A Free Lunch? Adapting PP-OCRv6 for Historical Text Recognition

arXiv:2609.20064 · cs.CV · Submitted 2026-09-17 · Read on arXiv

cs.CV

Submitted: 2026-09-17

Updated: 2026-09-17

Project page: https://tesseract-ocr.github.io/tessdoc/tess4

Terminology

• Fine-Tuning — 17× in this paper · explained in 5 episodes
• Accuracy — 10× in this paper · explained in 1 episode
• Adaptation — 10× in this paper · explained in 1 episode
• Transformer — 9× in this paper · explained in 2 episodes
• Adam — 4× in this paper · explained in 2 episodes
• Generalization — 3× in this paper · explained in 13 episodes
• Hallucination — 3× in this paper · explained in 3 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• International Conference on Frontiers in Handwriting Recognition — 2× in this paper
• Visual Grounding — 2× in this paper · explained in 2 episodes
• AGN — 1× in this paper · explained in 1 episode
• Ablation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Distillation — 1× in this paper · explained in 2 episodes
• Domain Shift — 1× in this paper · explained in 4 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Low-Resource Languages — 1× in this paper · explained in 4 episodes
• Transformer Architecture — 1× in this paper · explained in 2 episodes
• Transformer Models — 1× in this paper · explained in 2 episodes

Sources

• Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
• Easter2.0: Improving convolutional models for handwritten text recognition
• DTrOCR: Decoder-only Transformer for Optical Character Recognition
• Reading or Guessing? Visual Grounding Failures of Vision-Language Models for OCR in Ancient Greek Editions
• LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR
• Calamari - A High-Performance Tensorflow-based Deep Learning Package for Optical Character Recognition
• PP-OCRv6: From 1.5M to 34.5M Parameters, Surpassing Billion-Scale VLMs on OCR Tasks

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