Fig. 3: An illustration of the three steps in MSHRR.
From: An open benchmark for oracle bone rubbing image retrieval
Rubbing feature extraction is performed using a cascaded network designed to extract character features from rubbings; Rubbing feature matching compares morphological and spatial features to find analogous glyphs, bypassing OCR; Rubbing rank scoring ranks rubbings by glyph similarity, structure, and matched pairs to prioritize identical content.
