Convolutional Neural Network and BLSTM for Offline Arabic Handwriting Recognition

There have been an exciting advance in machine learning during the last decade. In fact, increasing computer processing power has supported the analytical capabilities of recognition systems. In this study, we focus on Offline Arabic handwritten recognition and for this task, we propose a new system based on the integration of two deep neural networks. First a Convolutional Neural Network (CNN) to automatically extract features from raw images, then the Bidirectional Long Short-Term Memory (BLSTM) followed by a Connectionist Temporal Classification layer (CTC) for sequence labelling. We validate this model on an extended IFN/ENIT database, created with data augmentation techniques. This hybrid architecture results in appealing performance. It outperforms both hand-crafted features-based approaches and models based on automatic features extraction. According to the experiments results, the recognition rate reaches 92.21%.

• Publication year

  2018

• Venue

  Automation, Control, and Information Technology

• Publication date

  2018-11-01

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1109/ACIT.2018.8672667
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Convolutional Feature Learning and CNN Based HMM for Arabic Handwriting Recognition

  2018cited by this paper
• Transfer Learning for Handwriting Recognition on Historical Documents

  2018influential reference
• Sentiment Analysis of Movie Reviews Based on CNN-BLSTM

  2017cited by this paper
• Deep learning for Arabic NLP: A survey

  2017cited by this paper
• Deep neural networks for anger detection from real life speech data

  2017cited by this paper
• Arabic handwritten word recognition based on dynamic bayesian network

  2016cited by this paper
• A New Design Based-SVM of the CNN Classifier Architecture with Dropout for Offline Arabic Handwritten Recognition

  2016cited by this paper
• Convolutional feature learning and Hybrid CNN-HMM for scene number recognition

  2016cited by this paper
• Online Arabic Handwriting Recognition with Dropout Applied in Deep Recurrent Neural Networks

  2016cited by this paper
• Recognition of Handwritten Arabic Words with Dropout Applied in MDLSTM

  2016cited by this paper
• Improving MDLSTM for Offline Arabic Handwriting Recognition Using Dropout at Different Positions

  2016cited by this paper
• On the Benefits of Convolutional Neural Network Combinations in Offline Handwriting Recognition

  2016cited by this paper
• Reading Car License Plates Using Deep Convolutional Neural Networks and LSTMs

  2016cited by this paper
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

  2014cited by this paper
• DeepFace: Closing the Gap to Human-Level Performance in Face Verification

  2014cited by this paper
• Long-term recurrent convolutional networks for visual recognition and description

  2014cited by this paper
• DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection

  2014cited by this paper
• Very Deep Convolutional Networks for Large-Scale Image Recognition

  2014cited by this paper
• Deep Learning Face Representation from Predicting 10,000 Classes

  2014cited by this paper
• Effective technique for the recognition of offline Arabic handwritten words using hidden Markov models

  2013cited by this paper
• Tandem HMM with convolutional neural network for handwritten word recognition

  2013cited by this paper
• ImageNet classification with deep convolutional neural networks

  2012cited by this paper
• LSTM Neural Networks for Language Modeling

  2012cited by this paper
• Supervised Sequence Labelling with Recurrent Neural Networks

  2012cited by this paper
• Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks

  2008cited by this paper
• RIMES evaluation campaign for handwritten mail processing

  2006cited by this paper
• Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks

  2006cited by this paper
• Offline Arabic handwriting recognition: a survey

  2006cited by this paper
• 2005 Special Issue: Framewise phoneme classification with bidirectional LSTM and other neural network architectures

  2005cited by this paper
• The IAM-database: an English sentence database for offline handwriting recognition

  2002cited by this paper
• Bidirectional recurrent neural networks

  1997cited by this paper
• Long Short-Term Memory

  1997cited by this paper
• Handwritten Digit Recognition with a Back-Propagation Network

  1989cited by this paper
• A Method of Recognition of Arabic Cursive Handwriting

  1987cited by this paper

• The “Digital Maktaba LP”

  2026cites this paper
• Enhancing Arabic handwritten word recognition: a CNN-BiLSTM-CTC architecture with attention mechanism and adaptive augmentation

  2025influential citation
• Designing a Novel CNN–LSTM-based Model for Arabic Handwritten Character Recognition for the Visually Impaired Person

  2025cites this paper
• Towards Accurate Recognition of Historical Arabic Manuscripts: A Novel Dataset and a Generalizable Pipeline

  2025influential citation
• Speaker-based language identification for Ethio-Semitic languages using CRNN and hybrid features

  2024cites this paper
• A Comparative Analysis of Two Arabic Handwritten Datasets Using Pretrained Deep Learning Models

  2024cites this paper
• Enhancing Arabic Handwritten Recognition System Based CNN-BLSTM Using Generative Adversarial Networks

  2024cites this paper
• CNN-based Methods for Offline Arabic Handwriting Recognition: A Review

  2024cites this paper
• Deep Learning for Accurate Recognition of Arabic Handwritten Words in Historical Documents

  2024cites this paper
• Ancient but Digitized: Developing Handwritten Optical Character Recognition for East Syriac Script Through Creating KHAMIS Dataset

  2024cites this paper
• IDPL-PFOD2: A New Large-Scale Dataset for Printed Farsi Optical Character Recognition

  2023cites this paper
• Arabic Handwritten Recognition Using Hybrid CNN, HMM and an Intelligent Network Based on Dentate Gyrus of the Brain

  2023influential citation
• A Novel Hybrid DL Model for Printed Arabic Word Recognition based on GAN

  2023cites this paper
• New MDLSTM-based designs with data augmentation for offline Arabic handwriting recognition

  2022cites this paper
• Arabic Handwritten Recognition Using Deep Learning: A Survey

  2022influential citation
• Improving end-to-end deep learning methods for Arabic handwriting recognition

  2022cites this paper
• Handwritten Tamil Character Recognition in Palm Leaf Manuscripts using BiLSTM Classifier

  2021cites this paper
• Novel Deep Convolutional Neural Network-Based Contextual Recognition of Arabic Handwritten Scripts

  2021cites this paper
• Deep Sparse Auto-Encoder Features Learning for Arabic Text Recognition

  2021influential citation
• Conditional Deep Convolutional Generative Adversarial Networks for Isolated Handwritten Arabic Character Generation

  2021cites this paper
• Arabic Handwritten Word Recognition Based on Stationary Wavelet Transform Technique using Machine Learning

  2021influential citation
• Cross-People Mobile-Phone Based Airwriting Character Recognition

  2021cites this paper
• Automatic processing of Historical Arabic Documents: A comprehensive Survey

  2020cites this paper
• Survey of Offline Arabic Handwriting Word Recognition

  2020cites this paper
• Handwritten Arabic Character Recognition: Comparison of Conventional Machine Learning and Deep Learning Approaches

  2020cites this paper
• Arabic handwriting recognition system using convolutional neural network

  2020cites this paper
• Comparative Study on Deep Convolution Neural Networks DCNN-Based Offline Arabic Handwriting Recognition

  2020cites this paper
• Exploring Deep Learning Approaches to Recognize Handwritten Arabic Texts

  2020cites this paper
• Two streams deep neural network for handwriting word recognition

  2020cites this paper
• ReLU to Enhance MDLSTM for Offline Arabic Handwriting Recognition

  2019cites this paper
• CNN-Bidirectional LSTM Based Optical Character Recognition of Sanskrit Manuscripts : A Comprehensive Systematic Literature Review

  2019cites this paper
• Maxout into MDLSTM for Offline Arabic Handwriting Recognition

  2019cites this paper