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

Cigarette filter stick identification method and system based on machine vision

A cigarette filter rod and machine vision technology, applied in the field of image recognition, can solve the problems of manual marking and low work efficiency, and achieve the effects of avoiding misidentification, improving work efficiency, and improving accuracy

Pending Publication Date: 2022-03-04
CHINA TOBACCO GUANGDONG IND
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to overcome the defects of manual marking of a large number of data samples and low work efficiency described in the above prior art, the present invention provides a method for identifying cigarette filter rods based on machine vision, and a method for identifying cigarette filter rods based on machine vision system

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
  • Cigarette filter stick identification method and system based on machine vision
  • Cigarette filter stick identification method and system based on machine vision
  • Cigarette filter stick identification method and system based on machine vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] This embodiment proposes a cigarette filter rod recognition method based on machine vision, such as figure 1 Shown is a flow chart of the machine vision-based cigarette filter rod recognition method of this embodiment.

[0033] In the cigarette filter stick recognition method based on machine vision proposed by the present embodiment, the following steps are included:

[0034] S1. Collect vertical cross-sectional images of cigarette filter rods.

[0035] In this embodiment, an industrial camera is used to obtain a vertical cross-sectional image of a cigarette filter rod with a fixed focal length and a fixed pixel size.

[0036] Such as figure 2 Shown is the vertical cross-sectional image of the cigarette filter rod collected in this embodiment. The content of the rectangular box is the noise interference outside the container.

[0037] S2. Perform preprocessing on the collected image, and intercept the filter stick area in the image.

[0038] In this embodiment, t...

Embodiment 2

[0067] This embodiment adopts the cigarette filter rod recognition method based on machine vision proposed in Embodiment 1, and adopts the currently commonly used filter rod quantity detection method based on the canny operator, for common filter rods, granular filter rods and thin filter rods that are common in the market at present. The filter rods are individually identified for cigarette filter rods.

[0068] Among them, the cut surface of the ordinary filter rod is solid color, the diameter is about 7.66mm, and the number of each sieve is about 4300-5000. The cut surface of the granular filter rod contains particles with a diameter of about 7.66 mm, and the number per sieve is about 4500 to 5000. The cut surface of the thin filter rod is solid color, the diameter is about 5.35mm, and the number of each sieve is about 9150-9350.

[0069] First, for ordinary filter sticks, the cigarette filter stick identification method based on machine vision proposed in this embodiment ...

Embodiment 3

[0098] This embodiment proposes a system for recognizing cigarette filter rods based on machine vision, and applies the method for recognizing cigarette filter rods based on machine vision proposed in Embodiment 1. Such as Figure 9 Shown is the architecture diagram of the machine vision-based cigarette filter stick recognition system of this embodiment.

[0099] In the cigarette filter stick recognition system based on machine vision proposed in this embodiment, include:

[0100] Image collection module 1, for collecting the vertical section image of cigarette filter rod;

[0101] A preprocessing module 2, configured to preprocess the collected images;

[0102] Filter stick area extraction module 3, for intercepting the filter stick area image in the image;

[0103] The filter rod identification module 5 is used to identify the filter rod, obtain the edge, center and radius of the filter rod through edge detection and circle detection, and mark the edge and center of the f...

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 relates to the technical field of image recognition, and provides a cigarette filter stick recognition method and system based on machine vision, and the method comprises the following steps: collecting a vertical section image of a cigarette filter stick; the collected image is preprocessed, and a filter stick area in the image is intercepted; the filter stick is identified based on the intercepted filter stick area, the edge, the circle center and the radius of the filter stick are obtained through edge detection and circle detection, and the edge and the circle center of the filter stick are marked in the filter stick area image; carrying out abnormity elimination on the identified filter sticks; and calculating the number of circle centers and / or filter stick contours in the filter stick area image through image detection to obtain a cigarette filter stick counting result. Accurate cigarette filter stick positions and counting results can be obtained without a large amount of manual correction operation.

Description

technical field [0001] The present invention relates to the technical field of image recognition, in particular to a method and system for recognizing cigarette filter rods based on machine vision. Background technique [0002] At present, there are two main types of image-based filter rod counting methods in the industry. One is area method myopia estimation. A filter rod counting method and device based on image acquisition and recognition proposed by et al. However, the essence of the area method is an estimation method, the accuracy rate is low, and it cannot be manually corrected in the later stage, and the evaluation of its accuracy rate is costly. There is also a recognition algorithm based on machine learning, such as the circle-like object recognition and counting detection algorithm based on machine vision and deep learning proposed by Zhang Kun et al. and a cigarette filter rod counting method based on AA R2Unet and HMM. The algorithm is accurate. The rate is 98...

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): G06T7/00G06T7/12G06T7/13G06T7/168G06T7/181G06T7/62G06T7/66
CPCG06T7/0004G06T7/12G06T7/13G06T7/168G06T7/181G06T7/62G06T7/66G06T2207/30242G06T2207/20061
Inventor 王征勇曾赛周德祥姜宇卉
Owner CHINA TOBACCO GUANGDONG IND
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