The article presents a multi-expert system for historical Manchu OCR that handles visually distinct writing styles like regular script, running script, and semi-cursive chancery hand despite limited labeled data. The approach reuses checkpoints from an iterative fine-tuning process as domain specialists and employs a lightweight page-level image classifier to dispatch pages based on visual style.
- The router achieves 99.3 percent page-level domain accuracy, matching the domain-label oracle at the same precision.
- On frozen test sets, the system matches the selected specialist for each style at two-decimal precision: 0.30 percent CER on regular script, 1.57 percent on memorials, and 4.83 percent on running script.
- Two of the three selected specialists were not trained specifically for their final domain; only the running-script expert was trained with that domain as its target.
The authors report the evaluation protocol, router design, and per-page predictions to ensure the comparison is reproducible.