Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A visual detection method of a visible foreign body in a large infusion medicine

A technology for visual inspection and large infusion, applied in image analysis, image enhancement, instruments, etc., can solve problems such as processing errors, and achieve the effect of reducing the impact of weak foreign objects

Inactive Publication Date: 2019-01-08
SHANDONG UNIV
View PDF2 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the vibration or shaking during the acquisition process, the bright spots on the bottle wall were extracted, which introduced errors for subsequent processing

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 visual detection method of a visible foreign body in a large infusion medicine
  • A visual detection method of a visible foreign body in a large infusion medicine
  • A visual detection method of a visible foreign body in a large infusion medicine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] The purpose of this embodiment 1 is to provide a visual detection method for visible foreign matter in large infusion medicines, such as figure 1 As shown, the method includes the following steps:

[0068] Step 1: Image acquisition.

[0069] Continuously collect N frames of large infusion bottle sequence images, such as figure 2 shown.

[0070] Step 2: Histogram equalization, enhance image contrast, such as image 3 shown.

[0071] After collecting N frames of large infusion bottle sequence images, formula (1) is used to perform histogram equalization processing on each frame image to enhance image contrast.

[0072] The histogram equalization formula is:

[0073]

[0074] In the formula, m k is the gray value of the processed image, n k is the gray value of the input image, p(n i ), i=1,2,..., L represents the gray value n in the input image i The frequency of occurrence, i=1,2,...,k, k=1,2,...,L, L is the gray level of the image, r i is the gray value n ...

Embodiment 2

[0117] The purpose of Embodiment 2 is to provide a computer-readable storage medium.

[0118] In order to achieve the above object, the present invention adopts the following technical scheme:

[0119] A computer-readable storage medium, in which a plurality of instructions are stored, and the instructions are suitable for being loaded by a processor of a terminal device and performing the following processing:

[0120] Image Acquisition;

[0121] Histogram equalization to enhance image contrast;

[0122] Threshold segmentation, select the appropriate threshold to segment each frame of image, used to identify the area of ​​interest and non-target area;

[0123] Sequentially process each frame of the segmented image to obtain the region of interest of each frame of image;

[0124] Perform Gaussian filtering on the region of interest of each frame image;

[0125] Calculate the rotation angle and horizontal translation of the large infusion bottle for image registration;

[...

Embodiment 3

[0129] The purpose of Embodiment 3 is to provide a terminal device.

[0130] In order to achieve the above object, the present invention adopts the following technical scheme:

[0131] A terminal device, including a processor and a computer-readable storage medium, the processor is used to implement instructions; the computer-readable storage medium is used to store multiple instructions, and the instructions are suitable for being loaded by the processor and performing the following processing:

[0132] Image Acquisition;

[0133] Histogram equalization to enhance image contrast;

[0134] Threshold segmentation, select the appropriate threshold to segment each frame of image, used to identify the area of ​​interest and non-target area;

[0135] Sequentially process each frame of the segmented image to obtain the region of interest of each frame of image;

[0136] Perform Gaussian filtering on the region of interest of each frame image;

[0137] Calculate the rotation angl...

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 visual detection method of a visible foreign body in a large infusion bottle medicine. N-frame serial images of large infusion bottle are continuously collected, and the histogram equalization is processed, an appropriate threshold value is selected to segment each frame image, each frame image after segmentation is processed in turn to obtain a ROI of each frame image,the rotation angle and the horizontal translation of a large infusion bottle are calculated, and each frame image of the sequence image is corrected in turn according to rotation angle and horizontaltranslation of the large infusion bottle; differential processing is performed on the corrected sequence images to complete the detection of foreign bodies. The method calculates the rotation angle and the horizontal translation amount of the large infusion bottle for image registration, eliminates the influence of vibration on the image, utilizes the bilinear interpolation method to sequentiallycorrect each frame image of the sequence image, performs the differential processing on the sequence image, and can detect the visible foreign bodies in the large infusion bottle with high efficiencyand accuracy.

Description

technical field [0001] The invention relates to the field of machine vision detection, in particular to a visual detection method for visible foreign objects in large infusion medicines. Background technique [0002] Because the liquid in the large infusion bottle is colorless and transparent, there may be foreign matter such as glass shavings, fibers, hair, and floating objects in the liquid. Generally, the foreign matter appears in the image with only a few or a dozen pixels. There are reasons such as relief on the wall, uneven surface, and bubbles generated by liquid movement during online detection. Therefore, there are bright spots in the grayscale image collected by the camera, which are very similar to foreign objects; Reflective interference will be generated. Due to the interference of the industrial production site, some interference noise will be mixed in the image. These interference information and false foreign object information have caused greater difficultie...

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): G06T7/254G06T7/215
CPCG06T7/215G06T7/254G06T2207/10016G06T2207/20224
Inventor 李玮韩毅陈财雷鸣汪静雷晟暄
Owner SHANDONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com