Matrox Design Assistant X Color Analysis

Digital cameras with color image sensors are now commonplace. The same is true for the computing power and device interfaces necessary to handle the additional data from color images. What’s more, as users become familiar and comfortable with machine vision technology, they seek to tackle more difficult or previously unsolvable applications. These circumstances combine to make color machine vision an area of mounting interest. Color machine vision poses unique challenges, but it also brings some unique capabilities for manufacturing control and inspection.

Matrox Design Assistant X

The color challenge

Color is the manifestation of light from the visible part of the electromagnetic spectrum. It is perceived by an observer and is therefore subjective – two people may discern a different color from the same object in the same scene. This difference in interpretation also extends to camera systems with their lenses and image sensors. A camera system’s response to color varies not only between different makes and models for its components but also between components of the same make and model. Scene illumination adds further uncertainty by altering a color’s appearance. These subtleties come about from the fact that light emanates with its own color spectrum. Each object in a scene absorbs and reflects (i.e., filters) this spectrum differently and the camera system responds to (i.e., accepts and rejects) the reflected spectrum in its own way. The challenge for color machine vision is to deliver consistent analysis throughout a system’s operation – and between systems performing the same task – while also imitating a human’s ability to discern and interpret colors.

The majority of today’s machine vision systems successfully restrict themselves to grayscale image analysis. In certain instances, however, it is unreliable or even impossible to just depend upon intensity and/or geometric (i.e., shape) information. In these cases, the flexibility of color machine vision software is needed to:

  •  optimally convert an image from color to monochrome for proper analysis using grayscale machine vision software tools
  •  calculate the color difference to identify anomalies
  •  compare the color within a region in an image against color samples to assess if an acceptable match exists or to determine the best match
  •  segment an image based on color to separate object or features from one another and from the background

Color images contain a greater amount of data to process (i.e., typically three times more) than grayscale images and require more intricate handling. Efficient and optimized algorithms are needed to analyze these images in a reasonable amount of time. This is where Matrox Design Assistant X color analysis tools come to the fore.

Matrox Design Assistant X color analysis steps

 

Matrox Design Assistant X

 

 

 

Matrox Design Assistant X includes a set of tools to identify parts, products, and items using color, assess quality from color, and isolate features using color.

 

 

 

 

 


The ColorMatcher step determines the best matching color from a collection of samples for each region of interest within an image. A color sample can be specified either interactively from an image—with the ability to mask out undesired colors—or using numerical values. A color sample can be a single color or a distribution of colors (i.e., a histogram). The color matching method and the interpretation of color differences can be manually adjusted to suit particular application requirements. The ColorMatcher step can also match each image pixel to color samples to segment the image into appropriate elements for further analysis using other steps such as BlobAnalysis.

Color Matcher step

                                              Color Matcher step

The ImageProcessing step includes operations to calculate the color distance and perform color projection. The distance operation reveals the extent of color differences within and between images, while the projection operation enhances color to grayscale image conversion for analysis using other grayscale processing steps.

The color analysis tools included in the Matrox Design Assistant X interactive development environment (and the Matrox Imaging Library (MIL) software development kit) offer the accuracy, robustness, flexibility, and speed to tackle color applications with confidence. The color tools are complemented with a comprehensive set of field‐proven grayscale analysis tools (i.e., pattern recognition, blob analysis, gauging and measurement, ID mark reading, OCR, etc.). Moreover, application development is backed by the Matrox Imaging Vision Squad, a team dedicated to helping developers and integrators with application feasibility, best strategy and even prototyping.

Assistant X

New SOSA™ Aligned, VITA 62, 6U VPX AC/DC Power Supply Unit

New SOSA™ Aligned, VITA 62, 6U VPX AC/DC Power Supply Unit

Rugged, off-the-shelf power supply solution ready to roll

In April, North Atlantic Industries, Inc. (NAI), a leading supplier of embedded computing solutions and power supplies that Integrys is proud to represent in Canada, announced the availability of the VPX56H2-6 1,400-Watt Ruggedized, Programmable Power Supply.

SOSA™ Aligned

The VPX56H2-6 power supply unit is aligned with SOSA™, the main aim of which is to speed up and simplify the development and deployment of C4ISR systems (joint battle management that can gather data, understand it, and communicate freely with all of its components) based on open standards components. SOSA aligned systems are based on a multi-purpose backplane that allows for easy reconfiguration of the VPX Plug In Cards (PICs) to create Electronic Warfare, Signal Intelligence, RADAR or other sensor-based systems. Enabling future technology upgrades and reconfiguration are two key benefits of SOSA aligned solutions that will reduce the cost and extend the useful life of these platforms.

