From Zero to OCR: A Data-Centric Framework for Unsupported Low-Resource Scripts
cs.CV, cs.CL
Submitted: 2026-10-18
Updated: 2026-10-18
Code: https://github.com/JaidedAI/EasyOCR
Terminology
Sources
- General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
- Qwen2.5-VL Technical Report
- PP-OCR: A Practical Ultra Lightweight OCR System
- 600k-ks-ocr: a large-scale synthetic dataset for optical character recognition in kashmiri script
- Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs