CN116281070A - Medicine sorting system and method based on big data - Google Patents
Medicine sorting system and method based on big data Download PDFInfo
- Publication number
- CN116281070A CN116281070A CN202310327703.4A CN202310327703A CN116281070A CN 116281070 A CN116281070 A CN 116281070A CN 202310327703 A CN202310327703 A CN 202310327703A CN 116281070 A CN116281070 A CN 116281070A
- Authority
- CN
- China
- Prior art keywords
- medicine
- image
- module
- information
- big data
- 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 118
- 238000000034 method Methods 0.000 title claims abstract description 44
- 229940079593 drug Drugs 0.000 title claims description 18
- 230000000877 morphologic effect Effects 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 7
- 238000003709 image segmentation Methods 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 6
- 230000002146 bilateral effect Effects 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 5
- 238000005286 illumination Methods 0.000 claims description 5
- 230000010365 information processing Effects 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 239000003086 colorant Substances 0.000 claims description 3
- 238000005260 corrosion Methods 0.000 claims description 3
- 230000007797 corrosion Effects 0.000 claims description 3
- GNFTZDOKVXKIBK-UHFFFAOYSA-N 3-(2-methoxyethoxy)benzohydrazide Chemical compound COCCOC1=CC=CC(C(=O)NN)=C1 GNFTZDOKVXKIBK-UHFFFAOYSA-N 0.000 claims description 2
- FGUUSXIOTUKUDN-IBGZPJMESA-N C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 Chemical compound C1(=CC=CC=C1)N1C2=C(NC([C@H](C1)NC=1OC(=NN=1)C1=CC=CC=C1)=O)C=CC=C2 FGUUSXIOTUKUDN-IBGZPJMESA-N 0.000 claims description 2
- 230000008569 process Effects 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000004806 packaging method and process Methods 0.000 description 3
- 230000001276 controlling effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 235000008694 Humulus lupulus Nutrition 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013461 design Methods 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
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65G—TRANSPORT OR STORAGE DEVICES, e.g. CONVEYORS FOR LOADING OR TIPPING, SHOP CONVEYOR SYSTEMS OR PNEUMATIC TUBE CONVEYORS
- B65G47/00—Article or material-handling devices associated with conveyors; Methods employing such devices
- B65G47/34—Devices for discharging articles or materials from conveyor
- B65G47/46—Devices for discharging articles or materials from conveyor and distributing, e.g. automatically, to desired points
- B65G47/48—Devices for discharging articles or materials from conveyor and distributing, e.g. automatically, to desired points according to bodily destination marks on either articles or load-carriers
- B65G47/49—Devices for discharging articles or materials from conveyor and distributing, e.g. automatically, to desired points according to bodily destination marks on either articles or load-carriers without bodily contact between article or load carrier and automatic control device, e.g. the destination marks being electrically or electronically detected
- B65G47/493—Devices for discharging articles or materials from conveyor and distributing, e.g. automatically, to desired points according to bodily destination marks on either articles or load-carriers without bodily contact between article or load carrier and automatic control device, e.g. the destination marks being electrically or electronically detected by use of light responsive means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0833—Tracking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/1431—Illumination control
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/1437—Sensor details, e.g. position, configuration or special lenses
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/146—Aligning or centring of the image pick-up or image-field
- G06V30/147—Determination of region of interest
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/146—Aligning or centring of the image pick-up or image-field
- G06V30/1475—Inclination or skew detection or correction of characters or of image to be recognised
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/155—Removing patterns interfering with the pattern to be recognised, such as ruled lines or underlines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/16—Image preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/16—Image preprocessing
- G06V30/162—Quantising the image signal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/16—Image preprocessing
- G06V30/164—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/18—Extraction of features or characteristics of the image
- G06V30/1801—Detecting partial patterns, e.g. edges or contours, or configurations, e.g. loops, corners, strokes or intersections
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Mechanical Engineering (AREA)
- Entrepreneurship & Innovation (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Processing (AREA)
Abstract
The invention belongs to the technical field of medicine sorting, and particularly relates to a medicine sorting system and method based on big data.
Description
Technical Field
The invention belongs to the technical field of medicine sorting, and particularly relates to a medicine sorting system and method based on big data.
