Sub-sampling Approach for Unconstrained Arabic Scene Text Analysis by Implicit Segmentation based Deep Learning Classifier

Sub-sampling Approach for Unconstrained Arabic Scene Text Analysis by Implicit Segmentation based Deep Learning Classifier

Saad Bin Ahmed Lecturer

Contact

Zainab Malik

Contact

Muhammad Imran Razzak

Contact

Rubiyah Yusof

Contact

α University of Technology Malaysia

Sub-sampling Approach for Unconstrained Arabic Scene Text Analysis by Implicit Segmentation based Deep Learning Classifier

Article Fingerprint

ReserarchID

1BN26

Sub-sampling Approach for Unconstrained Arabic Scene Text Analysis by Implicit Segmentation based Deep Learning Classifier Banner

AI TAKEAWAY

Connecting with the Eternal Ground

Abstract

The text extraction from the natural scene image is still a cumbersome task to perform. This paper presents a novel contribution and suggests the solution for cursive scene text analysis notably recognition of Arabic scene text appeared in the unconstrained environment. The hierarchical sub-sampling technique is adapted to investigate the potential through subsampling the window size of the given scene text sample. The deep learning architecture is presented by considering the complexity of the Arabic script. The conducted experiments present 96.81% accuracy at the character level. The comparison of the Arabic scene text with handwritten and printed data is outlined as well.

References

18 Cites in Article

Reference Format

Saeeda Naz,Arif Iqbal,Umar,Riaz Ahmad,Imran Siddiqi,Saad Bin,Ahmed,Muhammad Imran,Razzak,Faisal Shafait (2017). Urdu Nastaliq recognition using convolutional-recursive deep learning.
Saeeda Naz,Arif Umar,Riaz Ahmad,Saad Ahmed,Syed Shirazi,Imran Siddiqi,Muhammad Razzak (2016). Offline cursive Urdu-Nastaliq script recognition using multidimensional recurrent neural networks.
Maroua Tounsi,Ikram Moalla,Adel Alimi,Frank Lebourgeois Arabic characters recognition in natural scenes using sparse coding for feature representations.
A Graves,M Liwicki,S Fernandez,R Bertolami,H Bunke,J Schmidhuber (2009). A Novel Connectionist System for Unconstrained Handwriting Recognition.
Ahmed Saad Bin,Saeeda Naz,Salahuddin Swati,Muham-Mad Imran Razzak (2017). Handwritten Urdu Character Recognition using 1-Dimensional BLSTM Classifier.
Ryosuke Odate,Hideaki Goto (2016). Highly-accurate fast candidate reduction method for Japanese/Chinese character recognition.
Ahmed Saad Bin,Saeeda Naz,Muhammad Imran,Razzak,Rubiyah Yousaf (2017). Deep Learning based Isolated Arabic Scene Character Recognition.
Ahmed Saad Bin,Saeeda Naz,Muhammad Imran Razzak,Rubiyah Yusof Evaluation of Handwritten Urdu Text by Integration of MNIST Dataset Learning Experience.
Saad Ahmed,Saeeda Naz,Muhammad Razzak,Rubiyah Yusof,Thomas Breuel (2016). Balinese Character Recognition Using Bidirectional LSTM Classifier.
Saeeda Naz,Saad Ahmed,Riaz Ahmad,Muhammad Razzak (2016). Zoning Features and 2DLSTM for Urdu Text-line Recognition.
Ahmed Saad Bin,Saeeda Naz,Muhammad Imran,Razzak Shiekh,Faisal Rashid,Muhammad Zeeshan Afzal,Thomas Breuel (2016). Evaluation of cursive and non-cursive scripts using recurrent neu-ral networks.
Alex Graves (2012). Supervised Sequence Labelling with Recurrent Neural Networks.
Alex Graves,Santiago Fernández,Faustino Gomez,Jürgen Schmidhuber (2006). Connectionist temporal classification.
Z Zhang,L Jin,K Ding,X Gao Character-SIFT: A Novel Feature for Offline Handwritten Chinese Character Recognition.
Mohit Jain,Minesh Mathew,C Jawahar (2017). Unconstrained scene text and video text recognition for Arabic script.
Sonia Yousfi,Sid-Ahmed Berrani,Christophe Gar-Cia ;,Jean Hennebert,Sameh Masmoudi,Touj,Rolf Ingold,Najoua Essoukri,Ben Amara A dataset for Arabic text detection, tracking and recognition in news videos-AcTiV.
M,Ben Halima,H Karray,A Alimi (2013). Arabic Text Recognition in Video Sequences.
Saeeda Naz,Arif Umar,Riaz Ahmed,Muhammad Razzak,Sheikh Rashid,Faisal Shafait (2016). Urdu Nasta’liq text recognition using implicit segmentation based on multi-dimensional long short term memory neural networks.

