A dataset for Arabic text detection, tracking and recognition in news videos- AcTiV

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

doi:10.1109/icdar.2015.7333911

Cited by 52 publications

(36 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As mentioned in the introduction, AcTiV 1.0 (http://tc11.cvc.uab.es/datasets/AcTiV_1) was presented in the ICDAR'15 conference [14] as the first publicly accessible annotated dataset designed to assess the performance of different Arabic Video OCR systems. This database is currently used by several research groups around the world.…”

Section: Data Characteristics and Statisticsmentioning

confidence: 99%

“…We selected from these video clips 1843 frames dedicated to the detection task. In [14,46], the first results using AcTiV 1.0 were presented.…”

Section: Data Characteristics and Statisticsmentioning

confidence: 99%

“…The LADI text detection system is based in our previous work [14,46], with new added enhancements considering the color consistency of near text regions. Our text detector represents a hybrid approach consisting of two stages: a CC-based heuristic algorithm and a machine learning classification.…”

Section: Ladi Detectormentioning

confidence: 99%

“…AcTiV 2.0 is an important extension of the one published in ICDAR 2015 [14]. It includes 189 video clips with an average length of 10 min per sequence for a global duration of about 31 h. These video sequences have been collected from four different Arabic news channels during the period between October 2013 and March 2016.…”

mentioning

confidence: 99%

See 3 more Smart Citations

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

et al. 2018

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Data Characteristics and Statisticsmentioning

confidence: 99%

“…We selected from these video clips 1843 frames dedicated to the detection task. In [14,46], the first results using AcTiV 1.0 were presented.…”

Section: Data Characteristics and Statisticsmentioning

confidence: 99%

Section: Ladi Detectormentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

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

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…The Activ video dataset developed by Zayene et al [36] has been developed to include 80 videos consisting of more than 850,000 frames, from four different Arabic news channels. However this dataset has been designed specifically to retrieve text from closed captions and assess the performance of text detection, tracking and recognition systems.…”

Section: Video Datasetmentioning

confidence: 99%