Camera and Image recognition

Question

I recently watched a youtube video where a guy got a camera to recognize when a rubik's cube was held up to it, and it captured the 9 square color combination before snapping a picture of the cube and displaying the 3x3 grid on the screen of his computer. What kind of programming is this and where would I start reading to get into this sort of thing? specifically, controlling a camera, and getting it to pick out certain parts of an image and translate that data.

Answer 1

For starters, http://opencv.willowgarage.com/documentation/structural_analysis_and_shape_descriptors.html

and then http://www710.univ-lyon1.fr/~bouakaz/OpenCV-0.9.5/docs/ref/OpenCVRef_ImageProcessing.htm

code samples http://code.google.com/p/blockhead/source/browse/trunk/Xcode/CubeFinder.cpp?r=8

and http://blockhead.googlecode.com/svn-history/r13/trunk/CubeFinder.cpp

OpenCV cvFindContours - how do I separate components of a contour

Answer 2

This comes under the topic "Computer Vision" and OpenCV would be a good entry into this .... http://opencv.org/

maybe have a look at this tutorial :- Cascade Classifier