AI is pushing the boundaries of autonomous machine vision

Machine vision engineers are pushing the frontiers of camera specifications to offer solutions with incredible resolution. By Yonatan Hyatt, CTO and co-founder of Inspekto


irds of prey can see up to fi ve times farther than human beings, making them agile hunters. As with nature, in industry, adapting

to environmental demands also counts for successful evolution. In evolution of machine vision, it’s been crucial to achieve the best possible image of a product to be inspected, with the latest examples of ultra-high- resolution digital cameras off ering thirty megapixels and above. These solutions, however, do not tackle the biggest shortcomings of the industry. The hardware, software and algorithms of traditional solutions for visual quality assurance (QA) are tailor made by systems integrators to inspect only one product at a specifi c junction in the production line, and the process of designing, creating, installing and validating products is time-consuming and very expensive. Moreover, all phases often require numerous iterations after the validation stage.

Sophisticated cameras and illumination settings were developed to increase the details and signal-to-noise-ratio to much higher levels than required by a human inspector. Such technology makes things easier for the systems integrator when setting an algorithm, but these highly- sophisticated cameras and accessories make up a big chunk of the fi nal cost — lenses and fi lters alone can cost a small fortune.

Evolution or revolution? Autonomous machine vision (AMV) is the start of a new era. The INSPEKTO S70, the fi rst AMV system off ered by German- Israeli start-up Inspekto, takes a diff erent technological approach. Building on recent academic and industrial achievements in AI, Inspekto’s team pushed the frontier of autonomous systems to off er better decision making and hardware tuning. The system can reach excellent inspection results in a fraction of the set-up time and greatly reduce the costs associated with traditional solutions for visual quality assurance (QA). The INSPEKTO S70 is fl exible and user- friendly, so that any employee can install it in under an hour. The system integrates

26 July/August 2020 | Automation

a video sensor optimisation AI engine that automatically adjusts the illumination and camera parameters to the product’s refl ective properties and its environment. Changes in lighting, the nightmare of traditional QA solutions, are not a problem thanks to the system’s self-adjusting capabilities. Additionally, a Detection & Alignment AI engine can autonomously locate the product in a 3D space using just one image. This means that during the set-up phase, the user can add sample items in any orientation, since the INSPEKTO S70’s algorithms will detect and localise them even under heavy transformation and rotation. During installation, the user simply traces the fi eld of view (FOV) and presents an average of 20 good sample items to the system, which will automatically learn what a perfect item should look like. The benchmark for inspection is therefore established using a limited number of good products instead of hundreds or thousands of defective ones, making the set-up simple and more accurate.

After the system has learnt the item’s characteristics, inspection can begin. The S70 will alert the user automatically if it detects a product outside the parameters of the collected good samples set. However, if the QA manager deems that the item is not defective, the Defect Detection AI engine will process the new sample as a good product and the same issue will not be fl agged up again.

The simple and quick set-up process means that the system can be moved to diff erent points of a production line, off ering fl exibility. Additionally, since the whole system costs less than one tenth of traditional solutions, plant managers can have an S70 at every junction of the production line instead of just at the end, achieving “Total QA”, i.e. quality assurance at every step of production.

The apps To provide a more personalised experience, Inspekto recently launched a comprehensive range of apps for implementation with INSPEKTO S70. One of these apps is

The INSPEKTO system on a production line, with the screen showing the area to be inspected

INSPEKTO TRACKS, which archives all product images and data gathered during inspection, building a live archive that can be used in various scenarios, including to counteract claims that a defective product has left the premises. Emerging from the traditional constraints of one-product-per-solution, Inspekto allows manufacturers to inspect a variety of items using a single system, almost unimaginable until recently. One of the ways of achieving this is to use INSPEKTO TYPES. While traditional machine vision solutions are designed to monitor only one product at any given location on the production line, this app allows the S70 system to inspect any number of products — even tens or hundreds of diff erent ones — at that same location on the line. Meanwhile, INSPEKTO SEQUENCE allows the user to pre-set a specifi c sequence, for example to inspect the same item at diff erent production stages on the same production line. Both apps allow real-time switching of the product profi le being inspected, supporting fast changeovers. This makes the S70 ideal for industries that are normally challenging for traditional solutions, such as plastic injection moulding, where the same production line can manufacture products in many diff erent colours, or additive manufacturing, where the same 3D printer can produce thousands of diff erent items. CONTACT:


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46