AI OCR (screen-based)
The AI OCR (screen-based) action step is a further development of the existing OCR action steps. In contrast to the other OCR action steps, it is based on concepts of neural networks. The available languages, therefore, are based on trained patterns that take account of the characteristics of the relevant language. In many cases, therefore, the correct recognition of texts that are, for example, barely legible or have little contrast or an unusual font, is improved with this Action Step.
In contrast to the AI OCR (file-based) action step, which works with existing images, e.g. from document scans, the AI OCR (screen-based) action step works with screenshots of the currently active desktop. This means, it attempts to extract texts from a previously created screen copy.
You should consider the Intelligent OCR 2020 action step if more than one language is to be recognized at once or if you wish to use your own dictionary.
Properties
OCR Image Preprocessing
See also Properties in the Chapter entitled AI OCR (File-based).
Inbound Variables
Scan Area relative to (Coordinates) The defined Search Area is moved relative to these coordinates. The resulting result coordinates are then absolute and are with reference to the left screen corner.
This variable can only be mapped in the wizard.
Outbound Variables
IsSucceeded (Boolean) Shows whether text recognition has been carried out successfully or not.
Wizard
You can use OCR Image Preprocessing to improve the quality of the image so that the OCR operation can run optimally. This is always carried out in the specified sequence. Here, you can also switch the individual steps on or off.
First, a screenshot is made of the currently active desktop. Using Initial wait time, you can delay this operation. This can be very useful if the image takes time to form, e.g. due to animations.
You can find further explanations in Properties.