Machine Vision Conference Program

Keynote Speakers

SpeakerSeminarAbout
Richard Love
Nvidia
Applying AI at the Edge - a Vision of the Future

Read more...

The explosion of IoT in manufacturing and smart cities, is seeing millions of video sensors deployed worldwide, generating enormous amounts of data, while computer vision and image processing algorithms remain computationally intensive. NVIDIA’s Jetson Platform, CUDA and parallel GPU acceleration is one potential solution to the ever-increasing demands of 21st-century Machine Vision.
Kieran Edge
AMRC
Machine Vision in High-Value Manufacturing, and Trends in Machine Vision R&D

Read more...

Global manufacturing is going through a period of change and reflection, with machine vision being lined up to play a pivotal role in the new world of manufacturing. I will be discussing the machine vision needs of high-value manufacturers and current advanced machine vision research. I will also discuss opportunities for engagement with the AMRC.

Deep Learning & Embedded Vision

SpeakerSeminarRead More
Gion-Pitschen Gross
Allied Vision Technologies GmbH
Machine Vision vs. Embedded Vision – Moving closer together

Read more...

Machine Vision vs. Embedded Vision – Moving closer together.
Dr Stephen Se
Flir Systems Inc
Manufacturing Inspection with Inference on the Edge

Read more...

Deep learning has gained significant attention in the machine vision industry because it does not require the complex algorithm development used by traditional rule-based methods. Deep learning inference on the edge is feasible, as there are smaller deep learning models available which are practical for embedded vision applications. We will cover the deep learning workflow from data collection to training and deployment, as well as the process of transfer learning. We will present two case studies on manufacturing inspection with inference on the edge, showing that deep learning is highly suitable for such application.
Clyde Xu
Hikrobot
A powerful deep learning inspection system becomes unprecedentedly simple

Read more...

The conventional rule-based machine vision inspection methods have been applied in various industrial fields nowadays, and their limitations are increasingly obvious, especially when they encounter demanding situations such as complex imaging background where the defect features are difficult to extract. That is where deep learning method distinguishes itself. However in many occasions, the complexity of a deep learning platform is higher comparing to regular machine vision systems. Take pc-base system for example, a deep learning platform requires high-performance PC plus an independent graphics card to provide the computing capacity. Moreover, the deep learning algorithms set-up approach is totally different. Hikrobot believes that technology should always progress towards a high-end yet more practical way. With such thought in mind, our machine vision team developed SC7000 Series Smart Camera —— a deep learning based all-in-one vision system. With SC7000, the construction of a powerful deep learning inspection system becomes unprecedentedly simple.
Patrick Schick
IDS Imaging Development Systems Ltd
Machine Vision with Neural Networks

Read more...

The implementation of new technology can be an important competitive edge. Neural networks, for example, allow vision tasks to be solved automatically that previously - using rule-based image processing - required great effort, were time-consuming or simply not possible not at all. Deep learning enables completely new machine vision applications. The talk will explain how users can benefit from the new technology, point out typical challenges and show how it is possible to overcome them. It will also focus on the major steps that are required to implement and execute a neural net on an edge device.
Patrick Schick
IDS Imaging Development Systems Ltd
Object detection with on-camera AI

Read more...

Detect and locate objects are major tasks in machine vision. Artificial intelligence allows to refine them even further. Thanks to neural networks, industrial cameras are able to handle even highly varying objects – this also applies to challenging conditions like changing light. This talk discusses how AI-based object detection, executed directly on-camera, can support you to solve machine vision tasks more efficiently.
Adriano Biocchi
MVTec Software GmbH
Embedded Vision as a Strategic Choice

Read more...

With an increasing number of embedded systems becoming smart(er), new possibilities and business opportunities are opening up within the embedded market. Most of these new smart embedded solutions and devices rely heavily on machine vision software to take a decision based on information contained within the acquired image data. MVTec experts will outline the specifics of the embedded vision market, highlighting the key financial and technical aspects which need to be taken into account and will try to shed some light onto the underestimated complexity that hides behind choosing the “right” machine vision software to be integrated into smart embedded devices.
Petr Smid
Pekat Vision
How deep learning substitutes algorithmic methods

Read more...

