Deep learning-based method for positioning and recognizing medical label barcodes

A technology of deep learning and identification method, which is applied in the field of positioning and identification of medical label barcodes, which can solve the problems of difficult barcode positioning and uneven illumination.

Active Publication Date: 2018-11-30
CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF3 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The invention discloses a method for positioning and identifying barcodes of medical labels based on deep learning. The inv

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Deep learning-based method for positioning and recognizing medical label barcodes
  • Deep learning-based method for positioning and recognizing medical label barcodes
  • Deep learning-based method for positioning and recognizing medical label barcodes

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0080] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments. The present invention is illustrated by taking the DataMatrix two-dimensional code, drug supervision code (Code-128 code) and commodity barcode (EAN-13 code) on the medical packaging as examples, but the present invention is not limited thereto.

[0081] In this example, the camera adopts an area array Gigabit CCD camera with a resolution of 1080*960, the lens is a 6mm wide viewing angle Computar lens, and the light source is a ring-shaped LED light source with a radius of 10cm;

[0082] like figure 1 As shown, a method for positioning and identifying barcodes of medical labels based on deep learning includes the following steps:

[0083] Step 1: Collect the barcode image of the medicine box label on the high-speed production line, denoted as Image0, such as Figure 3-1 and Figure 3-2 As shown in 1(a) and 2(a);

[0084] Step 2: Input the ima...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a deep learning-based method for positioning and recognizing medical label barcodes. Through the method, the problem that the barcode positioning is difficult under complicatedcircumstances of uneven illumination, twist deformation and the like is solved; and on the basis, the problem of correcting linear distorted two-dimensional barcodes is solved, the barcode position can be effectively positioned under the complicated circumstances and distortion correction and detail processing are carried out to obtain a high-quality barcode binary image and realize accurate reading. Identified objects in the method disclosed by the invention comprise Data Matrix two-dimensional codes, commodity barcodes (EAN (European Article Number)-13 codes) and drug electronic supervisioncodes (Code-128 codes).

Description

technical field [0001] The invention belongs to the field of automatic identification, and in particular relates to a positioning and identification method of a medical label barcode based on deep learning. Background technique [0002] Barcode technology is widely used in the pharmaceutical industry. Laser coding is used to give drugs unique codes to realize the serialization of drugs and build a global drug traceability system, which greatly improves the safety of medicine and health. For example, China's drug electronic supervision code and the Data Matrix QR code in Europe and the United States all indirectly or directly provide information such as the production date, batch number, and serial number of the drug. Barcodes can be found and read because of their own positioning features. Due to its wide use, the application scenarios are complicated. Barcodes can appear distorted, defaced, etc. In the case of losing part of the positioning features, or weakening the pos...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K7/14
CPCG06K7/1443G06K7/146
Inventor 张辉时国良邓广梁志聪赵淼刘理钟杭
Owner CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap