Printed Arabic Text Recognition using Linear and Nonlinear Regression

Arabic language is one of the most popular languages in the world. Hundreds of millions of people in many countries around the world speak Arabic as their native speaking. However, due to complexity of Arabic language, recognition of printed and handwritten Arabic text remained untouched for a very long time compared with English and Chinese. Although, in the last few years, significant number of researches has been done in recognizing printed and handwritten Arabic text, it stills an open research field due to cursive nature of Arabic script. This paper proposes automatic printed Arabic text recognition technique based on linear and ellipse regression techniques. After collecting all possible forms of each character, unique code is generated to represent each character form. Each code contains a sequence of lines and ellipses. To recognize fonts, a unique list of codes is identified to be used as a fingerprint of font. The proposed technique has been evaluated using over 14000 different Arabic words with different fonts and experimental results show that average recognition rate of the proposed technique is 86%.

• Publication year

  2017

• Venue

  arXiv.org

• Publication date

  2017-02-05

• Fields of study

  Computer Science

• Identifiers
  DOI 10.14569/IJACSA.2017.080129arXiv 1702.01444
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Detection and removal of graphical components in pre-printed documents

  2016cited by this paper
• Evaluation of cursive and non-cursive scripts using recurrent neural networks

  2016cited by this paper
• A model-based approach to offline text-independent Arabic writer identification and verification

  2015cited by this paper
• The Thinning Problem in Arabic Text Recognition A Comprehensive Review

  2014cited by this paper
• Distinction between handwritten and machine-printed text based on the bag of visual words model

  2014cited by this paper
• Isolated Printed Arabic Character Recognition Using KNN and Random Forest Tree Classifiers

  2014cited by this paper
• A Serial Combination of Neural Network for Arabic OCR

  2014cited by this paper
• Modified Bootstrap Approach with State Number Optimization for Hidden Markov Model Estimation in Small-Size Printed Arabic Text Line Recognition

  2014cited by this paper
• Arabic Character Recognition Based M-SVM: Review

  2014cited by this paper
• Improved Zhang-Suen thinning algorithm in binary line drawing applications

  2012cited by this paper
• Printed Arabic Text Recognition

  2012cited by this paper
• On-line Arabic handwriting recognition system based on visual encoding and genetic algorithm

  2009cited by this paper
• Computer-Aided Intelligent Recognition Techniques and Applications

  2005cited by this paper
• Printed Arabic character recognition using HMM

  2004cited by this paper
• Off-Line Arabic Character Recognition – A Review

  2002cited by this paper
• Recognition of printed Arabic text using machine learning

  1998cited by this paper
• Numerically Stable Direct Least Squares Fitting of Ellipses

  1998cited by this paper
• Feature extraction and scene interpretation for map-based navigation and map building

  1998cited by this paper

• UTRNet: High-Resolution Urdu Text Recognition In Printed Documents

  2023cites this paper
• Recent advances of ML and DL approaches for Arabic handwriting recognition: A review

  2023cites this paper
• Detection and Extraction of Faces and Text Lower Third Techniques for an Audiovisual Archive System using Machine Learning

  2022cites this paper
• Improved recognition results of offline handwritten Gurumukhi characters using hybrid features and adaptive boosting

  2021influential citation
• Attention-Based CNN-RNN Arabic Text Recognition from Natural Scene Images

  2021cites this paper
• An Efficient Language-Independent Multi-Font OCR for Arabic Script

  2020cites this paper
• Unconstrained Arabic Scene Text Analysis using Concurrent Invariant Points

  2020cites this paper
• Persian OCR with Cascaded Convolutional Neural Networks Supported by Language Model

  2020cites this paper
• A Proposed Arabic Text and Text Image Classification Technique Using a URL Address

  2019cites this paper
• Arabic Language Character Recognition using Walsh-Hadamard Transform (WHT) vs. Discrete Fourier Transform (DFT)

  2019cites this paper
• Character and numeral recognition for non-Indic and Indic scripts: a survey

  2018cites this paper
• Sub-word based Persian OCR Using Auto-Encoder Features and Cascade Classifier

  2018cites this paper
• Computer Science & Information Technology

  2018cites this paper
• A path to AI

  2017cites this paper
• ON ARABIC OBJECT CHARACTER RECOGNITION USING DYNAMIC TIME WARPING

  2017cites this paper
• Application of Neural Networks on Cursive Text Recognition

  year unknowninfluential citation