read time: 4min
Autonomous Machine Vision as a self-experiment

Mar 9, 2020 | Allgemein, inVISION, Topstory

Visual inspection in parts manufacturing is expensive, complicated and error-prone - this is the general consensus. Inspekto from Heilbronn has made it its business to change this and promises a plug&play system that delivers reliable results in the shortest time and with minimal installation effort. The inVISION has tested this in a self-experiment.

The Autonomous Machine Vision system Inspekto S70 of the German manufacturer with Israeli DNA is supposed to function independently, to set itself up, to adapt autonomously and to learn independently. For this purpose, it uses several AI modules simultaneously and can thus reduce the overall error costs. The S70 can even adapt its own settings to changes in the environment, such as lighting, handling methods and vibrations. Only 20 to 30 perfect samples are required for configuration. In addition, the unit is able to inspect multiple products or different models of the same product at the same inspection site.

The test setup

To ensure that these are not just advertising promises, Inspekto invited two editors of the trade magazine inVISION to the Innovation Factory in Heilbronn to commission the system themselves and test its plug & play capability. The test setup was very simple: a conference table, a standard laptop with external monitor and of course the image processing system itself. After a short briefing by a technician, the self-experiment could begin. The randomly selected component is read into the system via a graphic interface. With a simple mouse click, the parameters to be tested can be defined or certain areas can be excluded. In addition, special points of interest that require particularly thorough inspection can also be marked – and indeed: All of this was easily possible for the editor, who did not have an engineering degree, with a simple point&click.


After successful reading, the artificial intelligence of the Inspekto S70 did its job autonomously. About 20 to 25 samples of the workpiece were presented to the system to learn the object properties. Even the fact that a workpiece that was particularly difficult to inspect – black, square, small – was selected with accuracy did not present the system with any major obstacles. At the end of this process, which took about 20 minutes including the setting up of the test pattern, the S70 was able to present several comparison pieces. Despite the extremely poor lighting conditions in the conference room of the former machine factory, which had been converted into a hub for start-ups, the vision system was able to reliably detect small defects in the reference pieces and mark them clearly visible on the display. A thoroughly convincing result.

Mission accomplished

Autonomous Machine Vision – with the S70, the plug&play capable inspection system seems to be a reality. It is therefore not surprising that the young start-up – the first public presentation of the system took place at Vision 2018 – already has a considerable list of partners and supporters from many industrial sectors, including Bosch, BSH, Daimler, Mahle, Schneider Electric and BMW. This is not surprising, as Harel Boren, CEO of Inspekto, confidently explains: “The advantages of the S70 are so convincing that, until now, every company has placed an order after a live demonstration in its production plant”. The packaging of the vision system, which contains everything necessary for the installation on site, is equally convincing: “Our mission and passion is to make QA professionals love their jobs.



Autonomous Picking
Autonomous Picking

ActiNav is a UR+ application kit that simplifies the integration of autonomous bin picking of parts and accurate placement in machines using UR cobots. It synchronously handles vision processing, collision-free motion planning and autonomous real-time robot control.


Curved Image Sensors
Curved Image Sensors

Silina’s curved image sensors enhance the performance of vision systems by improving image quality (sharpness, light sensitivity, contrast, chromatic aberration) across the entire field of view and enabling system miniaturization.

this may also interest you

Safety First

For years, image processing has only marginally dealt with the subject of safety.

inVISION at home

Special events require special reactions. To ensure that you always have access to the current issue even during the Corona pandemic and that you can read our trade journals in your home office (or any other place), TeDo Verlag provides you with the upcoming issues of its trade journals free of charge as an eMagazine.

Fingers Crossed

Probably none of us imagined March 2020 at the beginning of the year like this.

Who’s next?

Unfortunately, the coronavirus currently has the trade fair landscape firmly under its control.

DGQ Quality Day

DGQ Quality Day For the sixth time, the Deutsche...