AgnosPCB API released

Created to easily embed the AgnosPCB solution to your existing AOI system. If you already have a good camera want to integrate the AgnosPCB neural netwrok powered AOI service to your system, just upload an image of your PCB/ Panel to our cloud server using this API and get the inspection result within seconds. More info here.


Why do the vast majority of customers who use our AOI software keep using it?

Agnospcb was born to offer a quality AOI service available to everyone, without having to face costly investments in equipment.

Since the beginning of 2020, many customers have relied on us to check the integrity of their PCBs in a fast and efficient way: from companies with short runs to those that have required continuous use 24h/seven days a week.

The constant evolution of the network’s detection capabilities has allowed Agnospcb’s visual inspection service to adapt to the very different needs of customers. No matter what these may be.

Today’s neural network is capable of processing images from any type of camera, from a simple smartphone camera to units with powerful optics but affordable for any customer. Don’t you believe it? Try it for yourself.

Just a number: 98.25% of our customers have remained using Agnospcb’s visual inspection service after the free trial. Not bad at all. By today, April 2021, Agnospcb is servicing 587 clients all over the World.

While all this is happening, we keep evolving our AOI software by improving it to be able to offer, inspection of the components placed on the PCBs just before the reflow-oven process. This doubles Agnospcb’s service capabilities without doubling the number of systems required for this.

Do you want to give it a try? Just grab your smartphone and contact us.
We will create a free user account for you

New Neural Network Architecture Release (v 2.0.1)

This update brings many and very important immediate improvements:

1) The number of false positives in error detection has been reduced up to 70%. And increased the ability to demarcate where an error is (boundary marking elements with “problems”)

2) The error detection capacity of very small elements has been increased by 35% (SOT416, 663, 0402 and similar size components).

3) The network is more tolerant with elements with a very variable geometry (large electrolytic capacitors, tall elements on the PCB) They are not longer (mostly) tagged as “faulty“:

4) Added 2-color error masks alternatives (apart from red: blue and green) to facilitate spotting the position of faulty elements on different PCBs materials. Selectable from the webAPP next to the user and password fields (MASK).

5) Processing time has been reduced by 15-18%

6) The accuracy of the translation and rotation algorithm of the PCBs in the photographs has been improved by increasing the error detection capacity.