TRIOSlib is a library that contains implementations of state-of-the-art methods in Image Operator Learning. It has been used, in its many incarnations, in many research papers over the last 15 years. The current version (2.0) has had many parts rewritten and was redesigned to be flexible and to allow users to combine and extend each of its parts.
Developed in Cython, TRIOSlib is many times faster than equivalent pure Python code, while still being expressive and easy to use.
We do not have yet a research paper specifically on TRIOSlib, so if you use it in a paper, please cite
Montagner, I. S.; Hirata, R.; Hirata, N.S.T., “A Machine Learning Based Method for Staff Removal,” Pattern Recognition (ICPR), 2014 22nd International Conference on.