On Wednesday, August 11, 2021, at 12:04 PM, magnuswootton81 wrote: > Ever thought of doing it in the 3d space instead of 2d? Might offer some > advantages The algorithms themselves support this. In fact, the number of dimensions is already flexible in the central helper class (URecognizer <https://code.botcompany.de/1031930>) and just happens to be 2 in normal use.
However... where would I get 3d data from? Are you talking about stereoscopy? Or Kinect? All I have to work with is a screenshot function and a webcam... Greetings ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T5c987d7a3fa78a4f-Ma70a38553f328beb5b66eaa4 Delivery options: https://agi.topicbox.com/groups/agi/subscription