Adaptable workhorse for when the going gets heavy

Designed to meet the many harsh environmental requirements of rugged military and aerospace applications, NAI’s VPX56H2-6 plugs directly into a standard 6U VPX chassis with a VITA 62, 1.0” power supply slot. This off-the-shelf solution for VITA 46.0 and VITA 65 systems is:

  • Compatible with VPX specifications
  • Supports all VITA standard I/O, signals, and features
  • Conforms to the VITA 62 mechanical and electrical requirements for modular power supplies

The VPX56H2-6 is conduction-cooled through the card edge/wedgelock. It operates at full load through the entire -40°C to +85°C temperature range, accepts 3Ø AC or +270 VDC input and provides up to five outputs and I/O at up to 1,400 Watts.

Output configurations include Standard VITA 62 and SOSA™ Aligned, +12V Only (with +3.3VDC_Aux) and +12V Heavy configurations. In addition, the VPX56H2 contains Integrated IPMC, with Dual Bus IPMB-A, IPMB-B.

With its intelligent design, the VPX56H2-6 also has the flexibility to address special needs and includes current share and alignment keys for input and output configurations.

The VPX56H2 is compliant with MIL-STD-810H and VITA47 as well as MIL-STD-704F, MIL-STD-461F.

Additional standard features

  • Continuous Background Built-in-Test (BIT)
  • Remote error sensing and protection against transients
  • Over-voltage, over-current, and short circuits

Security

“We are delighted to be teaming with wolfSSL to offer embedded security in our growing portfolio of rugged COTS SBC’s,” says Lino Massafra, VP of Sales and Marketing at NAI. “North Atlantic Industries takes security seriously and is working hard to protect our solutions against cyber threats. Aligning with wolfSSL helps achieve this.”

About NAI

NAI is a leading independent supplier of embedded computing, Input/Output, communications, measurement, simulation, power and systems products for commercial, industrial and military applications built on a Configurable Open Systems Architecture™ (COSA®). COSA offers the greatest modularity, flexibility, adaptability and configurability in the industry that accelerates time-to-mission. COSA supports a Modular Open Systems Approach (MOSA) that delivers the best of both worlds: custom solutions from COTS components with No NRE.

For over 50 years, companies like Lockheed Martin, Boeing, Northrop Grumman and Raytheon have leveraged NAI’s capabilities to meet the demanding requirements of a wide range of processing, I/O and communication-centric applications, and do so with uncompromising quality, efficiency and responsiveness.

Learn More

For additional information on NAI’s latest power supply unit for rugged military and aerospace applications, click here. We look forward to discussing your power supply requirements with you.

 

Zivid Two—See More. Do More.

Zivid is a Norwegian machine vision technology company that designs and sells 3D-color cameras with vision software that are used in autonomous industrial robot cells, collaborative robot cells and other industrial automation systems. Zivid Two, a 3D industrial color camera supported by companion software products such as the Zivid Software Development Kit (SDK) and the Zivid Studio, a graphical user interface (GUI), is one of the company’s primary hardware products. And what a wonder this camera is!

Zivid Two

Zivid Two applications

Zivid Two brings human-like vision to your collaborative robotics and industrial automation systems. That’s quite a claim, but it‘s true. And in so doing it greatly helps customers ramp up efficiency and productivity in a range of applications, including:

  • De-palletizing
  • Bin-picking
  • Pick-and-place
  • Assembly
  • Packaging
  • Quality control

With capabilities like this, Zivid 3D machine vision is giving rise to the smarter factories and warehouses of Industry 4.0, which are now rising before our eyes.

Robotics

On many fronts, the future of technological advancement clearly rests with robotics. The automation of anything that can be automated is becoming the holy grail of all major robotics companies. While there have been some extraordinary advances in robotics in recent years, it’s not easy to create machinery capable of performing many basic tasks, which is where Zivid has stepped in with the Zivid Two.

Most robots need cameras to use as their vision input, and with the rapid growth in pick-and-place robotics, the Zivid Two is poised to be a key part of this process. It is a compact high-performance 3D-color camera made primarily for machine-tending applications. The camera has super-high 3D precision and advanced artifact suppression to help reduce image noise.

Machine learning for precision

The Zivid Two has a high-capture speed to make it as precise as it can possibly be in everything it does. This greatly improves the camera’s performance and eliminates constraints that restrict most cameras from working in robotics. It also has a deep-learning AI and object-detection algorithms to improve the accuracy of grabbing and placing objects.

