Aluminum/aluminum blister packaging tablet recognition and positioning method based on machine vision

A blister packaging, machine vision technology, applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems of laborious, low efficiency, etc., to achieve identification and positioning, efficient identification and positioning, and automatic work. Effect

Active Publication Date: 2019-07-19
XI AN JIAOTONG UNIV
View PDF14 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, if the packaging of the medicine is manually stripped, it is often laborious and inefficient, and cannot meet today's medical needs

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
  • Aluminum/aluminum blister packaging tablet recognition and positioning method based on machine vision
  • Aluminum/aluminum blister packaging tablet recognition and positioning method based on machine vision
  • Aluminum/aluminum blister packaging tablet recognition and positioning method based on machine vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] The present embodiment is described with colored tablet, as figure 1 shown, including the following steps:

[0060] Step 1: Image acquisition is required. The image acquisition uses a 5-megapixel industrial camera. The industrial camera is vertically arranged directly above the drug stripping machine station. It is illuminated by fluorescent lamps and the illumination is kept uniform; the aluminum / aluminum blister packaging drug is removed in the field of view of the camera. There is no debris outside the board, the edge of the aluminum / aluminum blister package is parallel to the field of view of the camera, and the background is black to ensure uniform lighting, clear images, and strong contrast. See the results figure 2 .

[0061] Step 2: Perform region-of-interest extraction to segment the aluminum-plastic blister pack medicine board from the camera's field of view. First, the color image needs to be converted to a grayscale image according to formula 1.

[0062]...

Embodiment 2

[0087] Embodiment 2: For white medicines, step 4 has the following differences. White medicines are similar in color to aluminum-plastic packaging, and it is difficult to judge visual significance, but image segmentation can be better achieved by using histogram equalization.

[0088] First, use formula 1 to convert the image grayscale;

[0089] In order to eliminate the influence of the texture of the aluminum-plastic package, a large-scale median filter is performed on a digital image sequence X j (-∞

[0090] Histogram equalization is to modify the...

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 an aluminum / aluminum blister packaging tablet recognition and positioning method based on machine vision. Tablets are automatically recognized and positioned through words. Themethod comprises the steps of image acquisition, ROI extraction, color pixel statistics, saliency object (tablet) extraction, tablet contour recognition, contour centroid extraction, coordinate sorting, clamp position positioning and the like. Through the steps, aluminum / aluminum blister packaging tablets of different specifications can be adaptively identified, the quantitative output of the positions of the tablets is realized, and the production efficiency of the medicine stripping machine is improved. According to the method for carrying out tablet detection by utilizing machine vision, the automatic work of a medicine peeling machine can be realized, the colored and white tablets classified by statistical information are used for identification, and various working condition requirements can be flexibly met. And finally, an LAB color space frequency domain method is used for extracting the visual saliency object, so that the recognition and positioning of the color tablets can beefficiently achieved.

Description

[0001] 【Technical field】 [0002] The invention belongs to the field of identifying tablets in aluminum / aluminum blister packages, in particular to a machine vision-based identification and positioning method for tablets in aluminum / aluminum blister packages. [0003] 【Background technique】 [0004] The aluminum-plastic blister packaging form of medicines is widely used in the pharmaceutical industry because of its independent sealing and convenient taking of medicines. At present, in major hospitals and pharmacies, when some medicines need to be used in large quantities, it is often necessary to remove the packaging shell of the medicines to facilitate use. However, if the packaging of the medicine is manually stripped, it is often time-consuming and laborious, and the efficiency is low, which cannot meet the current medical needs. [0005] Machine vision is the use of computers to realize human visual functions, that is, the perception, recognition and understanding of objec...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/34G06K9/46G06K9/32
CPCG06V20/20G06V10/26G06V10/25G06V10/462
Inventor 要义勇王世超辜林风高射
Owner XI AN JIAOTONG UNIV
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