文献类型： 会议论文
第一作者： Oussama Zayene
作者： Oussama Zayene 1 ; Jean Hennebert 1 ; Sameh Masmoudi Touj 2 ; Rolf Ingold 1 ; Najoua Essoukri Ben Amara 2 ;
作者机构： 1.DIVA group Department of Informatics, University ofFribourg (Unifr) Fribourg, Switzerland
2.SAGE lab National Engineering School of Sousse (Eniso), University of Sousse, Tunisia
关键词： Video OCR;Video database;Benchmark;Arabic text
会议名称： International Conference on Document Analysis and Recognition
主办单位：
页码： 996-1000
摘要： Recently, promising results have been reported on video text detection and recognition. Most of the proposed methods are tested on private datasets with non-uniform evaluation metrics. We report here on the development of a publicly accessible annotated video dataset designed to assess the performance of different artificial Arabic text detection, tracking and recognition systems. The dataset includes 80 videos (more than 850,000 frames) collected from 4 different Arabic news channels. An attempt was made to ensure maximum diversities of the textual content in terms of size, position and background. This data is accompanied by detailed annotations for each textbox. We also present a region-based text detection approach in addition to a set of evaluation protocols on which the performance of different systems can be measured.
分类号： TP391.41-53
- 相关文献
[1]ROBIN: a platform for evaluating Automatic Target Recognition algorithms. Part 2: protocols used for evaluating algorithms and results obtained on the SAGEM DS database. D. Duclos, J. Lonnoy,Q. Guillerm SAGEM DS,F. Julie CNRS-INRIA,S. Herbin ONERA,E.D'Angelo DGA/DET/ASC/EORD. 2008
[2]ROBIN: a platform for evaluating Automatic Target Recognition algorithms. Par 1: Overview of the project and presentation of the SAGEM DS competition. D. Duclos, J. Lonnoy,Q. Guillerm SAGEM DS,F. Julie CNRS-INRIA,S. Herbin ONERA,E.D'Angelo DGA/DET/ASC/EORD. 2008
作者其他论文 更多>>
-
Transductive Transfer Learning to Specialize a Generic Classifier Towards a Specific Scene
作者：Houda Maamatou;Thierry Chateau;Sami Gazzah;Yann Goyat;Najoua Essoukri Ben Amara
关键词：Transductive Transfer Learning;Specialization;Generic Classifier;Pedestrian Detection;Sequential Monte Carlo Filter (SMC)
-
Interactive Content-Based Document Retrieval Using Fuzzy Attributed Relational Graph Matching
作者：Ramzi CHAIEB;Karim KALTI;Najoua ESSOUKRI BEN AMARA
关键词：Fuzzy Attributed Relational Graph indexing;Graph matching distance;Document image retrieval;User interaction
-
Modalities Combination for Italian Sign Language Extraction and Recognition
作者：Bassem Seddik;Sami Gazzah;Najoua Essoukri Ben Amara
关键词：Motion spotting;Action recognition;Fisher vector;Modalities combination;Classification fusion
-
Extraction of Homogeneous Regions in Historical Document Images
作者：Maroua Mehri;Pierre Heroux;Nabil Sliti;Petra Gomez-Kramer;Najoua Essoukri Ben Amara;Remy Mullot
关键词：Historical Document Images;Segmentation;SLIC Superpixels;Gabor Filters;Multi-Scale Analysis;ARLSA
-
SID Signature Database: A Tunisian Off-line Handwritten Signature Database
作者：Imen Abroug Ben Abdelghani;Najoua Essoukri Ben Amara
关键词：Off-line handwritten signature;SID-Signature database;Tunisian signature;Planar modeling signature
-
Texture approach for nets extraction Application to old Arab newspapers images structuring
作者：Mohamed Aymen Charrada;Najoua Essoukri Ben Amara
关键词：Segmentation;degradations;historical Arab periodicals;Gabor filters;post-processing