The Zivid Two has lightning fast 3D-image acquisition and capture time, making it much better than conventional 3D scanners used in most pick-and-place robotics. It also has a very flexible working window with a distance of 300mm to 1500mm and a field of view of 57 degrees and 35 degrees on the horizontal and vertical axes, respectively. These make the camera perfect for a wide range of on-arm stationary-mounted robot-guided applications. On top of this, weighing in at 880 grams, the Zivid Two is a lightweight, minimizing its impact on the robot’s maneuverability.

Zivid Two

Piece picking with the Zivid Two

 

Machine learning for precision

The Zivid Two has a high-capture speed to make it as precise as it can possibly be in everything it does. This greatly improves the camera’s performance and eliminates constraints that restrict most cameras from working in robotics. It also has a deep-learning AI and object-detection algorithms to improve the accuracy of grabbing and placing objects.

The Zivid Two has lightning fast 3D-image acquisition and capture time, making it much better than conventional 3D scanners used in most pick-and-place robotics. It also has a very flexible working window with a distance of 300mm to 1500mm and a field of view of 57 degrees and 35 degrees on the horizontal and vertical axes, respectively. These make the camera perfect for a wide range of on-arm stationary-mounted robot-guided applications. On top of this, weighing in at 880 grams, the Zivid Two is a lightweight, minimizing its impact on the robot’s maneuverability.

3D High Dynamic Range (HDR)

See a wide variety of objects

The unique combination of native color and high dynamic range enables imaging of a broad range of objects, including those that are:

  • Plastic
  • Ceramic
  • Metal
  • Cardboard
  • Wood
  • Colored
  • Textured
  • Light
  • Dark
  • Absorptive
Dynamic Range

The Zivid Two can work with single or mixed SKU bin scenarios, densely stacked or randomly arranged

Built tough

The Zivid Two gets used in some rugged industrial environments—but it stands up extremely well to the hard going. It comes in a magnesium housing and is dust and water-resistant, which greatly contributes to its durability. The Zivid Two can also withstand temperatures ranging from 0°C to 45°C and 15 G impacts.

Learn More or Get a Quote

To learn more about the Zivid Two, or to get a quote, click here.

 

 

 

Matrox Iris GTX Enhanced Smart Cameras for Machine Vision at the Edge

Matrox 23

On May 19 Matrox Imaging announced the launch of the Matrox Iris GTX Enhanced Smart Cameras, the “next evolution” of smart cameras from this dynamic, Dorval, Quebec-based company that will hit the market in Q3 2021. The Matrox Iris GTX is a machine vision and deep learning edge IoT device designed to handle traditional machine vision operation and deep learning inference.

Higher resolution and faster processing

What makes the Matrox Iris GTX so special? For starters it boasts an Intel Atom x6000 series embedded processor that allows the Matrox Iris GTX to use higher-resolution complementary metal-oxide-semiconductor (CMOS) image sensors from two to 16 megapixels —which drives performance to unprecedented heights for a compact all-in-one vision system. The graphic below makes it clear just how much better the Matrox Iris GTX performs compared to its immediate predecessor, the Matrox Iris GTR.

matriox image 1

The performance boost derived from the Matrox Iris GTX’s processor and image sensors allow the cameras to capture high-resolution images at high speed, which translates to more detailed inspections that provide users with additional critical information.

Matrox Design Assistant® X1 software

Matrox13.png

Paired with flowchart-based Matrox Design Assistant® X1 software, engineers and technicians can quickly configure and deploy machine vision to the Matrox Iris GTX smart cameras. Video capture, analysis, classification, location, measurement, reading, verification, communication, and I/O operations—as well as a web-based operator interface—are all set up within the same software. With Matrox Design Assistant® X1 software you can choose from a wide variety of image processing and analysis tools including image classification using deep learning.

Matrox 13.png

The Matrox Iris GTX is pre-licensed for pattern recognition (PatternMatching step), feature extraction and analysis (BlobAnalysis step), 1D and 2D measurements (Measurement, BeadInspection, and Metrology steps), color analysis (ColorMatcher step; GTX…C model only), 1D and 2D code reading and verification (CodeReader and CodeGrade steps), 2D calibration, basic image processing (IntensityChecker, ImageProcessing, and EdgeLocator steps; not EdgeFinder), image compression, and industrial communication.

BlobAnalysis step in Matrox Design Assistant X used to identify, count, locate, and measure basic features and objects (i.e., blobs) to determine presence and position, and enable further inspection.

