Improving OCR Accuracy Through Multi-Classifier Verification of Visually Similar Characters

arXiv:2610.22726 · cs.CV, cs.IR · Submitted 2026-10-15 · Read on arXiv

cs.CV, cs.IR

Submitted: 2026-10-15

Updated: 2026-10-15

Comments: 32 pages, 8 figures, 2 tables. Submitted to Computer Vision and Image Understanding (CVIU). Dataset available at https://github.com/VeCAD-P04-UTM/94-Class-ASCII-Image-OCR-Data

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 1× in this paper · explained in 1 episode
• Verification — 1× in this paper · explained in 2 episodes

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models