FEATURE Machine Vision
Overcoming the challenges of inspecting highly-refl ective moving parts
Quality assurance is an essential step of every manufacturing process; however, inspecting highly-reflective moving parts can be challenging for traditional machine vision solutions. By Ofer Nir, VP of Product and Marketing at Inspekto
Left to right: PCB before and after using Inspekto’s anti-reflection technology M
any parts and modules are made of highly-refl ective materials, such as metals and plastic. However,
during their manufacture, light refl ects from their surfaces towards the camera, causing image saturation and loss of detail. High dynamic range (HDR) is one method that reduces these refl ections. It is a technique used to reproduce a greater dynamic range of luminosity than traditionally possible with standard digital imaging or photographic techniques. Yet, an even bigger challenge is when the light source is an embedded lighting module that is part of the inspection system, with an illumination path that is parallel to the camera’s line of sight. In these cases, the likelihood and intensity of back refl ection increase.
HDR is not adequate in this scenario,
requiring state-of-the-art proprietary anti-refl ection techniques. Here, multiple images are generated using diff erent directional lighting modules. The images are then fused together to create a single, refl ection-free image.
Due to complexity of this process, most existing anti-refl ection techniques do not perform robustly enough for use on a production fl oor. The challenge is
30 November 2022 | Automation
compounded with moving parts. Until recently, it was considered impossible to fuse together multiple images where the part has a diff erent location and spatial orientation in each image. Inspekto has solved this problem by leveraging several new developments to create a unique, patent-pending anti- refl ection technology. The fi rst is its Autonomous Machine
Vision AI (AMV-AI) technology, containing three AI-based engines working in tandem. The fi rst of the three engines is the Acquisition AI engine, which dynamically adapts the parameters of an electro-optic system to a specifi c application, in real time. The second engine recognises the parts, whilst the third determines whether it is good or defective by comparing it to the characteristics of a perfect part that have been memorised during setup. The second is its ultra-fl exible electro- optic system, the INSPEKTO S70, which provides a large playing fi eld for the Acquisition AI engine to tailor the inspection profi le to the requirements of each application. The INSPEKTO S70 off ers a wide variety of parameters that can be autonomously and specifi cally adjusted by the system’s AI to the product being inspected, ensuring high accuracy.
Real-time, dynamic adjustments are performed autonomously to the full set of electro-optic parameters.
Unique technology Inspekto’s anti-refl ection technology is unique in several aspects: it creates no fl ickering that might disturb or inconvenience employees working near the INSPEKTO S70. It also combines unique anti-refl ection and HDR into an integrated technology, to dramatically reduce refl ection from both external light sources and the INSPEKTO S70’s integrated illumination system. In combination, Inspekto’s anti-refl ection technology enables the accurate inspection of highly-refl ective, moving parts without the traditional constraints associated with this process. This makes the INSPEKTO S70 the only industrial visual inspection solution able to perform in these scenarios, opening the doors of automated quality assurance to a wide variety of industrial processes in many diverse industries.
CONTACT:
Inspekto
www.inspekto.com
automationmagazine.co.uk
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50