Built for harsh environments, ease of upgrade and use

Matrox Iris GTX smart cameras preserve the same small footprint and cabling connections as its immediate predecessor, for ease of upgrade and implementation. They feature a sturdy, compact IP67-rated housing and robust M12 connectors for their external interfaces, allowing them to operate in dusty, wet, and other demanding conditions. By offering the same footprint, connection options, and software platform as the Matrox Iris GTR, Matrox Imaging makes it easy to expand or upgrade an existing system. The Matrox Iris GTX line also features an interface for direct focus adjustment, as well as an LED lighting intensity control output for direct adjustments, directly through the on-device software.

Matrox33

 

Direct interfacing to automation devices

Another benefit of the Matrox Iris GTX smart cameras is that they also offer real-time digital I/Os for interfacing directly to automation devices. They provide GigE and USB ports, and a VGA video output to enable full integration within an automation cell or machine.

Purchase

The Matrox Iris GTX is the “next evolution” of smart cameras from Matrox Imaging and will be available in Q3 2021. To learn more and request a quote, click here.

 

The Use of Artificial Intelligence in Machine Vision

The use of artificial intelligence (specifically, machine learning by way of deep learning) in machine vision is an incredibly powerful technology with an impressive range of practical applications, including:

  • Giving virtual assistants the ability to process natural language;
  • Enhancing the e-commerce experience through recommendation engines;
  • Assisting medical practitioners with computer-aided diagnoses; and
  • Performing predictive maintenance in the aerospace industry.

Deep learning technology is also fundamental to the fourth industrial revolution, the ongoing automation of traditional manufacturing and industrial processes with smart technology, a movement in which machine vision has much to contribute.

Deep learning alone, however, cannot tackle all types of machine vision tasks, and requires careful preparation and upkeep to be truly effective. In this article we look at how machine vision—the automated computerized process of acquiring and analyzing digital images primarily for ensuring quality, tracking and guiding production—benefits from deep learning as the latter is making the former more accessible and capable.

Machine vision and deep learning: The challenges

Machine vision deals with identification, inspection, guidance and measurement tasks commonly encountered in the manufacturing and processing of consumer and industrial goods. Conventional machine vision software addresses these tasks with specific algorithm and heuristic-based methods, which often require specialized knowledge, skill and experience to be implemented properly. Moreover, these methods or tools sometimes fall short in terms of their ability to handle and adapt to complex and varying conditions. Deep learning is of great help but requires a painstaking training process based on previously collected sample data to produce results generally required in industry. Furthermore, more training is occasionally needed to account for unforeseen situations that can adversely affect production. It is important to appreciate that deep learning is primarily employed to classify data and not all machine learning tasks lend themselves to this approach.

Where deep learning does and does not excel

As noted, deep learning is the process through which data—such as images or their constituent pixels—are sorted into two or more categories. Deep learning is particularly well suited to recognizing objects or objects traits, such as identifying that widget A is different from widget B The technology is also especially good at detecting defects, whether the presence of a blemish or foreign substance, or the absence of a critical component in or on a widget that is being assembled. It also comes in handy for recognizing text characters and symbols such as expiry dates and lot codes.

While deep learning excels in complex and variable situations such as finding irregularities in non-uniform or textured image backgrounds or within an image of a widget whose presentation changes in a normal and acceptable manner, deep learning alone cannot locate patterns with an extreme degree of positional accuracy and position. Analysis using deep learning is a probability based process and is, therefore, not practical or even suitable for jobs that require exactitude. High-accuracy, high-precision measurement is still very much the domain of traditional machine vision software. The decoding of barcodes and two-dimensional symbologies, which is inherently based on specific algorithms, is also not an area appropriate for deep learning technology.

Artificial Intelligence

Where deep learning excels: Identification (left), detect defection (middle) and OCR (right)

Artificial Intelligence1

Where deep learning does not excel: High-accuracy, high-precision pattern matching (left), metrology (middle), and code reading (right)

Matrox Imaging software

Matrox Imaging offers two established software development packages that include classic machine vision tools as well as image classification tools based on deep learning. Matrox Imaging Library (MIL) X is a software development kit for creating applications by writing program code. Matrox Assistant X is an integrated development environment where applications are created by constructing and configuring flowcharts (see graphic below). Both software packages include image classification models that are trained using the MIL CoPilot interactive environment, which also has the ability to generate program code. Users of either software development packaged get full access to the Matrox Vision Academy online portal, offering a collection of video tutorials on using the software, including image classification, that are viewable on demand. Users can also opt for Matrox Professional Services to access application engineers as well as machine vision and machine learning experts for application-specific assistance.