Background
At present, sorting operation in a production flow is one of important factors limiting production operation efficiency, high-quality sorting capability is an important ring in production, and particularly in the face of personalized and diversified demands of terminal clients at present, a production line needs to have enough flexibility to better serve different clients, and an automatic sorting system needs to be introduced in the production process based on the sorting operation.
The medicine logistics is a special logistics field, relates to the medication safety of the national citizens, is always the logistics behavior of the national regulatory agency under the important supervision, and medicine logistics enterprises must pass GSP authentication, so that the medicine sorting links are aimed at, and how to realize rapid, accurate and large-scale sorting is the direction of the important research in the existing medicine sorting field.
Disclosure of Invention
Aiming at the technical problems of medicine sorting, the invention provides a big data-based medicine sorting system and a big data-based medicine sorting method which are reasonable in design and can effectively realize quick sorting of medicines.
In order to achieve the above purpose, the invention provides a big data-based medicine sorting system and method, which comprises an image acquisition module for acquiring medicine photos, a medicine image segmentation module for removing irrelevant information, a medicine national medicine quasi-character positioning and identifying module for carrying out morphological processing, a medicine grabbing module for grabbing, a conveyor belt module for transmitting and an information processing module for uploading and tracking medicine information, wherein the image acquisition module selects a backlight illumination lighting mode to photograph the medicine, the photographed medicine images are transmitted to the medicine image segmentation module, the medicine image segmentation module acquires an interested area in the medicine images, the irrelevant information is removed, the medicine national medicine quasi-character positioning and identifying module carries out morphological processing on the segmented image images, the medicine grabbing module analyzes and grabs corresponding medicine to a corresponding conveyor belt through the information transmitted by the medicine national medicine quasi-character positioning and identifying module, and the medicine national medicine quasi-character positioning and identifying module carries out analysis acquisition on the uploaded photos comprises the following effective steps:
a. firstly, carrying out graying operation on an image;
b. denoising the photo subjected to the graying operation, and filtering out internal noise;
c. image enhancement is carried out on the photo after the image denoising operation;
d. correcting the photo subjected to the image enhancement operation, detecting the edges of the medicines, and removing the areas outside the edges;
e. performing mathematical morphology processing on the photographs after the rejection operation;
f. filling morphological areas of the photos subjected to mathematical morphological treatment;
g. scanning and positioning the filled photo;
h. identifying the image information of line scanning positioning to obtain a precisely positioned Chinese medicine quasi word sign region, and obtaining the information of the traceability code of the medicine;
in the step a, a weighted average method is adopted, and the calculation formula of the weighted average method is as follows:
f(i，j)＝0.299R+0.587G+0.114B
in order to avoid slower floating point number operation speed, an integer operation method is adopted:
f(i，j)＝(30R+59G+11B)/100
in the step b, the bilateral filtering method is adopted to remove the noise of the image,
wherein the weight coefficient w (i, j, k, l) depends on the product of the pixel location kernel and the pixel kernel,
in the step c, a piecewise linear gray enhancement method is adopted, and the piecewise linear change function formula is as follows:
wherein the gray scale of f (x, y) of the input image is M, the gray scale of g (x, y) of the output image is N, a gray scale interval of the input image is [ a, b ], and a gray scale interval of the output image is [ c, d ];
in the step d, the picture is corrected by adopting Hough transformation, and the rotation formula is as follows
Wherein θ is the angle between a straight line on the photo and the horizontal direction,
the threshold segmentation is adopted for elimination, and the segmented image g (x, y) is as follows:
wherein T is a set threshold;
preferably, in the step b, a bilateral filtering method is adopted to filter and denoise the photo after the graying operation.
Preferably, in the step d, an OTSU threshold segmentation method is used to determine the optimal threshold T.
Preferably, in the step e, the image is processed by adopting a corrosion, expansion, opening and closing method.
Preferably, in the step f, an 8-way communication mode is adopted to process the image, then morphological operation is carried out on the image, and gaps among pixels are filled.
Preferably, in the step g, according to the difference of the background colors of the image in the character area and the background area, the Chinese medicine standard word is confirmed, and the calculation formula is as follows:
wherein m (p) is the sum of the hop times of the current line after scanning, n is the number of columns, and G (i) is any scanning line of the image.
