OCR feature helps with text recognition, attention maps and OPC-UA are optimised
Software update IDS NXT 3.1 with new functions for the AI Vision System
Do you want to use an IDS NXT camera to read text on documents, such as a label or business card? The new software release IDS NXT 3.1 makes this and much more possible. The image processing feature OCR, short for "optical character recognition", is now available in the block-based editor.
But that is not all: in the block-based editor, you can now also find and filter objects by using brightness values, without having to train a neural network beforehand. The objects found can then be further filtered or sorted out via the object values.
Another new feature is that users can generate a visualisation based on attention maps in the cloud for each test data set. This allows them to check the inference with their own images, visually understand AI decisions and thereby evaluate the quality of the trained neural network.
In addition to the standardised Companion Specification for Machine Vision Systems, we also provide our own easy-to-understand information model for accessing IDS NXT via OPC-UA. We have extended this with IDS NXT 3.1 to make integration via OPC-UA for applications such as factory automation even easier.
As always, the update is free of charge. You can find all information about the new functions in the release notes.