 

Press Release – Direct control: 65 MP cameras for Canon EF lenses

Baumer camera.jpg(06/01/2021) Two new 65 megapixel cameras enhance the Baumer portfolio of high-resolution and robust 10 GigE cameras of the LX series. Thanks to an integrated EF mount, Canon EF lenses are easily configured via Baumer GAPI, Baumer neoAPI, or third party software to allow the focus and the aperture to be dynamically matched to the applications. External accessories and associated cabling become completely unnecessary. This simplifies the integration and reduces costs while enhancing reliability. Dynamic lens control mainly benefits applications with varying operating distances and lighting situations, e.g., track-and-trace in pharmaceutical logistics. The serial production of the new models will commence in the 2nd quarter of 2021.

The high-quality Canon EF lenses deliver high-contrast images with great depth of field. The cameras also support modern lenses with ultrasound motors. These combine reduced power consumption with precise, low-noise, and very quick focus with high reliability for the cost-efficient and robust implementation of applications. Based on the GMAX3265 sensor from Gpixel, the cameras offer excellent image quality and a high dynamic range of 66 dB. A compact optical format with a diagonal of 37 mm is achieved by a small pixel size of only 3.2 µm. This reduces edge shadowing and simplifies the choice of lenses. Minimal exposure times of 19 µs reduce the motion artifacts of fast moving objects. Thanks to the 65 megapixel resolution, the number of required cameras for each application is often even cut in half to reduce system and integration costs as well as enhance reliability.

The 10 GigE cameras of the LX series are the ideal choice for demanding inspection tasks that place strict demands on both the image capture precision and throughput. They have an exceptionally high range of functions for solving demanding applications. These include Multi ROI, shading correction, HDR, precise time synchronization according to IEEE 1588, or the direct control of illumination without external controllers. Robust M12 plug connectors, IP 65 and IP 67 protection class, as well as a temperature range from -30 °C to 60 °C make the cameras especially well-suited for difficult ambient conditions, such as the analysis of motion sequences in outdoor sports or the inspection of overhead lines and pantographs in railway transportation. In addition, thanks to their 10 GigE interface they can be easily and inexpensively integrated, while the images can be efficiently transmitted with a high bandwidth of 1.1 GB/s, reducing the evaluation time.

More information about the LXT cameras: https://www.baumer.com/cameras/LXT

Number of characters (with spaces): approx. 2700

Text and picture download at: www.baumer.com/press

Baumer Group

The Baumer Group is one of the worldwide leading manufacturers of sensors, encoders, measuring instruments and components for automated image processing. Baumer combines innovative technologies and customer-oriented service into intelligent solutions for factory and process automation and offers an unrivalled wide technology and product portfolio. With around 2,700 employees and 39 subsidiaries in 19 countries, the family-owned group of companies is always close to the customer. Baumer provides clients in most diverse industries with vital benefits and measurable added value by worldwide consistent high quality standards and outstanding innovative potential. Learn more at www.baumer.com on the internet. 

Press contact:

Nicole Marofsky

Marketing Communication

Baumer Group

Phone +49 (0)3528 43 86 19

Fax +49 (0)3528 43 86 86

nmarofsky@baumer.com

www.baumer.com

Company contact global:

Baumer Group

Phone +41 (0)52 728 11 22

Fax +41 (0)52 728 11 44

sales@baumer.com

www.baumer.com

Photo: The new 65 MP cameras with integrated EF mount allow the dynamic adjustment of focus and aperture with varying working distances or illumination conditions.

 

 

North Atlantic Industries Announces New SOSA™ Aligned, VITA 62, 6U VPX AC/DC Power Supply Unit (VPX56H2-6)

VPX56H2-6_PR_image.png

BOHEMIA, NY – April 2021 — North Atlantic Industries, Inc. (NAI), a leading supplier of embedded computing solutions and power supplies, announces the availability of the VPX56H2-6 1,400-Watt Ruggedized, Programmable Power Supply. Designed to meet the many harsh environmental requirements of rugged military and aerospace applications, NAI’s VPX56H2-6 is a 1,400-Watt AC/DC Power Supply that plugs directly into a standard 6U VPX chassis with a VITA 62, 1.0” power supply slot. This off-the-shelf solution for VITA 46.0 and VITA 65 systems is compatible with VPX specifications; supports all VITA standard I/O, signals, and features; and conforms to the VITA 62 mechanical and electrical requirements for modular power supplies. The VPX56H2-6 is conduction-cooled through the card edge/wedgelock. It operates at full load through the entire -40°C to +85°C temperature range, accepts 3Ø AC or +270 VDC input and provides up to five outputs and I/O at up to 1,400 Watts. Output configurations include Standard VITA 62 and SOSA™ Aligned, +12V Only (with +3.3VDC_Aux)and +12V Heavy configurations. In addition, the VPX56H2 contains Integrated IPMC, with Dual Bus IPMB-A, IPMB-B.

