Open Datasets and Tools for Arabic Text Detection and Recognition in News Video Frames

Zayene, Oussama; Masmoudi Touj, Sameh; Hennebert, Jean; Ingold, Rolf; Essoukri Ben Amara, Najoua

doi:10.3390/jimaging4020032

Open AccessArticle

Open Datasets and Tools for Arabic Text Detection and Recognition in News Video Frames

by

Oussama Zayene

^1,2,*,

Sameh Masmoudi Touj

¹,

Jean Hennebert

³,

Rolf Ingold

² and

Najoua Essoukri Ben Amara

¹

LATIS Lab, National Engineering School of Sousse (Eniso), University of Sousse, Sousse 4054, Tunisia

²

DIVA Group, Department of Informatics, University of Fribourg (Unifr), Fribourg 1700, Switzerland

³

ICoSys Institute, HES-SO, University of Applied Sciences, Fribourg 1705, Switzerland

^*

Author to whom correspondence should be addressed.

J. Imaging 2018, 4(2), 32; https://doi.org/10.3390/jimaging4020032

Submission received: 26 November 2017 / Revised: 23 January 2018 / Accepted: 26 January 2018 / Published: 31 January 2018

(This article belongs to the Special Issue Document Image Processing)

Download

Browse Figures

Versions Notes

Abstract

Recognizing texts in video is more complex than in other environments such as scanned documents. Video texts appear in various colors, unknown fonts and sizes, often affected by compression artifacts and low quality. In contrast to Latin texts, there are no publicly available datasets which cover all aspects of the Arabic Video OCR domain. This paper describes a new well-defined and annotated Arabic-Text-in-Video dataset called AcTiV 2.0. The dataset is dedicated especially to building and evaluating Arabic video text detection and recognition systems. AcTiV 2.0 contains 189 video clips serving as a raw material for creating 4063 key frames for the detection task and 10,415 cropped text images for the recognition task. AcTiV 2.0 is also distributed with its annotation and evaluation tools that are made open-source for standardization and validation purposes. This paper also reports on the evaluation of several systems tested under the proposed detection and recognition protocols.

Keywords: video text detection; video text recognition; AcTiV dataset; Arabic Video OCR

Share and Cite

MDPI and ACS Style

Zayene, O.; Masmoudi Touj, S.; Hennebert, J.; Ingold, R.; Essoukri Ben Amara, N. Open Datasets and Tools for Arabic Text Detection and Recognition in News Video Frames. J. Imaging 2018, 4, 32. https://doi.org/10.3390/jimaging4020032

AMA Style

Zayene O, Masmoudi Touj S, Hennebert J, Ingold R, Essoukri Ben Amara N. Open Datasets and Tools for Arabic Text Detection and Recognition in News Video Frames. Journal of Imaging. 2018; 4(2):32. https://doi.org/10.3390/jimaging4020032

Chicago/Turabian Style

Zayene, Oussama, Sameh Masmoudi Touj, Jean Hennebert, Rolf Ingold, and Najoua Essoukri Ben Amara. 2018. "Open Datasets and Tools for Arabic Text Detection and Recognition in News Video Frames" Journal of Imaging 4, no. 2: 32. https://doi.org/10.3390/jimaging4020032

APA Style

Zayene, O., Masmoudi Touj, S., Hennebert, J., Ingold, R., & Essoukri Ben Amara, N. (2018). Open Datasets and Tools for Arabic Text Detection and Recognition in News Video Frames. Journal of Imaging, 4(2), 32. https://doi.org/10.3390/jimaging4020032

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Open Datasets and Tools for Arabic Text Detection and Recognition in News Video Frames

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI