The first question is here, so sorry if I ask anything, it's completely stupid.
I work in a project for pattern recognition, where Iβm supposed to develop an application that receives two images: the original and the sketch made by the user. I have to detect the contours of 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 of Canny edge detection and was able to get the outlines of several images. After the contours, I need to analyze all the contours of the image and find the best match, not counting the 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 may be useful to me? I also discovered BoofCV, but it seems like such a task is not implemented.
Thank you for your patience.
EDIT:
I was looking for other ways to do this, and I found the Hausdorff distance:
http://cgm.cs.mcgill.ca/~godfried/teaching/cg-projects/98/normand/main.html
Is it possible to change this algorithm to an invariant of rotation? They only talk about translation and scaling.
source
share