AI & Deep Learning for Vision Applications
July 10, 2018
12:00-1:30 pm ET
ABOUT THIS WEBINAR
ML for verification and defect detection/classification
Image based ML algorithms have been advancing exponentially, but manufacturing industries have been slow to adopt these new methods. Supervised ML algorithms can be taught to perform inspections with less developer effort for certain classes of problems when compared to traditional methods, and will often work where traditional techniques are infeasible. Advances in IIOT have reduced the cost of acquiring and labelling large datasets, situating manufacturing in a sweet-spot for leveraging ML.
Localization for debugging and more
A major criticism of ML is its “black-box” nature. In convolutional neural network (CNN) based ML models one very useful technique is the use of “class activation maps” – a heatmap showing the area(s) of an image that most heavily affected the output of the model for a certain image. By inspecting high-activation areas we can understand why a model made a certain prediction the way it did. Looking further, these algorithms can be used to localize parts without explicit training.
Vision inspection systems in manufacturing generate a lot of data. In many cases any incorrect predictions made by the system can be identified and associated with recorded data, allowing continuous-training and algorithm improvements to be had almost for free. In contrast with traditional vision systems which often degrade over time due to changing environmental and physical conditions, an ML based vision system can continually improve the longer it runs.
Artemis Vision builds repeatable, tested vision systems to transform the quality you promise into a system that can guarantee it. Our proven solutions address needs in the automotive, pharmeceutical, medical, defense, building materials, and energy industries, amonth others. We work closely with our customers to test solutions at every step along the development process, so that the theory is realized in a proven system both of us can stand behind. Our goal is always to the system to the point where the install is simple and turnkey. Once systems have been built, we can also work with you to link to your currentIT and SPC environments, so you can utilize the full value of your solutions and use the data to imporve your process. We help your company save money, time, increase realiability, and decrease liability.Click Here for More
FLIR Systems, Inc.
FLIR Systems, Inc. designs, develops, manufactures, markets, and distributes technologies that enhance perception and awareness. We are a global leader in the design and manufacturing of high-performance CMOS and CCD cameras for industrial, scientific, medical, traffic, and security applications. We offer a unique and comprehensive portfolio of USB 3.1, GigE, 10GigE, and FireWire cameras known for their outstanding quality, ease of use, and unbeatable price-performance.Click Here for More
Prolucid Technologies Inc.
Prolucid is an AIA Certified Systems Integrator that helps customers develop custom imaging and vision inspection solutions, including product development, component and surface inspection, and non-destructive examination, among others. We also provide products, tools, and services to help customer build secure Industrial IoT systems, including integration of edge devices with cloud & big data and apply custom machine learning and advanced analytics to extract useful information from the collected big data, enabling enhanced intelligence. Prolucid support customers across North America in regulated and industrial industries including energy, medical, and manufacturing.Click Here for More
Nick Stupich works at Prolucid, where he helps clients with their computer vision and machine learning software solutions. His work has spanned many industries, including medical, automotive, energy and manufacturing. Prior to working at Prolucid he developed software to analyze and recognize gestures from electromyography signals, and correct rolling shutter distortion in videos. Nick has a Bachelor’s degree in Engineering Physics and a Master’s degree in Electrical and Computer Engineering from Carleton University. When he’s away from his computer, Nick likes to ski, bike, and run up and down mountains.