Compared with the prior art, the medicine sorting system and method based on big data have the advantages that the multi-angle lens arrangement of the image acquisition module is utilized, batch acquisition of medicine photo information is effectively achieved, medicine Chinese medicine standard words and medicine related information are accurately identified through the medicine Chinese medicine standard word character positioning and identifying module, the medicine Chinese medicine standard words and medicine related information are connected with the cloud processing center, medicine tracking code related information is uploaded, the medicine grabbing module is controlled to sort medicines, the corresponding medicines are placed on the conveyor belt module and are conveyed to a packaging place, tracking and tracing of medicine logistics are achieved through the information processing module, guarantee is provided for safe use of the medicines, and medicine sorting efficiency is improved.
Detailed Description
In order that the above objects, features and advantages of the invention may be more clearly understood, a further description of the invention will be provided with reference to the following examples. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced otherwise than as described herein, and therefore the present invention is not limited to the specific embodiments of the disclosure that follow.
In order to achieve the above object, the big data-based medicine sorting system and method provided in the embodiment includes an image acquisition module for acquiring medicine photos, wherein the image acquisition module acquires photos of a plurality of medicines walking on a conveyor belt by controlling a plurality of lenses with different angles, and an LED lamp is used as a lighting source; the medicine image segmentation module is used for removing irrelevant information to segment the obtained photo and remove the information irrelevant to medicine; the image processing module is used for carrying out morphological processing on the divided images, a line scanning algorithm is used for carrying out morphological processing on the divided images, positioning the medicine standard characters, confirming the medicine standard characters of each medicine, conveniently and rapidly sorting the medicine standard characters, carrying out rapid grabbing by the medicine grabbing module for grabbing, placing the medicine on the appointed conveyor belt module, conveying the corresponding medicine to a packaging part by the conveyor belt module for conveying, conveniently carrying out packaging processing, uploading the processed photos to a cloud processing center by the information processing module for uploading and tracking medicine information, identifying the medicine information, storing and recording the medicine information, realizing sharing of the medicine information, ensuring that the medicine information can be browsed and downloaded in real time and can be rapidly searched.
In order to better process the captured photograph, in this embodiment, a related analysis and acquisition method is specially formulated, and the specific operation is as follows.
The image is first grayed, the gray refers to the color value of each pixel in the gray image, the color depth of the black-and-white image is a range, the upper limit is 255, the lower limit is 0, that is, white is an upper limit, black is a lower limit, and the shade of the color is called the gray value. The color mode of most of the existing color images is RGB mode, the images with the same RGB components are called gray images, the gray images obtained after the gray treatment of the color images only contain original image brightness information, but the characteristic information of most of the original images is reserved, the subsequent image processing is carried out by using the gray images, the operation speed of a computer is greatly improved,
the weighted average of the R, G, B three components of pixel p (i, j) is taken as the gray value for that pixel. The choice of weights is generally determined by the importance of the R, G, B three components. The calculation formula is as follows:
f(i，j)＝0.299R+0.587G+0.114B
in order to avoid slower floating point number operation speed, an integer operation method is adopted:
f(i，j)＝(30R+59G+11B)/100
because the image is often influenced by uncertainty factors such as environment, illumination, manual operation and the like in the acquisition process, noise is inevitably introduced, and on the basis of keeping the original information, the image needs to be subjected to denoising treatment, and the internal noise is filtered. The image denoising process processes pixels with larger differences from surrounding pixels in the image, and then adjusts the pixels with larger differences to be close to the surrounding pixels.
The specific operation method is as follows: the image denoising is carried out by adopting a bilateral filtering method,
wherein the weight coefficient w (i, j, k, l) depends on the product of the pixel location kernel and the pixel kernel,
in order to enhance the integral information of the image, the interested area in the image is enhanced according to the requirement, irrelevant information is weakened or removed, the difference of object characteristics is enlarged, the visual effect is enhanced, a piecewise linear gray enhancement method is adopted, and a piecewise linear change function formula is as follows:
wherein the gray scale of f (x, y) of the input image is M, the gray scale of g (x, y) of the output image is N, a gray scale interval of the input image is [ a, b ], and a gray scale interval of the output image is [ c, d ];
the position of the medicine on the visual inspection table is random relative to the camera, so that the medicine image collected by the camera is also in a random inclined state, therefore, the collected image must be subjected to inclination correction, the picture is corrected by adopting Hough transformation, and the rotation formula is that
Wherein θ is the angle between a straight line on the photo and the horizontal direction,
for image f (x, y), one obvious way to extract medicine from the image is to select a threshold T that separates the two. We call the point (x, y) where f (x, y) > T as the object point, the other points as the background point, cull by threshold segmentation, and the segmented image g (x, y) is:
wherein T is a set threshold;
for a field environment with stable illumination and simple background, the target can be well segmented by using the threshold value determined when the system debugging is completed. However, as long as the illumination condition of the scene changes, such as sunlight changes or adjustment of the self light source, the gray scale range of medicine and background changes, the previously set threshold value is not applicable to the current scene any more, so that the adaptive threshold value calculation method is needed for the application scene of gray scale changes, and therefore, the OTSU threshold value segmentation method can be adopted, and is the prior art, and therefore, the detailed description is not provided herein.
