• Font Size:
  • A
  • A
  • A

ASK THE EXPERTS

Vision Systems Questions

Question Asked:

aside from Golden unit, what is the best way to correlate vision systems?

6 Answers

  • = Company Profile
  • = Answered Questions

Joseph Asor - Technical Sales Manager
SACMI
jasor [at] sacmiusa [dot] com
(515) 735-6000

Correlate? like a central hub control - where all activities can be monitored? At SACMI we offer Panorama supervisor which allows viewing in just one screen of all SACMI Vision systems installed in a production plant, reporting in real time the main information.

Tobias Kempe - Product Manager Twincat Vision
Beckhoff Automation GmbH & Co. KG
t [dot] kempe [at] beckhoff.com
+49 (5246) 963-7617

If you mean physical correlation, there need's the be some kind of calibration. If you mean data exchange, it depends heavily on the system you use. E.g. in Beckhoff's TwinCAT Vision you can develop multiple vision stations at once in one engineering environment and monitor all stations aggregated in one HMI.

David Dechow - Principal Vision Systems Architect
Integro Technologies
ddechow [at] integro-tech [dot] com
(704) 636-9666

Hello Jay; I believe by correlation you mean the actual validation of your machine vision inspection system's performance. This is a topic that I won't be able to answer in this limited Q&A format, but the short response is that in some applications a set of "golden" parts is the correct way to validate system performance. This works well particularly in cases where the vision task is a "go/no-go" inspection or an inspection for well-defined defects or features. For more subjective inspections, a regular statistical analysis of accepted and failed part samples can provide some validation of performance. For measurements, the vision system reliability should be validated using standard MSA (measurement systems analysis) techniques and statistics like a Gauge R&R, P/T (precision/tolerance) analysis or others. If you'd like to discuss further, feel free to contact me directly. Best Regards, David

Adi Weinberger - VP Sales and Marketing
Kitov.ai
adiw [at] kitov [dot] ai
+972544871238

Golden references and 3D computer vision algorithms are being used by our Smart Visual Inspection system only partially. Our software is also using various algorithms including AI-based algorithms, leveraging deep learning and machine learning to detect defects without relying on golden references. For example our system is trained to recognize screws, surfaces or ports and effectively identify defects. Our software is able to identify defects by looking for abnormal features which is not necessarily related to a golden reference. Therse are just few examples, for more detailed information, please do not hesitate to contact me directly at adiw@kitov.ai

Michael Beising - CEO
EVT Eye Vision Technology GmbH
mmb [at] evt-web [dot] com
+49 721 626 905 82

Based on a DXF File

Perry West - President
Automated Vision Systems, Inc.
perry [at] autovis [dot] com
(408) 267-1746

Jay -- your question mentions "systems" (plural). I infer from the plural that you want to know if you are getting nearly identical results from two or more nominally identical systems. A "Golden Unit" means, to me, a part that is as close to ideal as possible and should give a known result (within some tolerance band). Comparing the results from multiple systems to a Golden Unit only correlates one point on a spectrum of possible results. Yes, use a Golden Unit to start, and assuming good correlation between systems on the Golden Unit, collect a spectrum of other parts spanning the widest range of variations possible. Using those parts, look for correlation between systems. While the Golden Unit must give a prescribed result, these other parts do not need to give a prescribed result; each part gives results across the systems that agree within some tolerance.

Search AIA:


Browse by Products:


Browse by Company Type: