First question here so sorry if anything I ask is completely stupid.
I'm working in a shape recognition project where it is supposed for me to develop an application that receives two images: an original one and a sketch made by a user. I am supposed to detect contours of the two images and find the best match in the original image corresponding to the sketch made by the user.
I am already learning some basics about the Canny edge detection and was able to get the contours of several images. After having the contours, I need to analyze all contours in the image and find the best match, disregarding translation, rotation, scaling and occlusion.
Then, I found this code that does exactly what I want: http://www.morethantechnical.com/2012/12/27/2d-curve-matching-in-opencv-w-code/ but is in C++.
Do you know any alternative for similar code in Java or any algorithm that could be useful to me? I also discovered BoofCV but it seems that such task is not implemented.
Thank you for your patience.
EDIT:
I've been searching for other ways of doing this, and I found the Hausdorff distance: http://cgm.cs.mcgill.ca/~godfried/teaching/cg-projects/98/normand/main.html
Is it possible to modify this algorithm to be rotation invariant? They only talk about translation and scaling.
As you mentioned you already have the source code in C++ and can't find a Java version - possibly your best bet might be to convert the C++ code into Java code. If you don't need all parts of the C++ program, you might want to covert only the parts (classes) that you need.
Conversion from C++ to Java might not be always trivial but I am guessing it might be easier if you know exactly what you want and how you want your program to behave. Below is a link to some conversion tools - although they might not be free.
http://www.researchgate.net/post/How_to_convert_the_C_C_code_to_java2