The national drug standard word label is used as a unique basis for drug label identification, and is positioned by adopting a positioning method combining mathematical morphology with line scanning for determining the national drug standard word label on the surface of a drug.
Researching the integral morphological characteristics of the image area, arranging structural elements for calculating and extracting image information, simplifying the number of images on the basis of preserving the image information, performing mathematical morphological operation including corrosion, expansion, opening and closing, then processing the medical image by adopting an 8-communication mode, performing morphological operation on the medical image, filling gaps among pixels, connecting the independent character communication domains into a large communication domain,
after the morphological treatment, more than one candidate area of the national drug quasi-word label can be obtained. In order to enhance the accuracy of the positioning effect, after filling the region by using mathematical morphology, a line scanning positioning method is used for the candidate region, and the two methods are combined to finally determine the positioning region. Because the medical image after threshold segmentation has different background colors in the character area and the background area, when the character area is scanned in a line, the phenomenon of black-white alternation can occur. The number of times each row hops is formulated as follows:
wherein m (p) is the sum of the hop times of the current line after scanning, n is the number of columns, and G (i) is any scanning line of the image.
In general, 13 orderly arranged characters are arranged in a Chinese medicine quasi-word label area on a medicine label, and normally, the black-and-white change of the characters is at least 2 times and at most 4 times when the characters pass each time in the line scanning process. Therefore, the jump range of one row of pixels of the Chinese medicine standard word on the medicine label is set as (26, 42).
And (3) carrying out line scanning judgment on the candidate region from top to bottom and from left to right, obtaining m (p) through calculation, judging the range of m (p), judging whether the range is in a character region (18, 36), if so, indicating that the scanning line is in the character region, adding 1 to the number of lines meeting the condition, namely t=t+1, counting the number of lines meeting the condition after the candidate region is scanned, if the ratio of the number of lines meeting the condition to the total number of lines is larger than 0.5, judging that the region is a target region, otherwise, repeating the steps, and finally extracting the character region to obtain the Chinese medicine standard word.
Uploading the obtained Chinese medicine standard words to the identification module to obtain information of medicines, controlling the medicine grabbing module to grab and placing the medicine standard words on the corresponding conveyor belt module, and simultaneously uploading the identified medicine information to the information processing module by the identification module, so that sharing of medicine data is guaranteed, and tracing is convenient.
The present invention is not limited to the above-mentioned embodiments, and any equivalent embodiments which can be changed or modified by the technical content disclosed above can be applied to other fields, but any simple modification, equivalent changes and modification made to the above-mentioned embodiments according to the technical substance of the present invention without departing from the technical content of the present invention still belong to the protection scope of the technical solution of the present invention.