Additional standard features include continuous Background Built-in-Test (BIT), remote error sensing and protection against transients, over-voltage, over-current, and short circuits. With its intelligent design, the VPX56H2-6 also has the flexibility to address special needs and includes current share and alignment keys for input and output configurations. The VPX56H2 is compliant with MIL-STD-810H and VITA47 as well as MIL-STD-704F, MIL-STD-461F.

“We are delighted to be teaming with wolfSSL to offer embedded security in our growing portfolio of rugged COTS SBC’s,” says Lino Massafra, VP of Sales and Marketing. “North Atlantic Industries takes security seriously and is working hard to protect our solutions against cyber threats. Aligning with wolfSSL helps achieve this.”

“The VPX56H2-6 is a high-power density Power Supply which accepts 3Ø AC or +270 VDC input and provides multiple output configurations up to 1,400 Watts, the highest (VITA Power Supply) available from NAI today,” said Lou Garofolo – Product Manager, Power Division. “It is the latest in a complete line of 3U & 6U VPX AC/DC power supplies that support some of today’s harsh environmental requirements and demanding system power requirements.”

NAI is a leading independent supplier of embedded computing, Input/Output, communications, measurement, simulation, power and systems products for commercial, industrial and military applications built on a Configurable Open Systems Architecture™ (COSA®). COSA offers the greatest modularity, flexibility, adaptability and configurability in the industry that accelerates our customers’ time-to-mission. COSA supports a Modular Open Systems Approach (MOSA) that delivers the best of both worlds: custom solutions from COTS components with No NRE. For over 50 years, companies like Lockheed Martin, Boeing, Northrop Grumman and Raytheon have leveraged NAI’s capabilities to meet the demanding requirements of a wide range of processing, I/O and communication-centric applications, and do so with uncompromising quality, efficiency and responsiveness. Information about NAI and its products can be found at integrys.com

 

What is Deep Learning?

Deep Learning

Answering the question “What is deep learning?” requires us to stick our heads down a rabbit hole. We say this because deep learning is a type of machine learning—which, in turn, is a type of artificial intelligence (AI). You now get the reference to the rabbit hole . . . Time now for some definitions to provide clarity.

Artificial intelligence: The simulation of human intelligence in machines that are programmed to think like humans and mimic their actions. The term may also be applied to any machine that exhibits traits associated with a human mind, such as learning and problem-solving.

Machine learning: The use and development of computer systems (hardware and software) that are able to learn and adapt without following explicit instructions, by using algorithms and statistical models to analyze and draw inferences from patterns in data.

Deep learning: A subset of machine learning based on artificial neural networks in which multiple layers of processing are used to extract progressively higher level features from data.

What distinguishes deep learning is that it empowers  machines to learn from unstructured, unlabeled data, as well as labeled and categorized data. With all the rapid developments in deep learning, a lot of new applications  for machine vision have been introduced.  Time now for another definition:

Machine vision: The technology and methods used to provide imaging-based automatic inspection and analysis for such applications as automatic inspection, process control, and robot guidance, usually in industry. Machine vision refers to many technologies, software and hardware products, integrated systems, actions, methods and expertise. A machine vision system uses a camera to view an image. Computer vision algorithms then process and interpret the image, before instructing other components in the system to act upon that data. Computer vision can be used alone, without needing to be part of a larger machine system.

GPUs for computer vision applications

Many technology companies have discovered the benefit of using GPUs (Graphical Processer Units) for computer vision applications due to their ability to handle the rapid parallel processing of images. Traditional GPUs from companies like NVIDIA are large, power-hungry PCIe boards running in the cloud or temperature-conditioned environments.   So how do industrial companies take advantage of GPU technology in the field, or what’s often called ‘the edge’?

NVIDIA Jetson

Introducing NVIDIA Jetson, the world’s leading small-footprint GPU platform for running AI in harsh environments at the edge of the action.  Its high-performance, low-power computing for deep learning and computer vision makes it the ideal platform for compute-intensive projects in the field. Some of Integrys’ most valued partners provide nimble solutions in this space. But before we look at these companies and their products, it’s advisable to ask, and answer, the question below.

What’s the difference between carriers and Jetson modules?

A carrier board is specifically designed to work with one of the NVIDIA Jetson modules allowing users to connect IO, cameras, power, etc., to their devices.  Together with JetPack SDK, the combination of the carrier and module is used to develop and test software for specific use needs.

