← Back to all news
arXiv Computation and Language By Faizan Iqbal, Haq Nawaz Malik, Hafsah Pervaiz

From Zero to OCR: A Data-Centric Framework for Unsupported Low-Resource Scripts

Read the original on arXiv Computation and Language →

The paper introduces a data‑centric framework that enables end‑to‑end OCR for low‑resource scripts using only an unannotated text corpus and digital fonts, eliminating the need for manually annotated training images. A synthetic data engine generates realistic word, line, and page images with accurate script shaping, which are then used to train a YOLOv8 word detector and a convolutional recurrent recognizer via connectionist temporal classification. Applied to the Kashmiri Perso‑Arabic Nastaliq script, the system achieves a 0.39% character error rate on held‑out words and provides publicly released models, code, and a synthetic dataset of 285,864 text‑line images.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv Computer Vision
Sep 22

All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts

The paper introduces an all‑in‑one multilingual scene text recognizer called ScriptMoE, which uses a script‑aware mixture‑of‑experts architecture to handle 10 scripts and 229 languages. It is built on a new large‑scale synthetic dataset, TextMuSS‑10M, and evaluated on the TextMuSS‑Bench, achieving 82.06% accuracy—1.31% higher than the best baseline. When integrated into the PP‑OCRv5 pipeline, ScriptMoE raises the end‑to‑end multilingual F1 score from 65.71% to 80.89%, slightly surpassing the best vision‑language model while using far fewer parameters.

By Xingsong Ye, Yongkun Du, Jiaxin Zhang, Zhixian Li, Chong Sun, Chen Li, Jing Lyu, Lianwen Jin, Zhineng Chen
llmscomputer-visionmultimodal
More like this →
arXiv Machine Learning
Aug 28

Systematic Literature Review of Machine Learning Models and Applications for Text Recognition

This systematic literature review examines 97 studies on optical character recognition (OCR) from 2015 to 2025, tracing the evolution of AI models, application domains, data types, and linguistic coverage. It identifies key OCR models, evaluates their performance, strengths, and limitations, and highlights unresolved challenges such as limited resources for underrepresented languages, high variability in handwritten text, and constraints in real‑time applications. The review proposes promising approaches—including self‑supervised learning, multimodal AI, AutoML, AI‑assisted postprocessing, TinyML, and joint corpora creation—to enhance OCR accuracy and address these challenges for industrial use.

By Nuzhat Khan, Ab Al-Hadi Ab Rahman, Shahriyar Masud Rizvi, Ibrahim Yousef Alshareef, Muhammad Nadzir Marsono, Muhammad Paend Bakht, Mohd Shahrizal Rusli, Shahidatul Sadiah
computer-visionmultimodal
More like this →
arXiv Computer Vision
Aug 31

UniLipi: A Unified Multi-Script OCR for Historical Indic Manuscripts

UniLipi is a unified multi‑script OCR model trained on 13 Indic scripts to recognize handwritten manuscripts under challenging conditions such as varied line geometry, length, and interruptions by non‑textual elements. It uses script‑aware synthetic data generation to perform well even with limited real annotated data. The model also predicts script identity and per‑line character counts, aiding manuscript cataloging, and its representations transfer to contemporary Indic handwriting and several non‑Indic scripts.

By Tathagata Ghosh, Sai Madhusudan Gunda, Simran Singh Sandral, Ravi Kiran Sarvadevabhatla
computer-vision
More like this →