FEATURE Machine Vision
Rising to the machine-vision data challenges
Jim Witherspoon, Product Manager for machine vision at Zebra Technologies, discusses the best ways to capture and annotate data with modern machine vision systems
T
he interest, innovation and buzz around various types of artifi cial intelligence (AI) – machine learning, neural networks and
computer vision (CV) – are well recognised. What is less recognised, however, is the renewed interest and application of modern machine vision (MV) systems by manufacturers and warehouse operators. MV and CV are both intelligence-based systems used for image capture, processing and analysis, but the speed and level at which intelligence is gathered, distributed and applied diff erentiates the two. MV systems are self-contained, i.e., data doesn’t have to be sent to a back-offi ce system for processing, since image capture and analysis occur directly on the line.
On the other side, CV is often used as a back-end processing platform for front- line image capture. Though CV elicits fast decision making and action, the lead times are longer, given the depth and breadth of data being processed and moving through the system.
Every company looking to implement MV systems today must decide how to share and manage image datasets and use them most benefi cially to deliver quality, actionable results on a consistent basis – data has become as important as code. However, while there are industrial practices for code management, progress needs to be made for managing image data. Now there are new solutions to help industrial imaging professionals to think and act like data scientists.
32 November 2022 | Automation
New machine-vision systems Zebra Technologies launched its new line of MV cameras and fi xed industrial scanners (FIS) in mid-2021. Zebra’s complementary software, Zebra Aurora, pairs with Zebra’s MV/FIS products to facilitate the set up and confi guration of track-and-trace and quality inspection solutions. Zebra Aurora was engineered from the
ground up, to be easy to set up, install and run. Zebra wants the software to be modern, with a reduced number of clicks and mouse movements for users. Within the fi rst few minutes of navigating the software, users get to experience new and intuitive ways to work with the images they’ve captured. Scroll bars have been eliminated and the interface provides an immersive experience akin to photo editor rather than traditional MV software. In addition, Zebra also made the navigation process intuitive for MV inspection and barcode scanning experts, as well as novice users. To do this, the Zebra MV team broke down the process of creating and confi guring the software as follows:
• Stage one is ‘Capture’, to set up the exposure, lighting and triggering. • The second stage is ‘Build’, to easily add and confi gure MV/FIS tools. • The third stage is ‘Connect’, which gets the image data from the MV/FIS camera to the host system.
For example, with Capture a user can
create 16 individual images to ensure that every inspection or barcode read has the
perfect lighting. Zebra calls this feature “ImagePerfect+”. Often, parts are not evenly lit or have inspections at diff erent depths and focus, necessitating changes to exposure settings. ImagePerfect+ allows adjustment of the image settings, links the inspection tool with the ImagePerfect+ data bank, and gives a pass or fail response with a single trigger pull. By eliminating the need for multiple job changes or tracking, ImagePerfect+ can save hours when installing a system. Build off ers QuickDraw for using drawing tools directly on the image. This feature alone eliminates fi ve clicks and drags when added as a tool.
Another unique tool is the Golden Image Compare, developed to keep the system up and running while eliminating downtime, should something happen to the camera or setup. This feature allows a user to capture an image at the time of setup – the time when the system works best – and saves it. In a malfunction, the user can access Golden Image Compare to get a side-by- side view of the Golden Image vs the new one. If the camera was bumped, or a light is no longer working, or if key settings were changed, Golden Image Compare helps users quickly identify the problem and get the system back up and running immediately.
CONTACT:
Zebra Technologies
www.zebra.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