Claims (6)
1. The medicine sorting system and method based on big data are characterized by comprising an image acquisition module for acquiring medicine photos, a medicine image segmentation module for removing irrelevant information, a medicine national medicine quasi-character positioning and recognition module for carrying out morphological processing, a medicine grabbing module for grabbing, a conveying belt module for conveying and an information processing module for uploading and tracking medicine information, wherein the image acquisition module selects a backlight illumination lighting mode to photograph medicines and conveys the photographed medicine images to the medicine image segmentation module, the medicine image segmentation module acquires interested areas in the medicine images and removes irrelevant information, the medicine national medicine quasi-character positioning and recognition module carries out morphological processing on the segmented image images, the medicine grabbing module analyzes and grabs corresponding medicines on corresponding conveying belts through the information transmitted by the medicine national medicine quasi-character positioning and recognition module, and the medicine national medicine quasi-character positioning and recognition module acquires the uploaded pictures in the analysis and acquisition mode comprising the following effective steps:
a. firstly, carrying out graying operation on an image;
b. denoising the photo subjected to the graying operation, and filtering out internal noise;
c. image enhancement is carried out on the photo after the image denoising operation;
d. correcting the photo subjected to the image enhancement operation, detecting the edges of the medicines, and removing the areas outside the edges;
e. performing mathematical morphology processing on the photographs after the rejection operation;
f. filling morphological areas of the photos subjected to mathematical morphological treatment;
g. scanning and positioning the filled photo;
h. identifying the image information of line scanning positioning to obtain a precisely positioned Chinese medicine quasi word sign region, and obtaining the information of the traceability code of the medicine;
in the step a, a weighted average method is adopted, and the calculation formula of the weighted average method is as follows:
f(i，j)＝0.299R+0.587G+0.114B
in order to avoid slower floating point number operation speed, an integer operation method is adopted:
f(i，j)＝(30R+59G+11B)/100
in the step b, a bilateral filtering method is adopted to remove the noise of the image,
wherein the weight coefficient w (i, j, k, l) depends on the product of the pixel location kernel and the pixel kernel, (i, j), (k, l) refer to the coordinates of two pixel points respectively,
wherein sigma d Standard deviation, sigma, of spatial Gaussian function r Is the standard deviation of the spatial domain gaussian function,
in the step c, a piecewise linear gray enhancement method is adopted, and the piecewise linear change function formula is as follows:
wherein the gray scale of f (x, y) of the input image is M, the gray scale of g (x, y) of the output image is N, a gray scale interval of the input image is [ a, b ], and a gray scale interval of the output image is [ c, d ];
in the step d, the picture is corrected by adopting Hough transformation, and the rotation formula is as follows
Wherein θ is the angle between a straight line on the photo and the horizontal direction, X is the abscissa before transformation, X is the abscissa after transformation, Y is the ordinate before transformation, Y is the ordinate after transformation,
and adopting threshold segmentation to reject, wherein the segmented image g (x, y) is as follows:
wherein T is a set threshold.
2. The big data based medical sorting system and method according to claim 1, wherein in the step b, a bilateral filtering method is adopted to filter and denoise the photos after the graying operation.
3. The big data based medical sorting system and method according to claim 2, wherein in step d, the optimal threshold T is determined by OTSU thresholding.
4. A big data based medical sorting system and method according to claim 3, wherein in step e, the images are processed by corrosion, expansion, opening and closing methods.
5. The big data based medical sorting system and method according to claim 4, wherein in the step f, the image is processed by 8-way communication, and then morphological operation is performed on the image to fill up gaps between pixels.
6. The big data based medicine sorting system and method according to claim 5, wherein in the step g, according to the difference of the background colors of the image in the character area and the background area, the national medicine standard is confirmed, and the calculation formula is as follows:
wherein m (p) is the sum of the hop times of the current line after scanning, n is the number of columns, and G (i) is any scanning line of the image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310327703.4A CN116281070A (en) | 2023-03-30 | 2023-03-30 | Medicine sorting system and method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310327703.4A CN116281070A (en) | 2023-03-30 | 2023-03-30 | Medicine sorting system and method based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116281070A true CN116281070A (en) | 2023-06-23 |