Our Deep Learning Partners

DIAMOND SYSTEMS
Stevie: Carrier for Nvidia Jetson AGX Xavier. Used in PPE and temperature monitoring, robotics, deep learning, and smart intersections/ traffic control.

 

Diamond-Systems-JETBOX-STEVIE.jpg

Featured product: JETBOX-STEVIE JETSON AGX XAVIER SYSTEM

Floyd: Carrier for Nvidia Jetson Nano & Xavier NX. Used in industrial safety, drone video surveillance and facial recognition.

Diamond-Systems-JETBOX-FLOYD.jpg

Featured product: JETBOX-FLOYD JETSON NANO / NX SYSTEM

Connect Tech Logo.png
Sentry-X Rugged Embedded System: Built for the NVIDIA® Jetson AGX Xavier™, Sentry-X is ideal for aerospace and defense applications, or for any market that can benefit from the Jetson AGX Xavier’s incredible performance in a rugged enclosure.

ConnectTech-Sentry X-Rugged Embedded System.png

Featured product: SENTRY-X RUGGED EMBEDDED SYSTEM POWERED BY NVIDIA® JETSON AGX XAVIER™

Rogue: a full featured carrier board for the NVIDIA® Jetson™ AGX Xavier™ module, the Rogue is specifically designed for commercially deployable platforms, and has an extremely small footprint of 92mm x 105mm.

ConnectTech-Rogue.png

 

Featured product: ROGUE CARRIER FOR NVIDIA® JETSON™ AGX XAVIER™

Matrox_Imaging_logotype_250px_RGB.jpg
Leveraging convolutional neural network (CNN) technology, the Matrox classification tool within their Computer Vision library, MIL (Matrox Imaging Library) categorizes images of highly textured, naturally varying, and acceptably deformed goods. The inference is performed exclusively by Matrox Imaging-written code on a mainstream CPU, eliminating the dependence on third-party neural network libraries and the need for specialized GPU hardware.

 

 

 

 

 

Matrox Imaging-Library X.png

Featured product: MATROX IMAGING LIBRARY X

Eizo_Rugged_Solutions.png
The Condor product line of GPGPU and video capture cards feature NVIDIA Quadro® GPUs with Pascal™ and Turing™ architecture. These processing powerhouses leverage the latest GPGPU advancements from NVIDIA for machine-learning and artificial intelligence applications, as well as standard rendering pipelines.

 

 

 

 

 

EIZO-Condor 4107xX.png

Featured product: CONDOR 4107XX XMC XMC GRAPHICS & GPGPU CARD

FREE

OFFER

We have a NVIDIA Jetson AGX Xavier AI-at-the-edge computing platform (diamondsystems.com) Jetbox-Stevie from Diamond in our DEMO Lab. I would like to promote it and offer a “FREE” Demo by filling a form

Integrys Clearance sale.jpg

 

Deep Learning

3 Ways to Kickstart your 3D Machine Vision Project

3D machine vision

In a 3D machine vision system, the target object image is no longer just a flat picture. Now it’s a three-dimensional point cloud of precise coordinates where the position of every pixel in space is known. It simultaneously provides X, Y and Z plane data along with respective rotational information (around each of the axes) as well.

Zivid-2D-3D-camera-3D-object.png

This 3rd dimension of Data is ideal for applications such as:

  • Thickness, height and volume measurement
  • Dimensioning and space management
  • Measuring shapes, holes, angles, and curves
  • Detection of surface or assembly defects
  • Quality control and verification against 3D CAD models
  • Robot guidance and surface tracking (e.g., for welding, gluing, deburring, and more)
  • Bin picking for placing, packing or assembly
  • Object scanning and digitization

Download an e-book

Download our latest eBook, Solving Pick and Place Automation Challenges with industrial 3D machine vision, for free. This eBook includes 6 industrial automation challenges and how to solve them with 3D machine vision solutions.

Download an e-book

Book an online demo

Schedule a free 3D camera demo with our vision engineers! Let us show you a quick demo of what you can expect from Zivid 3D machine vision cameras tailored to meet your specific business requirements.

Email item no.2 Online demo (002).png

Purchase a development kit

Now, you can buy a Zivid developer kit bundle to kickstart your 3D vision automation project. Whether it’s bin-picking, piece picking, or machine tending related – the dev kit bundle makes it easy to design stationary or on-arm robot-based picking cells.

Email item no.3 Devkit.jpg

3D machine vision

Hyperspectral Machine Vision

Hyperspectral Machine Vision

 

What is hyperspectral machine vision ?

