title extraction model generation method and device and electronic equipment | |
| CN113111801A (en) | Goods checking method, equipment and storage medium for automatic vending machine | |
| CN111666816A (en) | Method, device and equipment for detecting state of logistics piece | |
| CN114596188A (en) | Watermark detection method, model training method, device and electronic equipment | |
| CN117422708A (en) | Medicine boxing detection method, device, electronic equipment and storage medium | |
| CN112364702A (en) | Article verification method and device | |
| CN116051558A (en) | Defect image labeling method, device, equipment and medium | |
| CN114067328A (en) | Text recognition method and device and electronic equipment | |
| CN112734446A (en) | Commodity verification method and device based on vision and gravity detection | |
| CN114120305A (en) | Training method of text classification model, and recognition method and device of text content | |
| CN113378958A (en) | Automatic labeling method, device, equipment, storage medium and computer program product | |
| CN112749978A (en) | Detection method, apparatus, device, storage medium, and program product | |
| CN113111734A (en) | Watermark classification model training method and device | |
| CN113761169A (en) | Price identification method and device | |
| CN115497113B (en) | Information generation method, device, electronic equipment and storage medium | |
| CN117575735B (en) | Ordering verification method, device, equipment and storage medium for medicines |
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 |