Why your unused machine vision hardware doesn’t have to go to waste

Unlock the benefits of legacy equipment with an equipment-agnostic solution

In many plants you will find cameras, lighting and other hardware that was once part of a visual inspection system but is no longer fit for purpose. Do you have to rip it up and build from scratch? Here, Zohar Kantor, vice president of sales at visual inspection software company Lean AI explains why an equipment-agnostic software technology could can breath new life into your existing machine vision hardware.


It is estimated that between 2017 and 2020, approximately 270,000 machine vision systems were installed around the world. How many of these are still performing as they were intended to? It is impossible to know the exact figure, but this is a field where technology is moving very quickly. Solutions that were promised to be cutting-edge just a couple of years ago quickly become unsuitable.

A common issue is the lack of interoperability between different hardware components, or between hardware and software. Some software solutions are vendor-specific, requiring you to buy new cameras and other sensors to get the best out of the latest artificial intelligence solutions. You face the problem that economists refer to as ‘‘sunk costs.'' You have already invested considerable money in your machine vision equipment, so do you really want to rip it out and start again?

Retrofit and rejuvenate
Quality managers and plant managers are unfortunately not fully aware that there is an alternative solution in retrofitting. If a software solution is equipment-agnostic, meaning it is designed to operate with hardware from different vendors rather than being exclusive to one, you can bring new capacity to old investments.

If your existing image acquisition equipment is perfectly okay in terms of image quality and illumination, then the software was the problem. Why not leverage your existing hardware by finding a software solution that will work in tandem with it? We are currently putting this theory into practice with a leading powder metal company in Canada. Lean AI's artificial intelligence algorithms are designed to work with any hardware, so we can make use of cameras and computer hardware already in the plant, removing the need for the customer to rip this out and start again. Retrofitting in this way saves time, money and risk.

If only a small fraction of the 270,000 machine vision systems installed between 2017 and 2020 are no longer performing the tasks they were intended to then there is a huge opportunity to retrofit an equipment-agnostic software technology to breathe new life into your existing hardware. This is a problem in any industry where technological progress is flourishing, but with Lean AI's software, you may not need to replace your hardware as soon as you think.

Lean AI uses patented deep learning algorithms to automate the process of building an AI inspection model for your production line. Discover more at lean-ai-tech.com

Featured Product

T.J. Davies' Retention Knobs

T.J. Davies' Retention Knobs

Our retention knobs are manufactured above international standards or to machine builder specifications. Retention knobs are manufactured utilizing AMS-6274/AISI-8620 alloy steel drawn in the United States. Threads are single-pointed on our lathes while manufacturing all other retention knob features to ensure high concentricity. Our process ensures that our threads are balanced (lead in/lead out at 180 degrees.) Each retention knob is carburized (hardened) to 58-62HRC, and case depth is .020-.030. Core hardness 40HRC. Each retention knob is coated utilizing a hot black oxide coating to military specifications. Our retention knobs are 100% covered in black oxide to prevent rust. All retention knob surfaces (not just mating surfaces) have a precision finish of 32 RMA micro or better: ISO grade 6N. Each retention knob is magnetic particle tested and tested at 2.5 times the pulling force of the drawbar. Certifications are maintained for each step in the manufacturing process for traceability.