Matrox Deep learning

Matrox Deep learning and its role in machine vision

Posted on by Mihir Mehta
A leader in the machine vision industry, Matrox® Imaging leverages our vision expertise to apply deep learning technology when and where most appropriate and help our customers find the best solution for their applications.Matrox Deep learningArtificial intelligence, specifically machine learning by way of deep learning, is making machine vision technology for automated visual inspection more accessible and capable. Deep learning technology mimics how the human brain processes visual input but performs this task with the speed and robustness of a computerized system. The technology works to ensure quality in manufacturing industries, controlling production costs and enhancing customer satisfaction.Deep learning technology excels at certain applications, such as identification and defect detection, specifically in instances where there are complex and varying imaging conditions. The technology still benefits from conventional image processing and analysis to locate regions of interest within images to speed up the overall process and make it even more robust.

Real-world examples

Identification

Identification

Image classification using deep learning categorizes images or image regions to distinguish between similarly looking objects including those with subtle imperfections. Image classification can, for example, determine if the lips of glass bottles are safe or not.
example_defect_detection_0.jpg

Defect detection

Image segmentation using deep learning categorizes image neighborhoods to pinpoint features like defects, such as dents and scratches on sheet metal. The located features can then be further analysed and measured using traditional machine vision tools.

Deep learning software and hardware

Matrox Imaging’s software offerings—Matrox Imaging Library (MIL) X and Matrox Design Assistant® X—include vision tools to classify or segment images for inspection using deep learning. Both software packages deliver optimized convolutional neural networks (CNNs) or models for the task.

Key to deep learning is the training of a neural network model. MIL CoPilot’s interactive environment provides the platform for training these models for use in machine vision applications. MIL CoPilot delivers all the functionality needed for this task, so you can create and label the training image dataset; augment the image dataset, if necessary; and train, analyze, and test the neural network model.
copilot_diagram_1920.png

e also offer hardware products that facilitate deep learning training and deployment. A suitably equipped and configured model of the Matrox 4Sight XV6 industrial computer comes ready for deep learning training. Another Matrox 4Sight XV6 model as well as the Matrox 4Sight EV6  vision controller and Matrox Iris GTX smart cameras are available to run both traditional machine vision workloads as well as deep learning inference.

Matrox Imaging’s team of vision experts know where and when to leverage machine and deep learning technologies to your best advantage. Our specialists can help identify your needs and find a customized vision solution for your requirements.

Deep learning Artificial intelligence

 

JAI Go-X Series

JAI Go-X Series : Compact, attractively-priced area scan cameras with industrial grade reliability

Posted on by Mihir Mehta

The JAI Go-X Series offers compact, attractively-priced industrial area scan cameras with a blend of features, image quality and industrial grade reliability that is in high demand for the next generation of machine vision systems.

The JAI Go-X Serie incorporates the most popular Sony Pregius CMOS sensors with resolutions ranging from 2.3 to 12.3 megapixels and a choice of USB3 Vision or GigE Vision interfaces. Also included are rolling shutter models featuring Sony Starvis CMOS sensors with resolutions of 6.3, 12.2, or 20 megapixels.

With industrial grade shock and vibration ratings (80G/10G) and excellent thermal dissipation, they are designed to keep critical inspection systems running 24/7/365.

Backed by a six-year warranty – the longest in the industry – they are built using JAI’s proven manufacturing process that has delivered field failure rates of less than two cameras per thousand over the last five years.

All cameras include a robust set of capabilities like region-of-interest (ROI), image flipping and mirroring (most models), 8/10/12-bit output, blemish compensation and shading correction – plus, advanced features like two different sequencer modes and an intelligent, user-customizable auto-exposure function (ALC).

Also available is a collection of compact C-mount lenses which have been pre-qualified for the Go-X Series sensor formats, pixel sizes, and other specifications to ensure a complete, high quality imaging solution.

  • Resolutions from 2.3 to 20 megapixels (Bayer color and monochrome models).
  • Equipped with Sony Pregius or Sony Starvis CMOS sensors.
  • Industrial grade shock and vibration ratings (80G/10G), plus excellent thermal dissipation.
  • Prices starting at €289 with a 6-year warranty.
  • Extensive dust prevention measures include cleanroom assembly, and a sealed sensor compartment for dust-free optical path on all models.
  • Three sets of mounting holes with 20, 21, and 12 mm spacing fit most existing designs with no re-tooling.
  • A free SDK plus high-level API lets you easily design for Windows, Linux, or ARM embedded platforms.
  • A compact camera size (29 x 29 x 52 mm) helps to minimize the overall size of the vision system.
JAI Go-X Series