Download References

Funding

No external funding was declared for this work.

Conflict of Interest

The authors declare no conflict of interest.

Ethical Approval

No ethics committee approval was required for this article type.

Data Availability

Not applicable for this article.

How to Cite This Article

Saad Bin Ahmed. 2019. \u201cSub-sampling Approach for Unconstrained Arabic Scene Text Analysis by Implicit Segmentation based Deep Learning Classifier\u201d. Global Journal of Computer Science and Technology - D: Neural & AI GJCST-D Volume 19 (GJCST Volume 19 Issue D1): .

More Citation Formats

Select Citation Style:

Download Citation

Download Article

GJCST Volume 19 Issue D1
Pg. 7- 16

Explore Journals Explore Volume Read This Issue

Journal Specifications

Crossref Journal DOI 10.17406/gjcst

Print ISSN 0975-4350

e-ISSN 0975-4172

Keywords

Not Found

Classification

GJCST-D Classification: I.2.6

Submission ReceivedDecember 15, 2018
Peer Review Double Blind
Handling Editor
Accepted January 5, 2019
Published January 15, 2019

Version of record

v1.2

Issue date

March 26, 2019

Language

Experiance in AR

Explore published articles in an immersive Augmented Reality environment. Our platform converts research papers into interactive 3D books, allowing readers to view and interact with content using AR and VR compatible devices.

View in VR

Read in 3D

Your published article is automatically converted into a realistic 3D book. Flip through pages and read research papers in a more engaging and interactive format.

View in 3D

Article Matrices

Total Score: 104

Country: Unknown

Subject: Global Journal of Computer Science and Technology - D: Neural & AI

Authors: Saad Bin Ahmed, Zainab Malik, Muhammad Imran Razzak, Rubiyah Yusof (PhD/Dr. count: 0)

View Count (all-time): 266

Total Views (Real + Logic): 5265

Total Downloads (simulated): 1482

Publish Date: 2019 03, Tue

Monthly Totals (Real + Logic):

Month 1: 61 views
Month 2: 48 views
Month 3: 30 views
Month 4: 47 views
Month 5: 29 views
Month 6: 38 views
Month 7: 41 views
Month 8: 43 views
Month 9: 55 views
Month 10: 53 views
Month 11: 18 views
Month 12: 35 views
Month 13: 14 views
Month 14: 20 views
Month 15: 32 views
Month 16: 29 views
Month 17: 14 views
Month 18: 32 views
Month 19: 32 views
Month 20: 20 views
Month 21: 22 views
Month 22: 29 views
Month 23: 15 views
Month 24: 14 views
Month 25: 26 views
Month 26: 26 views
Month 27: 31 views
Month 28: 24 views
Month 29: 25 views
Month 30: 26 views
Month 31: 31 views
Month 32: 41 views
Month 33: 22 views
Month 34: 20 views
Month 35: 17 views
Month 36: 25 views
Month 37: 20 views
Month 38: 22 views
Month 39: 43 views
Month 40: 47 views
Month 41: 28 views
Month 42: 44 views
Month 43: 15 views
Month 44: 45 views
Month 45: 37 views
Month 46: 35 views
Month 47: 27 views
Month 48: 31 views
Month 49: 31 views
Month 50: 36 views
Month 51: 33 views
Month 52: 37 views
Month 53: 23 views
Month 54: 39 views
Month 55: 21 views
Month 56: 22 views
Month 57: 34 views
Month 58: 45 views
Month 59: 40 views
Month 60: 26 views
Month 61: 41 views
Month 62: 13 views
Month 63: 26 views
Month 64: 30 views
Month 65: 26 views
Month 66: 43 views
Month 67: 31 views
Month 68: 23 views
Month 69: 19 views
Month 70: 38 views
Month 71: 28 views
Month 72: 28 views
Month 73: 22 views
Month 74: 45 views
Month 75: 30 views
Month 76: 40 views
Month 77: 18 views
Month 78: 47 views
Month 79: 14 views
Month 80: 33 views
Month 81: 30 views
Month 82: 25 views
Month 83: 62 views
Month 84: 57 views
Month 85: 64 views

Total Views: 5265

Total Downloads: 1482

2026 Trends

Published Article

Our website is actively being updated, and changes may occur frequently. Please clear your browser cache if needed. For feedback or error reporting, please email [email protected]