AI can solve many tasks of visual inspection where traditional algorithmic ways reached their limits and do not work, but how does the situation look at tasks where traditional algorithms work? Is it better to solve them with AI or not? What are the benefits of using AI in these cases? Are there any drawbacks? Why use AI even if we have a solution based on classical algorithms?
Dr Jon Vickers
Stemmer Imaging Ltd
Machine Learning in Machine Vision - its another tool in the toolbox, you should know it, but where do you start? Starting points, application areas, hints and tricks

Read more...

Machine learning isn't new, but the interest in it has exploded in recent years, but, do you need to employ a bright young thing straight out of university to deploy it? Not really. It has rapidly become a mainstream part of the machine vision toolkit and while it is necessary to learn enough to apply machine learning, you don't need to be a 'data scientist' or even a good programmer! This talk explores some of the different types of machine learning, how to get started, how to test, improve and deploy systems. The types of applications that are good for machine learning is discussed along with the pitfalls and unique considerations.
Robert Chang
Neousys Technology
Deep Learning Machine Vision – The Hawk’s eye of Industrial 5.0

Read more...

GPU-powered deep learning technology is growing at an immense rate and can be found all around us. This Neousys Technology presentation focuses on how, by implementing deep learning technology can benefit machine vision applications and why Neousys’ high-powered GPU solutions thrive in extreme conditions to accelerate tasks. To see deep learning machine vision in action, stay tuned until the end for success stories.

Understanding Vision Technology

SpeakerSeminarRead More
Allan Anderson
ClearView Imaging Ltd
Thermal Imaging: How to successfully specify and implement Thermal Imaging technology

Read more...

Thermal Imaging is becoming a more popular method to solve some applications which cannot be cracked using standard visible machine vision technology. This presentation is intended to help anyone new to the subject of Thermal Imaging and to give some basic information about the background and fundamentals of infrared, answer the question “why use thermal imaging”, before covering important topics like emissivity and how to get the right set-up. Finally, the presentation will conclude by giving some examples of how Thermal Imaging is being used in certain applications.
Neil Sandhu
SICK UK Ltd
Vision - Simple & Adaptable

Read more...

In the current industrial environment, technology in automation is advancing at an increasing rate. What was new age technology today, could be superseded in a matter of months. A good philosophy is to make sure solutions are adaptable, easy to integrate and deploy so using them initially is straight forward and then updating when the need arises is seamless. Here we will look at how Vision solutions can be created to simply 'plug and play' in a variety of industries and applications so the ease of use as well as the adaptability can be utilised to meet the challenges of advancing technology - but simple to work with.
Julian Parfitt
Alrad Imaging
Out of Sight - Imaging Beyond the Visible Spectrum – UV, NIR and SWIR

Read more...

Out of Sight - Imaging beyond the visible spectrum’ and will focus on UV, NIR and SWIR imaging applications.

Systems & Applications

SpeakerSeminarRead More
Simon Banks
Acrovision
Utilising AI / Deep Learning Vision for Real-World Applications

Read more...

Everyone’s talking about it – but Acrovision will share where the latest AI and Deep Learning advancements in Vision can be put to good use in real-life situations. Acrovision will show that Deep Learning Vision is solving applications not possible with traditional vision but remaining cost-effective.
John Dunlop
Bytronic Automation Ltd
Artificial Intelligence in Thermal Imaging

Read more...

This presentation considers the application of machine learning and artificial intelligence in the rapidly growing field of thermal imaging. Thermal cameras are rapidly becoming an essential tool in the packaging sector – to identify quality issues during sealing and carton closure, but many of these processes cannot be easily defined in a programmatic sense. The processes do not have a clear manufacturing tolerances defining pass or fail criteria and are affected by variations like environment or poor fixturing. Inspections are better defined by learning by examining the characteristics of passed and failed examples, as with machine learning. This presentation considers some real cases and how artificial intelligence can be used to improve inspection performance.
Conor O’Kelly
Crest Solutions Ltd
Machine Vision Solutions for Sterile Pharmaceuticals: Vial Inspection Turnkey Systems

Read more...

The inspection of parenteral liquids and primary & secondary packaging to ensure patient safety is a critical quality control function in aseptic environments. Pharmacopeia regulations mandate visual inspection of product to safeguard patients. Machine vision is used to achieve a level of resolution, speed and repeatability not possible with manual visual inspection. This presentation details how Crest Solutions automate many inspection and automation functions around vial fill-finish and packaging processes.
Tim Irons
Dimaco
Camera.. Lights.. Inaction! (Or How to Correctly Specify a Vision System for Food Label Inspection)

Read more...

