Experiments show substantial reductions in Word Error Rate (WER) and Character Error Rate (CER), narrowing the performance gap between commercial and freely deployable OCR systems by approximately 80% in WER and over 90% in CER, while consistently outperforming general-purpose foundation-style baselines.
UniLipi, a unified multi-script OCR model for handwritten Indic manuscripts trained jointly across 13 Indic scripts within a single framework, serves as an effective foundational pretrained model and predicts script identity and per-line native character counts, supporting practical manuscript cataloging workflows.
Tathagata Ghosh, Sai Madhusudan Gunda, Simran Singh Sandral et al.· IEEE International Conferenc...· 0 citations
Handwritten mathematical expression recognition (HMER) refers to the task of recognizing and converting handwritten mathematics into a parsable markup language, usually LaTeX. No current state-of-the-art-competitive system adjusts to the way a specific person writes, and the domain gap between training images (usually...
P. Silva, Lorenz Bernard Marqueses, J. Ilao· 0 citations
This work constructs TextMuSS-10M, a large-scale synthetic scene text dataset spanning 10 scripts and 229 languages and proposes ScriptMoE, a script-aware Mixture-of-Experts (MoE) architecture that achieves the highest accuracy and is simpler than per-language experts, lighter than VLMs, and more accurate than both.
Xing-Song Ye, Yong-Kun Du, Jia-Xin Zhang et al.· 1 citation
Handwritten character recognition plays a crucial role in optical character recognition systems, particularly for low-resource and structurally complex scripts such as Tamil. Despite significant advances in deep learning, accurate recognition of handwritten Tamil characters remains challenging due to large variations i...
K. Manoj, M. Iyapparaja· Intelligent Data Analysis· 0 citations
This is the first study to introduce both a real handwritten Urdu word dataset and a diffusion-generated synthetic dataset, and develops a unified word recognition model trained jointly on handwritten and printed Urdu word data, leading to improved recognition robustness and performance.
Wahid Hussain, Shahbaz Hassan, I. Hassan et al.· IEEE Access· 0 citations
This paper proposes a Multi-Scale Transformer-Based Lexicon-Guided HTR framework built around an Adaptive Feature Fusion (AFF) mechanism, which trains a Transformer encoder with multi-head self-attention that models long-range context far more effectively than bidirectional recurrent layers.
Lalita Kumari· International journal on eme...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
