⛔️ This article is for a legacy version of Scan2CAD. See our updated tutorials. ⛔️


What are neural networks?


When Scan2CAD performs OCR text recognition, it does so by means of technology called neural networks.

Neural networks work in an analogous way to the human brain. They learn to recognize shapes and patterns from a range of examples called the training set.

Scan2CAD is supplied with a default neural network that can recognize text that has been written using standard fonts. It may not recognize other fonts well. It may also fail to recognize standard characters that are narrower or wider than normal or that are italicized. This is because a single neural network cannot be trained to recognize a wide range of fonts accurately. Ideally you need one neural network for each font type.

If the default neural network cannot recognize a font well and you have a lot of raster images containing that font, you may be able to train your own neural network to recognize the font using the font training commands in the Train Menu.


Have questions on this topic? Talk to us