I recently discovered the stroke width transform, as documented in the following research paper:
The algorithm is intended for detecting and extracting text from natural scenes.
However, I could not find any implementation, and from the paper I find it hard to determine all the details regarding the algorithm so I can implement it in practice. Does anyone know if this algorithm is implemented and used in practice in a system? Is there a C# or Java implementation of it?
My friend Andrew and I implemented Stoke Width Transform (SWT) on a mobile phone during a class project at Cornell. Maybe you can get hint from the report.
The report: http://www.cs.cornell.edu/courses/cs4670/2010fa/projects/final/results/group_of_arp86_sk2357/Writeup.pdf
Our code: https://sites.google.com/site/roboticssaurav/strokewidthnokia
Updated code: https://github.com/aperrau/DetectText