Superficially, a label inspection system seems simple. You just point a camera at the label, program in any data and that off you go. Unfortunately, this sort of system isn’t terribly useful and, in all likelihood, will not work at all. The difficulties can be placed in several different categories principally optical, mechanical, print, data, integrity and audit. This presentation will examine each in turn, based on Dimaco’s experience over nearly twenty years of designing such systems. We will highlight the likely technical issues and offer proven solutions to each in turn. Specifically, the presentation will consider the real-world practical problems of running a vision system operated by non-specialist personnel whilst ensuring 100% label verification, minimal false rejects, and highly accurate production data sets.
Jana Lambrecht
Scorpion Vision Ltd
How Vision Systems help Reduce Food Waste – A Case Study

Read more...

A lot of our recent projects have been in the food and agricultural sector. With an increased awareness of reducing throw away during food production vision systems are a great way to aid towards this goal and work together with automation machines and robots. Post-harvest vegetable processing is a major contributor to food waste. Improving this area of farming is a major challenge for farmers and can not only increase the produce quality but also reduce cost. Jana will talk about some of the challenges and solutions faced for this and give examples of successfully deployed systems.

3D Vision

SpeakerSeminarRead More
Christian Benderoth
LMI Technologies
Leveraging Ultra-Wide Field of View 3D Laser Profiling for Scanning and Inspection of Large Objects

Read more...

Automated quality control in packaging and logistics, automotive manufacturing and food processing applications often require scanning and inspection of large target objects. This presentation will explore how ultra-wide field of view smart 3D laser profiling provides a high-performance, cost-effective measurement and inspection solution for this emerging challenge. Specifically, there will be an introduction to the new Gocator 2490 3D laser profile sensor from LMI Technologies, which leverages an ultra-wide field of view (2 meter) and large measurement range to achieve an extensive scan area (1 meter x 2 meter –– allowing engineers to perform complete dimensional gauging and high-resolution 2D/3D quality inspection of large targets at inline production speed.
Torsten Wiesinger
Lucid Vision Labs, Inc
Time-of-Flight design tips to boost 3D performance and cut integration times

Read more...

Jason MacDonald
Matrox Imaging
Evolutionary 3D profiler design for higher-reproduction fidelity

Read more...

Dr. Konstantin Schauwecker
Nerian Vision GmbH
Fast 3D Sensing Through FPGA-BasedImage Processing

Read more...

The three-dimensional acquisition of objects, surfaces and structures has gained immensely in importance in recent years. New camera and sensor technologies have made this possible, while existing approaches have been further developed and have also contributed to the triumphant advance of 3D image acquisition.

Camera Technology

SpeakerSeminarRead More
Euresys/Vision Research
Understanding extreme high-speed imaging: the benefits and how to achieve it with a high-performance CoaXPress 2.0 frame grabber

Read more...

Extreme high-speed imaging in powerful and unlocks new capabilities, but also generates more data and has programming requirements than the machine vision industry is accustomed to. Understand these requirements and learn how a high-performance CoaXPress frame grabber addresses these requirements for ease of use.
Gaspar van Elmbt
GeT Cameras | Daheng Imaging
Vision hardware design rules reduce cost price of your project

Read more...

Reducing cost price of your project or product increases the sales potential and success of it. In the design phase you make crucial decisions that affect the cost price. In our presentation we focus on machine vision hardware (camera + lens + processing hardware). We provide you with tools and knowledge to optimise your decision during the design phase to reduce the cost price for machine vision hardware. You will understand the main cost drivers and cost driving decisions when defining the machine vision hardware. We will summarise it in a set of vision hardware design rules that you can use in your upcoming projects.
Nathan Cohen
Imperx, Inc
Advantages of Using Rugged IP67 Cameras in Industrial Applications

Read more...

Rugged IP67 cameras are the ideal choice for a myriad of industrial applications requiring superior imaging performance and durability in harsh conditions. With industrial environments often exposed to harsh elements including water, humidity, dirt, dust, shock, vibration, chemicals and extreme temperatures, there is a growing demand for the optimisation of industrial and automated processes. Rugged IP67 cameras overcome these challenges because they are designed to operate reliably and effectively in these demanding conditions. Learn about the advantages of using rugged IP67 cameras in industrial applications such as automotive, manufacturing, mining, oil & gas, pharmaceutical, food & beverage, inspection, robotics, aerospace, security, machine vision, packaging, process control, traffic & transportation, military, agricultural and MORE.
Paritosh Prayagi
JAI
High speed, high resolution HDR imaging for machine vision applications

Read more...

