Many key tasks in the manufacture of products, including inspection,
orientation, identification, and assembly, require the use of visual
techniques; but implementers need to carefully match machine vision options
with application requirements.
What makes a machine vision system robust? Robustness in this context is more than just reliability. It is a reliability that is maintained within the natural variations of the environment in which the system is being used.
They’re already widely used in offices or at ticket vending machines, but they’re only known to insiders within the industry: documents, cards or bank notes are often read and checked by scanners. Mitsubishi Electric has responded to the needs of the industry and has made this technology available for production, with the launch of a high-speed version of its Contact Image Sensor (CIS), distributed under the name Mitsubishi Electric Line Scan Bar.
Polarisation imaging can reveal information on physical properties such as stresses in plastic or glass. STEMMER IMAGING polarisation expert Jan Sandvoss gives us an insight into this powerful technique and its possibilities.
It is easy to overlook the contribution that optics make to a system; beyond
basic lens parameters such as focal distance, the details can seem confusing.
This Tech Tip presents a basic guide to optics to help users to make an
informed choice and get the best performance out of their existing systems.
High accuracy machine vision applications are dependent on the production of reproducible, high quality images, whether for inspection or measurement purposes. This means that the images must have sufficient resolution and proper definition of the areas of interest for the inspection or measurement to take place. Each element of a machine vision system has an important role to play in the overall outcome, but the optical system is a critical component since it forms the image of the object on the camera sensor.
All machine vision systems rely on the production of an image of sufficient quality to allow the required measurements to be made. Clearly the lens or lens combinations used in the vision system play a crucial role in determining the quality of the image produced. It has an impact on many other factors as well: These include the speed that can be achieved, measuring accuracy, and the reproducibility and reliability of the downstream analysis. Although fixed focus lenses are available, most lenses for machine vision applications are manufactured with metal housings and focus mechanisms.
When it comes to the topic of imaging and machine vision you usually think of
cameras first and perceive their impact on the performance of an imaging
system as a decisive factor. However, it is often overlooked that even the
most powerful camera can only deliver useful images when using the right
illumination and the optimal lens. The selection of the appropriate illumination and optical components is a crucial determinant for image quality and
influences important factors such as speed, measuring accuracy, repeatability
and reliability of the subsequent image evaluation. This article provides an
overview of the optical basics in imaging systems.
Prototyping is an important part of developing machine vision solutions. In addition to allowing developers to explore and learn about the problem in hand, it enables interim solutions to be presented to a customer or stakeholder to make sure everything is going in the right direction. In this way, everyone can see how the proposed solution would work and understand how a project is progressing with the added benefit that a better estimation of time and cost for the final solution can be provided.
This tech tip is an overview of how imaging deals with colour; it is split in
to two sections, sensor configurations looking at three methods of acquiring
colour data, and data rates how different setups affect data rate, and how to
STEMMER IMAGING’s CVB Polimago image recognition tool provides a comparatively simple and low cost solution as an alternative to Deep Learning tools for challenging machine vision search and classification tasks. Fewer training images, shorter training times and faster execution times on a CPU platform combine to avoid some of the drawbacks associated with the convolutional neural network (CNN) approach offered by deep learning. In CVB, Polimago is also available for embedded applications.