By this thread suggested here, I was able to found the below details. I have so far investigated the hot European names but the thread also mentions some Japanese research so probably taking some time to really understand the status of this research. The key terms are OCR, cluster-analysis, feature-extraction, feature-selection, image-processing, pre-processingg, decision-making -- Wikipedia article outlining things here and SE threads below.
Rigorous and mostly mathematical
- Adademic papers outlined here
Practical problems, mostly education -related
- OCR related info here, here -- relating to things such as OCR engines eg. Tesseract