UTRNet: High-Resolution Urdu Text Recognition In Printed Documents

Abstract

In this paper, we propose a novel approach to address the challenges of printed Urdu text recognition using high-resolution, multi-scale semantic feature extraction. Our proposed UTRNet architecture, a hybrid CNN-RNN model, demonstrates state-of-the-art performance on benchmark datasets. To address the limitations of previous works, which struggle to generalize to the intricacies of the Urdu script and the lack of sufficient annotated real-world data, we have introduced the UTRSet-Real, a large-scale annotated real-world dataset comprising over 11,000 lines and UTRSet-Synth, a synthetic dataset with 20,000 lines closely resembling real-world and made corrections to the ground truth of the existing IIITH dataset, making it a more reliable resource for future research. We also provide UrduDoc, a benchmark dataset for Urdu text line detection in scanned documents. Additionally, we have developed an online tool for end-to-end Urdu OCR from printed documents by integrating UTRNet with a text detection model. Our work not only addresses the current limitations of Urdu OCR but also paves the way for future research in this area and facilitates the continued advancement of Urdu OCR technology. The project page with source code, datasets, annotations, trained models, and online tool is available at abdur75648.github.io/UTRNet.

arXiv commentAccepted at The 17th International Conference on Document Analysis and Recognition (ICDAR 2023)

References in corpus (27)

• Sequence to Sequence Learning with Neural Networks
• ADADELTA: An Adaptive Learning Rate Method
• Deep Residual Learning for Image Recognition
• Attention U-Net: Learning Where to Look for the Pancreas
• Road Extraction by Deep Residual U-Net
• Densely Connected Convolutional Networks
• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
• Deep High-Resolution Representation Learning for Visual Recognition
• Rosetta: Large scale system for text detection and recognition in images
• UNet++: A Nested U-Net Architecture for Medical Image Segmentation
• EAST: An Efficient and Accurate Scene Text Detector
• Robust Scene Text Recognition with Automatic Rectification
• TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models
• What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis
• An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
• Shape Robust Text Detection with Progressive Scale Expansion Network
• Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet
• ContourNet: Taking a Further Step toward Accurate Arbitrary-shaped Scene Text Detection
• Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition
• Deep Relational Reasoning Graph Network for Arbitrary Shape Text Detection
• Printed Arabic Text Recognition using Linear and Nonlinear Regression
• CDistNet: Perceiving Multi-Domain Character Distance for Robust Text Recognition
• Urdu Handwritten Text Recognition Using ResNet18
• From Two to One: A New Scene Text Recognizer with Visual Language Modeling Network
• Scene Text Recognition with Permuted Autoregressive Sequence Models
• Handwritten Urdu Character Recognition using 1-Dimensional BLSTM Classifier
• Transformer based Urdu Handwritten Text Optical Character Reader