Family
ID=86803167
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310327703.4A Pending CN116281070A (en) | 2023-03-30 | 2023-03-30 | Medicine sorting system and method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116281070A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116504417A (en) * | 2023-06-28 | 2023-07-28 | 南京易联阳光信息技术股份有限公司 | Decision-making auxiliary method and platform based on medical big data |
| CN116976775A (en) * | 2023-07-25 | 2023-10-31 | 山东大舜医药物流有限公司 | Vaccine flow direction sorting and information monitoring system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106909941A (en) * | 2017-02-27 | 2017-06-30 | 广东工业大学 | Multilist character recognition system and method based on machine vision |
| CN109410026A (en) * | 2018-02-09 | 2019-03-01 | 深圳壹账通智能科技有限公司 | Identity identifying method, device, equipment and storage medium based on recognition of face |
| CN112347882A (en) * | 2020-10-27 | 2021-02-09 | 中德（珠海）人工智能研究院有限公司 | Intelligent sorting control method and intelligent sorting control system |
| CN115631128A (en) * | 2022-08-18 | 2023-01-20 | 郑州轻工业大学 | Circular medicine quantity detection method based on circular power theorem |
-
2023
- 2023-03-30 CN CN202310327703.4A patent/CN116281070A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106909941A (en) * | 2017-02-27 | 2017-06-30 | 广东工业大学 | Multilist character recognition system and method based on machine vision |
| CN109410026A (en) * | 2018-02-09 | 2019-03-01 | 深圳壹账通智能科技有限公司 | Identity identifying method, device, equipment and storage medium based on recognition of face |
| CN112347882A (en) * | 2020-10-27 | 2021-02-09 | 中德（珠海）人工智能研究院有限公司 | Intelligent sorting control method and intelligent sorting control system |
| CN115631128A (en) * | 2022-08-18 | 2023-01-20 | 郑州轻工业大学 | Circular medicine quantity detection method based on circular power theorem |
Non-Patent Citations (3)
| Title |
|---|
| 刘宏达: "基于机器视觉的药品分拣***研究", 中国优秀硕士学位论文全文数据库医药卫生科技；信息科技, 15 February 2022 (2022-02-15), pages 7 - 42 * |
| 张云博: "激光水平仪锥镜缺陷检测及分类研究", 中国优秀硕士学位论文全文数据库基础科技；信息科技, 15 January 2023 (2023-01-15), pages 12 - 14 * |
| 王朝轩: "基于机器视觉的西林瓶表面缺陷研究", 中国优秀硕士学位论文全文数据库工程科技Ⅰ辑；信息科技, 15 June 2022 (2022-06-15), pages 34 - 35 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116504417A (en) * | 2023-06-28 | 2023-07-28 | 南京易联阳光信息技术股份有限公司 | Decision-making auxiliary method and platform based on medical big data |
| CN116504417B (en) * | 2023-06-28 | 2023-09-12 | 南京易联阳光信息技术股份有限公司 | Decision-making auxiliary method and platform based on medical big data |
| CN116976775A (en) * | 2023-07-25 | 2023-10-31 | 山东大舜医药物流有限公司 | Vaccine flow direction sorting and information monitoring system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116281070A (en) | Medicine sorting system and method based on big data | |
| EP3309703B1 (en) | Method and system for decoding qr code based on weighted average grey method | |
| CN108920992A (en) | A kind of positioning and recognition methods of the medical label bar code based on deep learning | |
| CN111915704A (en) | Apple hierarchical identification method based on deep learning | |
| CN108416814B (en) | Method and system for quickly positioning and identifying pineapple head | |
| CN109146878A (en) | A kind of method for detecting impurities based on image procossing | |
| CN108875619A (en) | Method for processing video frequency and device, electronic equipment, computer readable storage medium | |
| JP6890427B2 (en) | Car number recognition device | |
| CN111680690A (en) | Character recognition method and device | |
| CN113034464B (en) | Visual real-time detection method for defects of liquid crystal display under multiple backgrounds | |
| CN110009615B (en) | Image corner detection method and detection device | |
| CN111145105B (en) | Image rapid defogging method and device, terminal and storage medium | |
| CN110032946A (en) | A kind of aluminium based on machine vision/aluminium blister package tablet identification and localization method | |
| CN112115948A (en) | Chip surface character recognition method based on deep learning | |
| CN112580383A (en) | Two-dimensional code identification method and device, electronic equipment and storage medium | |
| CN108520260A (en) | The recognition methods of visible foreign matters in bottled oral solution | |
| CN113012096A (en) | Display screen sub-pixel positioning and brightness extraction method, device and storage medium | |
| CN115587966A (en) | Method and system for detecting whether parts are missing or not under condition of uneven illumination | |
| Duong et al. | Vision inspection system for pharmaceuticals | |
| CN112547576A (en) | Vaccine sorting line ex-warehouse rechecking system | |
| CN111611866B (en) | Flame detection and identification method and system based on YCrCb and LAB color spaces | |
| CN108447072A (en) | A kind of image partition method and system of crystal grain | |
| CN107808382A (en) | A kind of PCB bar code dividing methods based on color saturation information | |
| CN108830834B (en) | Automatic extraction method for video defect information of cable climbing robot | |
| CN110298824A (en) | Squid automatic classification method based on color image and convolutional neural networks technology |
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 |