Unlock instant, AI-driven research and patent intelligence for your innovation.

Box surface defect detection and identification method and device based on machine vision

A technology of machine vision and defect detection, which is applied in the field of packaging, can solve the problems of carton quality decline, manual inability to effectively complete, and affect the degree of carton identification, etc., to achieve the effect of saving manpower and material resources and a good recycling industry chain

Pending Publication Date: 2022-01-14
HUBEI CHINA TOBACCO IND
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Heavy defects such as puncture, fracturing, adhesive failure, etc. will reduce the quality of the carton and affect the actual use
Light defects such as blurred printing, stains, appearance defects, etc. do not affect the use, but will affect the carton identification. Therefore, it is necessary to accurately detect all kinds of defects to achieve the purpose of recycling cartons, protecting the environment and reducing costs.
[0004] As the demand for packaging corrugated boxes gradually increases, it is impossible to effectively complete such a large number of products and high-efficiency testing tasks with manual labor alone, and manual identification of carton defects and whether the carton can be reused is often made based on experience. Judgment, there is a lack of a more unified criterion for judging

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
  • Box surface defect detection and identification method and device based on machine vision
  • Box surface defect detection and identification method and device based on machine vision
  • Box surface defect detection and identification method and device based on machine vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0060] According to the first aspect of the present invention, there is provided a machine vision-based box surface defect detection and recognition method, such as figure 1 As shown, it is a flow chart of the machine vision-based box surface defect detection and recognition method, including:

[0061] Step S101: building a detection model, and using reference data to complete the training of the detection model.

[0062] In the embodiment of the present invention, the object detected by the detection model is a corrugated box, and the data obtained is in the form of a picture, and the acquisition method is the same as the actual situation, all of which are obtained by machine vision. The staff can pre-prepare the original data based on corrugated boxes, that is, the original picture, and mark the defects on the original picture in batches to form reference data. It is understandable that the reference data should include at least two data structures, one is the original pict...

Embodiment 2

[0128] According to the second aspect of the present invention, a machine vision-based device for detecting and identifying surface defects of a box body is provided. Such as figure 2 As shown, it is a modular block diagram of the machine vision-based box surface defect detection and recognition device, including:

[0129] Building block 201: building a detection model, and using reference data to complete the training of the detection model;

[0130] Detection calculation module 202: obtain the surface data of the box to be tested, input the trained detection model, and output the detection data;

[0131] Report generation module 203: calculate and output defect data on the surface of the box to be tested according to the test data, and output a defect report.

[0132] It can be understood that all the devices provided in the embodiments of the present invention are applicable to the method described in the first embodiment, and the specific functions of each module can re...

Embodiment 3

[0134] An electronic device provided by an embodiment of the present invention is used to implement the method described in Embodiment 1. Figure 4 It is a schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention. The electronic device may include: at least one central processing unit, at least one network interface, control interface, memory, and at least one communication bus.

[0135] Among them, the communication bus is used to realize connection communication and information exchange between various components.

[0136] Wherein, the network interface may optionally include a standard wired interface and a wireless interface (such as a Wi-Fi interface).

[0137] Wherein, the control interface is used to transmit control instructions.

[0138] Wherein, the central processing unit may include one or more processing cores. The central processing unit uses various interfaces and lines to connect various parts in ...

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 box surface defect detection and identification method and device based on machine vision, and the method comprises the steps: building a detection model, and completing the training of the detection model through reference data; acquiring surface data of the to-be-detected box body, inputting the surface data into the trained detection model, and outputting detection data; and calculating and outputting defect data of the surface of the to-be-detected box body according to the detection data, and outputting a defect report. According to the method, the detection and recognition of the surface defects of the box body are realized based on the target detection of the deep neural network, the accurate and efficient defect recognition of the data based on the manufactured surface defect data set of the box body is realized, the characteristics of the deep surface defects of the box body are extracted, the specific defect types are recognized, and the area of the defects is calculated; therefore, the recycling of the box body is scientifically judged.

Description

technical field [0001] The invention relates to the field of packaging technology, and can be applied to the detection, identification and area calculation of common defects on the surface of corrugated boxes, and in particular to a method and device for detecting and identifying defects on the surface of a box based on machine vision. Background technique [0002] In recent years, corrugated boxes have become more and more widely used in packaging applications in various industries. The increasingly widespread market demand and the urgent need to protect the environment have made people put forward higher requirements for the quality assurance of corrugated boxes. Quality testing has put forward urgent requirements. [0003] Various quality indicators for corrugated boxes (such as appearance indicators: logo, printing, comprehensive size, squareness, combination, nail distance, indentation line, mounting, cutting edge, box corner, closing, flap folding resistance; Physica...

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): G06T7/00G06T7/62G06N3/04G06N3/08
CPCG06T7/0008G06T7/62G06N3/08G06T2207/20081G06T2207/10004G06N3/045
Inventor 贾伟萍刘文婷黄轲王波王娜陈琳廖宇
Owner HUBEI CHINA TOBACCO IND