Abstract
Despite considerable progress in handwritten text recognition, paragraph-level handwritten text recognition, especially in low-resource languages, such as Hindi, Urdu and similar scripts, remains a challenging problem. These languages, often lacking comprehensive linguistic resources, require special attention to develop robust systems for accurate optical character recognition (OCR). This paper introduces BharatOCR, a novel segmentation-free paragraph-level handwritten Hindi and Urdu text recognition. We propose a ViT-Transformer Decoder-LM architecture for handwritten text recognition, where a Vision Transformer (ViT) extracts visual features, a Transformer decoder generates text sequences, and a pre-trained language model (LM) refines the output to improve accuracy, fluency, and coherence. Our model utilizes a Data-efficient Image Transformer (DeiT) model proposed for masked image modeling in this research work. In addition, we adopt a RoBERTa architecture optimized for masked language modeling (MLM) to enhance the linguistic comprehension and generative capabilities of the proposed model. The transformer decoder generates text sequences from visual embeddings. This model is designed to iteratively process a paragraph image line by line, called implicit line segmentation. The proposed model was evaluated using our custom dataset ('Parimal Urdu') and ('Parimal Hindi'), introduced in this research work, as well as two public datasets. The proposed model achieved benchmark results in the NUST-UHWR, PUCIT-OUHL, and Parimal-Urdu datasets, achieving character recognition rates of 96.24%, 92.05%, and 94.80%, respectively. The model also provided benchmark results using the Hindi dataset achieving a character recognition rate of 80.64%. The results obtained from our proposed model indicated that it outperformed several state-of-the-art Urdu text recognition methods.
Abstract (translated)
尽管手写文本识别取得了显著进展，但段落级别的手写文本识别——尤其是在印地语、乌尔都语及其他类似书写系统的低资源语言中——仍然是一项具有挑战性的任务。这些语言往往缺乏全面的语言学资源，因此开发用于准确光学字符识别（OCR）的稳健系统需要特别关注。本文介绍了BharatOCR，这是一种针对手写印地语和乌尔都语段落文本的新颖无分割识别方法。 我们提出了一种基于视觉变换器-解码器语言模型架构的手写文本识别方法：一个视觉变换器（ViT）用于提取视觉特征，一个变压器解码器生成文本序列，而一个预训练的语言模型（LM）则通过提高准确度、流畅性和连贯性来优化输出。我们的模型采用了在本研究中提出的数据高效图像变换器（DeiT）架构，用于处理掩码图像建模，并采用经过优化的RoBERTa架构进行掩码语言建模，以增强所提模型的语言理解和生成能力。 变压器解码器从视觉嵌入中生成文本序列。该模型被设计为逐行迭代处理段落图像，称为隐式行分割。我们使用自定义数据集（'Parimal Urdu'和'Parimal Hindi'），以及两个公开的数据集来评估提出的模型。在NUST-UHWR、PUCIT-OUHL及Parimal-Urdu数据集中，我们的模型分别实现了96.24%、92.05%及94.80%的字符识别率，并在印地语数据集上达到了80.64%的字符识别率。实验结果显示，本研究提出的模型优于多种最新的乌尔都语文本识别方法。
URL
https://arxiv.org/abs/2512.01348