In machine vision applications with high levels of contrast (brightness/darkness) it may be difficult or impossible to find an exposure time that properly accommodates the range of photons striking the physical pixels. Some pixels that are receiving photons from light sources or other highly reflective areas in the scene may completely fill up (“saturate”) before the end of the exposure period. All of these pixels will thus be assigned a pure white value, regardless of their relative brightness to one another. Reducing the exposure time to avoid this may cause pixels in the darker portions of the image to not receive any photons, thus all of these would be assigned a zero (black) value regardless of their relative brightness. High Dynamic Range (HDR) imaging refers to the ability to capture such high contrast scenes in a way that maintains the relative order of brightness between all pixels, with few or no bright pixels saturating or dark pixels being assigned a zero value. here are many established methods of doing HDR depending on the type of imaging application (e.g. moving or static object, colour or monochrome). Depending on the requirements of the application, HDR data can be provided in linear form with the exact relationship between all pixels maintained, or can be provided in a piece-wise non-linear form where the hierarchy of brightness is maintained, but in a compressed value range for the brighter pixels. Sequential image fusion has been the most classical method of achieving HDR. Multi-slope integration, dual sensor fusion, single exposure-dual gain and double exposure are other methods being used in machine vision applications. This presentation explains various on-camera HDR methods used in machine vision with focus on high resolution, high speed cameras equipped with HDR for various machine vision applications.
Andreas Lange
Teledyne Imaging
The Future of Line Scan Technology

Read more...

This presentation discusses the exciting direction of line scan imaging with a focus on the latest trends in sensor technology, new speed benchmarks, interface evolution and more.

Optics & Illumination

SpeakerSeminarRead More
Dr Boris Lange
Edmund Optics
Integrating Liquid Lenses in Imaging Optics

Read more...

This presentation provides an overview of the two predominantly used technologies when it comes to liquid lenses – from a traditional optics manufacturer´s point of view. An introduction of the technologies used by Varioptic and Optotune is given, completed with a short overview of the associated products. The second part of the presentation illustrates how those products can be integrated in Fixed Focal Length Lenses and Telecentric lenses.
Jools Hudson
Gardasoft
Six Key Considerations for Machine Vision Lighting

Read more...

Lighting and lighting control should be vital considerations in every machine vision implementation because the quality of the captured image is defined by the exact design and implementation of the lighting components. It’s a common mistake for system designers to rely heavily on image correction, thinking that an inadequate image can be corrected before further processing is carried out. But Machine Vision software can only work with information that has been captured, which means that the primary consideration should be to obtain the best possible source image. Obtaining a perfect image requires a good, reliable lighting system. This presentation reviews the six key considerations for machine vision lighting: 1. Optimise the image at source 2. Get the most from your LEDs 3. Build in flexibility 4. Maintain stable illumination 5. Make setup easy 6. Utilise network connectivity
Cameron Millar
Keyence UK Ltd
Component Inspection through 3 Dimensional Change

Read more...

KEYENCE Illumination Technology has proven instrumental in enabling stable inspection industry-wide, without influence from target surface conditions and contrast or variations between good parts. In this must-see seminar for users of machine vision, we visit the main concepts behind KEYENCE lighting systems, and illustrate its potential, using real-life examples from solved applications. Senior Machine Vision Applications Engineer, Cameron Millar, covers the key features and benefits of KEYENCE Illumination Technology for accurately capturing target appearance and using lighting adjustments for stable detection of difficult to spot variations.
Daniel van de Sandt
Kowa
Customized Lens Developments

Read more...

Kowa offers a wide range of customised lens developments ranging from simple modifications to complete new developments.
Mr Luca Bonato
Opto Engineering
Advances in Telecentric Technology

Read more...

