mrquorr's profile - activity

@berak - what I meant was that the training images could be from anywhere, not necessarily one region @StevenPuttemans - mostly for educational purposes, but I didn't know of the existence of openaplr, I'll check em out for some pointers

What do you want to identify? Will it always have the same rotation and general form? For example, identifying the men will need a different method if they could be on different angles of rotation or with different type of clothes, or if you need it to be quickly identified, or with a certain percentage of certainty.

Anyone know of a database for an implementation of Haartraining on license plates? It would need around 5000 positive images (with license plates on them) and 2500 negative pictures (without license plates). The license plate region isn't important.