• Home
  • Search
  • Cursive Text Recognition in Natural Scene Images Using Deep Convolutional Recurrent Neural Network
  • Cite Icon64
  • https://doi.org/10.1109/access.2022.3144844Copy DOI Icon

Cursive Text Recognition in Natural Scene Images Using Deep Convolutional Recurrent Neural Network

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Text recognition in natural scene images is a challenging problem in computer vision. Different than the optical character recognition (OCR), text recognition in natural scene images is more complex due to variations in text size, colors, fonts, orientations, complex backgrounds, occlusion, illuminations and uneven lighting conditions. In this paper, we propose a segmentation-free method based on a deep convolutional recurrent neural network to solve the problem of cursive text recognition, particularly focusing on Urdu text in natural scenes. Compared to the non-cursive scripts, Urdu text recognition is more complex due to variations in the writing styles, several shapes of the same character, connected text, ligature overlapping, stretched, diagonal and condensed text. The proposed model gets a whole word image as an input without pre-segmenting into individual characters, and then transforms into the sequence of the relevant features. Our model is based on three components: a deep convolutional neural network (CNN) with shortcut connections to extract and encode the features, a recurrent neural network (RNN) to decode the convolutional features, and a connectionist temporal classification (CTC) to map the predicted sequences into the target labels. To increase the text recognition accuracy further, we explore deeper CNN architectures like VGG-16, VGG-19, ResNet-18 and ResNet-34 to extract more appropriate Urdu text features, and compare the recognition results. To conduct the experiments, a new large-scale benchmark dataset of cropped Urdu word images in natural scenes is developed. The experimental results show that the proposed deep CRNN network with shortcut connections outperform than other network architectures. The dataset is publicly available and can be downloaded from <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://data.mendeley.com/datasets/k5fz57zd9z/1</uri> .

Loading PDF

Similar Papers
  • Conference Article
  • Citations13

Convolutional Feature Fusion for Multi-Language Text Detection in Natural Scene Images

  • Jan 01, 2019
  • Asghar Ali Chandio +1
  • Research Article

Deep Recurrent Convolutional Neural Network for Fault Identification in Photovoltaic Panels using Thermal Imaging

  • Nov 30, 2025
  • Energy Systems Research
  • K Subha +1
  • Research Article
  • Citations6

DRCNNTLe: A deep recurrent convolutional neural network with transfer learning through pre-trained embeddings for automated ICD coding.

  • Sep 01, 2022
  • Methods (San Diego, Calif.)
  • Sajida Raz Bhutto +5
  • Research Article
  • Citations24

A driver stress detection model via data augmentation based on deep convolutional recurrent neural network

  • Oct 12, 2023
  • Expert Systems with Applications
  • Qianxi Zhao +2
  • Research Article
  • Citations5

A hierarchical recursive method for text detection in natural scene images

  • Dec 12, 2016
  • Multimedia Tools and Applications
  • Xiaobing Wang +3
  • Conference Article
  • Citations14

Integrated natural scene text localization and recognition

  • Apr 01, 2017
  • Kakade Snehal Satwashil +1
  • Conference Article
  • Citations6

Vietnamese Scene Text Detection and Recognition using Deep Learning: An Empirical Study

  • Jul 29, 2022
  • Nhat Truong Pham +5
  • Book Chapter

Bay Number Recognition Based on Deep Convolutional Recurrent Neural Network

  • Sep 04, 2020
  • Xingxing Li +4
  • Addendum
  • Citations22

RETRACTED: Deep learning network (DL-Net) based classification and segmentation of multi-class retinal diseases using OCT scans

  • Oct 25, 2023
  • Biomedical Signal Processing and Control
  • G Muni Nagamani +1
  • Research Article
  • Citations3

Handwritten Digit Recognition

  • May 20, 2024
  • International Journal of Innovative Research in Engineering
  • G Oviya +1
  • Book Chapter
  • Citations1

Convolutional Neural Networks for Scene Image Recognition

  • Jan 01, 2019
  • Yulian Li +3
  • Research Article
  • Citations8

Adversarial Robustness of Deep Convolutional Neural Network-based Image Recognition Models: A Review

  • Aug 28, 2021
  • 雷达学报
  • Hao Sun +4
  • Research Article
  • Citations3

Performance Evaluation of Efficient and Accurate Text Detection and Recognition in Natural Scenes Images Using EAST and OCR Fusion

  • Jan 01, 2025
  • International Journal of Advanced Computer Science and Applications
  • Vishnu Kant Soni +5
  • Preprint Article

An adapted deep convolutional RNN model for spatio-temporal prediction of wind speed extremes in the short-to-medium range for wind energy applications

  • Jun 28, 2022
  • Daan Scheepens +4
  • Research Article
  • Citations6

Computer vision and machine learning for image recognition: A review of the convolutional neural network (CNN) model

  • Jan 01, 2021
  • Asian Journal of Multidimensional Research
  • Ajay Rana +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.