Cursive Text Recognition in Natural Scene Images Using Deep Convolutional Recurrent Neural Network
Open Access
- 19 January 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 10062-10078
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 https://data.mendeley.com/datasets/k5fz57zd9z/1 .Keywords
Funding Information
- NVIDIA Corporation through Quadro (RTX6000)
- University of New South Wales Canberra, Australia
This publication has 49 references indexed in Scilit:
- Reading Text in the Wild with Convolutional Neural NetworksInternational Journal of Computer Vision, 2015
- Word Spotting and Recognition with Embedded AttributesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Strokelets: A Learned Multi-scale Representation for Scene Text Recognition2014
- Deep Features for Text Spotting2014
- Scene Text Recognition Using Part-Based Tree-Structured Character Detection2013
- Speech recognition with deep recurrent neural networks2013
- Connectionist temporal classification2006
- Framewise phoneme classification with bidirectional LSTM and other neural network architecturesNeural Networks, 2005
- Long Short-Term MemoryNeural Computation, 1997
- Backpropagation through time: what it does and how to do itProceedings of the IEEE, 1990