A liquid level detection method for medicine bottles based on image processing

A technology of liquid level detection and image processing, which is applied in the directions of image data processing, image analysis, liquid/fluid solid measurement, etc., can solve the problems of inability to obtain liquid level height and detection area, etc., so as to improve detection accuracy and make up for Insufficiency of the platform, the effect of eliminating pixel deviation

Active Publication Date: 2017-09-29
SHANDONG UNIV
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If the image is not corrected, the template matching cannot be performed, and the correct detection area cannot be obtained, and the correct liquid level height cannot be obtained

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
  • A liquid level detection method for medicine bottles based on image processing
  • A liquid level detection method for medicine bottles based on image processing
  • A liquid level detection method for medicine bottles based on image processing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0031] Such as figure 1 Shown, Step 1: Create a benchmark template image

[0032] Collect a typical medicine bottle image, the reference template image requires clear and universal feature elements, remove redundant pixel information in the original image, and properly cut the template image to ensure that the reference template image is templated with the detected bottle When matching, it can be found quickly and the matching time is shortened.

[0033] Step 2: Read the benchmark template image, extract the features of the benchmark template image, create a matching template and establish a matching template coordinate system; figure 2 Shown is the matching template image of the example of the present invention; matching templates need to be found as much as possible, and the features of matching templates are required to be possessed by every image...

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 method for detecting the liquid level of a medicine bottle based on image processing, which collects a typical medicine bottle image to create a reference template image, establishes a matching template and creates a matching template coordinate system; multiple collected images are detected The image of the medicine bottle is matched with the matching template one by one to obtain the displacement matrix of the image of the detected medicine bottle, and the corrected image of the detected medicine bottle image is obtained by using affine transformation; then the corrected image is segmented to obtain the detection area and extract The shape of the liquid level band; then based on the shape characteristics of the liquid level band, the lowest point of the liquid level is calculated, and the qualification of the medicine bottle is judged according to the relationship between the lowest point of the liquid level and the set threshold value of the lowest point of the liquid level α and the threshold value of the highest point β . The detection speed of the method of the invention is fast, and the total processing time of all images of a single bottle of liquid medicine is within 100ms. Its detection has sub-pixel level accuracy, which eliminates the pixel deviation caused by the vibration of the mechanical platform and greatly improves the detection accuracy.

Description

technical field [0001] The invention relates to machine vision detection technology, in particular to a liquid level detection method for medicine bottles based on image processing. Background technique [0002] Aqueous injection preparations are very common pharmaceutical preparations, and now my country's production of medical injections ranks among the top in the world. In the production process of water injection preparations, there are two factors that affect the quality of the medicine bottle leaving the factory. One factor is that there are tiny visible foreign objects inside the liquid medicine, and the other is caused by the quality of the non-medicine liquid. For example, the filling amount of the liquid medicine, the crack of the medicine bottle, the packaging of the medicine bottle, etc. While the machine detects the quality of the medicine bottle, the detection process of the capacity of the liquid medicine is essential. Traditional liquid level detection meth...

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 Patents(China)
IPC IPC(8): G01F23/292G06T7/136G06T7/13
Inventor 李玮韩毅赵翠芬赵运德孙晓琳吕晨光蒋润辉许腾飞曾海滨谭径元
Owner SHANDONG 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