Method for automatic parameterization of error recognition in image detection systems

An image detection and parameterization technology, applied in image data processing, image analysis, image enhancement and other directions, can solve the problems of lack of freedom, dependence, and high error rate

Active Publication Date: 2019-03-22
HEIDELBERGER DRUCKMASCHINEN AG
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The opposite disadvantage is the lack of degrees of freedom compared to a completely free manual setting
Furthermore, all known manual methods have the common disadvantage of being dependent on a human user whose analysis and thus the setting of the image detection method may contain errors
The more inexperienced the user and the more complex the choices regarding setting parameters, the higher the error rate
Furthermore, for reasons of time and thus cost, the parameters are generally not adjusted for each new printing job.

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
  • Method for automatic parameterization of error recognition in image detection systems
  • Method for automatic parameterization of error recognition in image detection systems
  • Method for automatic parameterization of error recognition in image detection systems

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] In a preferred embodiment, the user 13 can start the parameterization of the image detection within the framework of executing the printing task. Image detection is performed by a program such as figure 1 The display runs on a computer and includes a graphical user interface, which can be operated by a user 13 through a screen 12 connected to the computer. The user 13 can set through the screen 12 and the corresponding input and output instruments: whether he wants to perform the parameterization manually, whether he wants to use an automatic method, or whether he wants to modify the parameters of an already running method. Automatic parameterization process in figure 2 Shown in. If this parameterization is selected or started by the user 13, then the reference printed image 1 is derived from the setpoint value 10 for image detection. Because the basic measurement principle of image detection is based on the calibration between the nominal value 10 of the reference ima...

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 method for automatically parameterizing the error recognition of an image detection system by a computer, comprising the following steps: digitizing a reference image for determining nominal values; Homogeneous image areas with edges and non-homogeneous image areas with strongly structured image areas and multiple edges; low tolerance values ​​for homogeneous image areas of the digitized reference image are determined by statistical image analysis ( 3) and higher tolerance values ​​for non-uniform image areas; according to the position of the set-point value in the uniform or non-uniform image area, the calculated tolerance is assigned to the set-point value of each tolerance; The detection sensitivity is calculated according to the rated value and the respective tolerance of the rated value; the parameters of the image detection system are set according to the detection sensitivity; and the image detection is configured by using the parameters.

Description

Technical field [0001] The invention relates to a method for automatically parameterizing the error recognition of an image detection system. [0002] The invention is in the technical field of test automation. Background technique [0003] Until now, image detection methods to be parameterized have been used in order to check the completed printed product for possible errors within the framework of the execution of the printing task. Here, the printed image is scanned by means of a digital camera, transmitted to a server, and compared on the server with reference images generated from previous data. Depending on the parameterization of the comparison algorithm, the deviation between the re-digitized printed image and the reference image is recognized as an error and displayed here. [0004] For this parameterization, there are many possibilities according to the prior art. The most common possibility is to set the parameters manually by the user. Here, the user analyzes the refe...

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): G06T7/00
CPCG06T7/0004G06T2207/20012G06T7/41G06T2207/10008G06T2207/30144G06T7/0008G06T2207/20004G06T2207/30168H04N1/00015H04N1/00037H04N1/00068H04N1/00087
Inventor W·胡贝尔T·罗斯
Owner HEIDELBERGER DRUCKMASCHINEN AG
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