Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A paper defect detection method based on local brightness invariance priori

A local brightness and defect detection technology, which is applied in the direction of optical defect/defect, image data processing, instrument, etc., can solve the problem of insurmountable motor speed limit and stability, the failure rate of mechanical parts and detection parts is difficult to reduce, maintenance and Problems such as high debugging cost, achieve the effect of low performance requirements, high accuracy, and low detection cost

Active Publication Date: 2019-06-14
浙江企银印务科技有限公司
View PDF7 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

First of all, the line scanning scheme can only be applied to the unfolded scanning of the paper tube, and cannot be directly used for the detection of the cut paper; secondly, no matter how high the speed of the line scanning camera is, it cannot overcome the speed limit and stability problems caused by the motor rotation. The scanning of the paper tube needs to ensure local uniform speed, so the sensitivity of the paper tube speed control system is high, which further increases the complexity of the system. The failure rate of mechanical components and detection components in the detection system is difficult to reduce, and the maintenance and debugging costs are high.
[0004] The cost of using line scan cameras to scan and detect paper defects is very high, while ordinary rolling shutter area scan cameras have been popularized in most electronic products in our lives, such as notebook cameras, mobile phone cameras, security cameras, etc.

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 paper defect detection method based on local brightness invariance priori
  • A paper defect detection method based on local brightness invariance priori
  • A paper defect detection method based on local brightness invariance priori

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0075] A paper defect detection method based on the local brightness invariance prior includes the following steps:

[0076] Step 1. Make the color area array camera face the surface of the paper to be detected. The surface of the paper to be detected is located in the field of view of the color area array camera. Take a picture with the color area array camera to capture a frame of color image of the paper surface to be detected. The pixel format of the color image Use RGB components to represent;

[0077] Step 2: Use a convolution template with local brightness invariance prior to perform non-linear grayscale operation on all pixels of the color image in the mask of the convolution template, and finally obtain the pixels corresponding to the convolution window; according to 1× The 1 convolution operation and the 3×3 convolution operation respectively obtain two grayscale images;

[0078] Step 3, dividing the corresponding position pixels of the two grayscale images to obtai...

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 a paper defect detection method based on the local brightness invariance priori, which comprises the following steps of 1, photographing the surface of paper to be detected byusing a color area array camera, and capturing a frame of color image with a pixel format of RGB components; 2, carrying out nonlinear graying operation on all pixels of the color image in the mask of the convolution template by using a convolution template with local brightness invariance priori, and finally obtaining pixels corresponding to the convolution window; according to the 1*1 convolution operation and the 3 * 3 convolution operation, obtaining two gray level images respectively; 3, carrying out corresponding position pixel division on the two grayscale images to obtain a grayscaleimage; 4, performing 3 * 3 Fourier convolution operation on the grayscale image; 5, performing gradient morphological operation on an operation result; 6, performing thresholding processing to obtaina paper defect detection result. According to the present invention, a common light source and an area array camera can be used for detecting paper defects, and a detection system is low in complexity, high in accuracy and low in cost.

Description

(1) Technical field: [0001] The invention relates to a paper defect detection method, in particular to a paper defect detection method based on local brightness invariance prior. (two), background technology: [0002] The defects of paper mainly include creases, scratches, dirt, etc. The existence of these defects cannot guarantee the smoothness and solid color of the paper. The printing and packaging industry usually uses an expensive and special inspection device to detect many defects in the paper. Most of the inspection solutions for printing are mainly based on ultra-uniform LED lighting systems or bar light sources, using line scan cameras to scan the paper operation to overcome the non-uniformity of illumination that occurs with the above-mentioned light sources in a two-dimensional environment. This solution mainly uses a high-speed line scan camera to overcome the stroboscopic phenomenon caused by the LED lighting system. The stroboscopic phenomenon will cause regu...

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): G06T7/00G06T7/187G01N21/88
Inventor 刘咏晨毕成
Owner 浙江企银印务科技有限公司
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
Eureka Blog
Learn More
PatSnap group products