Ask Your Question

OCR for Handwriting Learning Robot

asked 2014-04-20 06:58:14 -0500

NaoRobotUser gravatar image


I am a uni student doing my final year project. The help I need is help in writing code (in python if possible) for a haar cascade that will build it's own pos and neg database of images. i can already crop a image of where the handwritten note is, I want to use that image and have a user say this is "A" and it will learn it. the idea is it(Nao Robot) will learn off a child, and be able to be given a letter and robot can recognise it, and add to a data base. please help :) background in c++,c,c# ada, java,Python. but really new to opencv

will reference all help in my project, thanks for reading

edit retag flag offensive close merge delete


Thank you Witek your information has saved me lots of time :) cheers for responding so quickly

NaoRobotUser gravatar imageNaoRobotUser ( 2014-04-21 03:32:01 -0500 )edit

1 answer

Sort by ยป oldest newest most voted

answered 2014-04-20 15:21:09 -0500

Witek gravatar image

I am not sure if haar cascades are a good idea here. First of all, the robot would have to be given a lot of examples before the haar cascade would be useful. Secondly, training a haar cascade requires a lot of time on a desktop machine, so that would take ages on the Nao. Thirdly, you would have to have as many cascades as there are characters. Thus, the recognition phase would be quite long, as each cascade would have to be used on each unknown character. I don't know if I'm right, but I would use a more classical approach: adaptive thresholdig, some feature extraction, a classifier training (something quick, most likely random trees). If the selected features are good, the classifier should be better and better with each new example.

edit flag offensive delete link more

Question Tools


Asked: 2014-04-20 06:58:14 -0500

Seen: 708 times

Last updated: Apr 20 '14