Before launching into this topic, let’s get comfortable with a few terms:

Hyperspectral: 1) Any technique that employs a large part of the electromagnetic spectrum, especially those parts of the spectrum invisible to the eye; 2) Very high-definition spectral imaging.

Machine vision (also known as Computer Vision): The technology and methods used to provide imaging-based automatic inspection and analysis for such applications as automatic inspection, process control and robot guidance, usually in industry. Machine vision refers to many technologies, software and hardware products, integrated systems, actions, methods and expertise. It attempts to integrate existing technologies in new ways and apply them to solve real-world problems.

Hyperspectral machine vision systems analyze the molecular properties of objects being investigated and create a chemical fingerprint of the materials that comprise them.

What are some real-world problems that hyperspectral machine vision helps solve?

Though there are multiple industrial applications of hyperspectral machine vision, today we are going to focus on three that are promoted by a key Integrys supplier, Perception Park, an Austrian company passionate about hyperspectral machine vision.

1) Chemical color imaging (CCI) for pharmaceuticals: In the pharmaceutical industry manufacturing capacities are growing rapidly all over the world, requiring faster and more complex production processes. To reduce the risk of product recalls and to protect consumers from contaminated drugs, strict safety regulations and guidelines have been put in place to optimize and monitor pharmaceutical production processes. Inspection systems are fundamental to this. Vision systems are already state of the art with respect to evaluating products according to shape, size, weight etc. in real time. CCI now enables a 100% inspection of pharmaceuticals according to molecular properties.

Hyperspectral Machine Vision

The image above illustrates how Perception Park CCI technology can be applied to pharmaceuticals, in this case detecting the content of different capsules. Hospitals and retirement and nursing homes administer personalized drugs that are often manually mixed and packed by pharmacists. The first and the third (from the left) of the four capsules above were filled with Respicure, the second was filled with Silybum Marianum and the fourth was filled with nothing. CCI allows for quick identification of the content of capsules, ensuring the patients receive the right drugs—which can be a matter of life and death.

2) Wood moisture measurement: The quality requirements of wood industry customers are increasing dramatically. The measurement of humidity is an important quality marker in professional wood processing. Hyperspectral imaging can now be used to quickly and accurately indicate moisture content (MC) in wood, a major indicator of product quality and hence price and producer margins. In the example below the moisture levels of a piece of spruce were measured using hyperspectral technology and a regular wood moisture meter. The portion of the wood on the left captured with CCI clearly shows the distribution of moisture within the wood, helping in a non-destructive manner quickly determine the quality and thus value of the wood.

Hyperspectral Machine Vision

3) Fruit quality measurement: Every year tons of food is wasted, compromising the bottom line of companies in many sectors of the food industry. Purchasers of food, be they grocery sotres, restaurants or the end consumer, can be fanatical about food quality and are loath to purchase fruit, for example, that is bruised. Bruises are an indicator that the fruit is in the process of decay, but are often not visible to the naked eye. With hyperspectral imaging, however, it is possible to make the invisible visible with a non-destructive technique for fruit quality analysis.

Hyperspectral Machine Vision

As Computer Vision using Hyperspectral imaging is relatively new to many, Integrys has invested in setting up a Hyperspectral imaging station in their engineering laboratory.  We would like to offer qualified customers an opportunity to review samples of their materials/parts in our lab and consult with our team of experts on application details.

Click Below to begin evaluating your samples in our Hyperspectral Imaging lab

Preception park logo 1.pngPerception Park is a company with a passion for Hyperspectral Imaging and the focus on generic and configurable hyperspectral data processing solutions for industrial inline applications.

Their unique technology Chemical Colour Imaging (CCI) makes complex hyperspectral data on a molecular level usable for machine vision. Hyperspectral imaging systems combined generic, intuitive configurable data processing platform to make the scientific methods of hyperspectral analysis accessible for everyone and open up new application areas.

Resonon logo

 

Resonon is a rapidly-growing, high-technology company that provides an exciting and friendly working environment. The company designs, manufactures, and supports hyperspectral imagers and related hardware and software.

They provide complete hyperspectral imaging systems as well as custom hardware and software solutions with compact, cost effective cameras.

 

Machine vision technology has gone through a constant development process over the past few decades and Perception Park, with its expertise in chemical color imaging, has developed an impressive range of solutions in hyperspectral machine vision with myriad real-world applications. Click here to contact Integrys to learn how our partnerships with Perception Park and Resonon could help your company optimize its operations through hyperspectral machine vision.