In the machine vision industry, a particularly demanding sector is the metrological one where telecentric lenses boast the primacy in terms of performances. On the other hand, telecentric lenses have a major drawback in the unavoidable design-related bulkiness, causing possible difficulties in the integration: considering that the best performance is achieved by matching lens and telecentric illuminator, the issue might be even more significant. Also, the overall accuracy of the system depends critically on fine-tuned mechanical adjustments related to lens-light alignment (when collimated illumination is used) and object plane alignment. Finally, a fast and reliable measurement software, together with high-quality calibration algorithms, are essential for the overall repeatability and accuracy of the system. Recent advances in optical design exploiting new fabrication techniques are showcased in this presentation, together with an insight into innovative calibration algorithms and measurement software to maximise the performance of the vision system.
Steve Kinney
Smart Vision Lights
The Importance of Syncing Camera, Software and Lighting in High-Speed Imaging Applications

Read more...

High-volume, mass-consumed products, such as packaged food, are subject to both government regulation and stringent quality assurance requirements that, in turn, demand high-speed performance from the components comprising machine vision inspection systems. Camera components must deliver sufficient frame rate or acquisition speed; image processing software requires a computing platform able to execute fast commands; and the LED lighting must trigger and come to full power quickly to freeze inspection images at the precise time. Additionally, all components of the machine vision system (camera, software, and LED lighting) must work in unison to achieve the accuracy, consistency, and performance required for these challenging applications. This presentation will discuss these challenges in detail and showcase advancements that are helping to enhance high-speed automated imaging applications.
Jack McKinley
TPL Vision
Vision System Enclosure for Food and Pharma Environments

Read more...

Food and Pharmaceutical environments are some of the harshest environments that a vision system will be integrated. Mostly due to intense cleaning cycles with chemicals and strict hygiene standards. This presentation will take you through what is really required from your vision components in food grade machines, such as standards to adhere to and design features to look for on the components you chose to integrate.

Vision Innovation

SpeakerSeminarRead More
Jason Biddulph
Micro-Epsilon UK Ltd
Solving the Challenges of Inline Automated Surface Defect Detection

Read more...

With the ever increasing demand on quality improvements, surface inspection systems can be used to identify both aesthetic defects and potential functional and integrity defects. The challenge for inspection systems is to allow for the natural deviation in form to be inspected and still achieve the levels of resolution required to identify those localised surface defects. With high precision measurement hardware and patented artificially intelligent algorithms Micro-Epsilon have utilised their years of experience and unique know how to combat these common real life challenges faced by today’s industry.
Simon Hickman
MultiPix Imaging
Anomaly Detection – Identify Undefined Defects

Read more...

Learn how powerful anomaly detection is the new approach to inspection tasks which until recently required an extensive and exhaustive list of known defects to be classified and defined before the inspection would return successful results.  Traditional software tools used for inspection applications can require lengthy development time and result in restrictive defect detection. With stunning results and ease of use, Anomaly Detection has the ability to redefine the use of machine vision in 1000’s of applications.
Neil Sandhu
Sick UK Ltd
The SMART World of Vision

Read more...

Todays manufacturing and industrial worlds are getting smarter. The intelligence in automation and what we are asking it to do is becoming a more information based environment. Robotic automation is more widely used and on the increase and, what used to be called, the information superhighway is now becoming 'Industry 4.0', 'Internet of Things' and 'Big Data'. Here we will explore how todays Vision technology can be incorporated into a 'smart' world and environment where the ability that Machine Vision can give to a Robot to see, is one part of the story. Carrying out the Inspection tasks, communication with the Robot but also how the progress, results and conclusions of the entire system can then be tracked, viewed and actioned upon is where the added benefit can be seen. We will look how this can be made possible.

Vision In Robotics

SpeakerSeminarRead More
Mike Wilson
British Automation & Robot Association (BARA)
Does UK manufacturing need more robots?

Read more...

The British Automation and Robot Association (BARA) will discuss the current market for robot automation in the UK, the opportunities and the benefits that would come from an increased application of robots. BARA will also highlight the importance of the new Robot Integrator Certification Scheme to the industry and end users alike.
Neil Stephenson
ISRA
How to successfully deploy 3D sensors for fully automated bin picking

Read more...

Learn more on how to successfully deploy 3D bin picking solutions into your production lines. Within this webcast we will give you an overview about different aspects for 3D bin picking applications. Starting with biggest application challenges & showing how ISRA VISIONs bin picking solutions overcome these hurdles. We also guide you through a complete process of the teaching-in of new parts, and concluding with an overview of different reference applications which are successfully implemented at our customers sites.

Media Partners

Contact:  Chris Valdes  T: +44 (0) 20 8773 5517     sales@machinevisionconference.co.uk

Organised by UKIVA Logo part of