FEATURE Machine vision
Machine vision without the programming skills
MVTec’s MERLIC enables any company to quickly and easily use the benefits of machine vision A
utomation in the industrial sector is advancing fast and machine vision is a big part of
personnel and programming skills frequently stop companies from using machine vision.
Machine vision meets challenges Machine vision has become an integral part operational quality assurance, since it reliably detect defects in products. The technology also aids robots in gripping, handling and depositing objects accurately, eliminating the need for human input. It operates quickly and precisely, processing large amounts of digital image data in milliseconds. Hence, thanks to modern machine vision, throughout assembly, quality assurance or
Easy to use
Integrating machine vision applications is usually a complex task, but easy-to- use machine vision software like MVTec MERLIC provides a suitable solution. Since no programming skills are required for machine vision software, industrial image processing can also provide a valuable contribution to digitisation for small to medium sized companies personnel or corresponding programming skills are often scarce.
As an all-in-one solution, MERLIC can be easily integrated into factories thanks to its support for all common industry standards and its compatibility with a wide range of hardware. It includes all the needed functions like image acquisition, image processing and visualisation displayed for easy viewing and assessment.
Particularly important, especially for machine vision beginners without programming skills, is its ease of use. The tools required to create the machine vision application can conveniently be selected
32 July/August 2024 | Automation
with the drag & drop functionality available in the MERLIC graphical user interface. This allows complete machine vision applications to be developed and operated quickly without writing any code. Simple integration into existing control concepts is also possible at any stage.
MERLIC in practice MVTec MERLIC also addresses the intelligence in the industrial context with its integrated deep learning technologies. Via self-learning algorithms MERLIC achieves outstanding results in object and defect detection. If neither the amount of high-quality image data nor the powerful hardware required for training are available, or if one is dealing with very high production speeds, classical rule-based methods are often the better alternative. MERLIC also provides a variety of industry-proven processing tools for this purpose.
When it comes to inspecting complex parts, like metal springs for example, deep-learning-based technologies such as global context anomaly detection
yield excellent results. In this process, a powerful camera captures an image from above for each component; see image above. On the captured images with the metal springs, global context anomaly detection performs the inspection. MERLIC’s deep-learning technology consists of two neural networks: The “local” checks for small-scale defects like scratches, cracks or contaminations. The “global” network goes a step further and checks for logical defects, such as bent or missing brackets. By combining the two, global context anomaly detection determines the anomaly score, which threshold determines product quality. If the anomaly score is above this threshold, it indicates a defective component that is then rejected.
The inspection process using deep- learning technology provides a major advantage over using a rule-based method. In a rule-based approach, all possible types of defects must be on “bad images”. In contrast, for training MERLIC’s deep learning methods, only “good images” are needed.
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 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58
