ICDAR 2009 Arabic Handwriting Recognition Competition
Published 1 January 2009
Volker Märgner, Haikal El Abed
Citations76
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The Online Arabic handwriting recognition competition held at ICDAR 2009 uses the ADAB-database with Arabic onlinehandwritten words and the most important characteristic of classification systems, recognition rate is compared.
Abstract
This paper describes the Online Arabic handwritingrecognition competition held at ICDAR 2009. This firstcompetition uses the ADAB-database with Arabic onlinehandwritten words. This year, 3 groups with 7 systems areparticipating in the competition. The systems were tested onknown data (sets 1 to 3) and on one test dataset which is unknownto all participants (set 4). The systems are comparedon the most important characteristic of classification systems,the recognition rate. Additionally, the relative speedof the different systems were compared. A short descriptionof the participating groups, their systems, the experimentalsetup, and the performed results are presented.
Keywords
Computer Science
Neural ComputationLong Short-Term Memory
98,079 Citations1997Sepp Hochreiter, Jürgen Schmidhuber
A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Studies in computational intelligenceSupervised Sequence Labelling with Recurrent Neural Networks
3,084 Citations2012Alex Graves
A new type of output layer that allows recurrent networks to be trained directly for sequence labelling tasks where the alignment between the inputs and the labels is unknown, and an extension of the long short-term memory network architecture to multidimensional data, such as images and video sequences.
Offline Arabic Handwriting Recognition with Multidimensional Recurrent Neural Networks
703 Citations2012Alex Graves
This paper introduces a globally trained offline handwriting recogniser that takes raw pixel data as input and does not require any alphabet specific preprocessing, and can therefore be used unchanged for any language.
IFN/ENIT: database of handwritten arabic words
428 Citations2002Mario Pechwitz, Samia Snoussi Maddouri +3 more
Lecture notes in computer scienceMulti-dimensional Recurrent Neural Networks
278 Citations2007Alex Graves, Santiago Fernández +1 more
Multi-dimensional recurrent neural networks are introduced, thereby extending the potential applicability of RNNs to vision, video processing, medical imaging and many other areas, while avoiding the scaling problems that have plagued other multi-dimensional models.
ICDAR 2005 Arabic handwriting recognition competition
196 Citations2005Volker Märgner, Mario Pechwitz +1 more
This paper describes the Arabic handwriting recognition competition held at ICDAR 2007, again uses the IFN/ENIT-database with Arabic handwritten Tunisian town names, and 8 groups with 14 systems are participating in the competition.
Arabic handwriting recognition using baseline dependant features and hidden Markov modeling
164 Citations2005Ramy El-Hajj, Laurence Likforman-Sulem +1 more
A 1D HMM offline handwriting recognition system employing an analytical approach supported by a set of robust language independent features extracted on binary images and learns character models without character pre-segmentation.
IEEE Transactions on Pattern Analysis and Machine IntelligenceCombining Slanted-Frame Classifiers for Improved HMM-Based Arabic Handwriting Recognition
144 Citations2009R. Al-Hajj Mohamad, Laurence Likforman-Sulem +1 more
The results show that the combination of classifiers performs better than a single classifier dealing with slant-corrected images and that the approach is robust for a wide range of orientation angles.
Improvements of a lexicon directed algorithm for recognition of unconstrained handwritten words
140 Citations2002Fumitaka Kimura, M. Shridhar +1 more
Improvements made to a lexicon directed algorithm for recognition of unconstrained handwritten words (cursive, discrete, or mixed) such as those encountered in mail pieces, in order to achieve higher recognition accuracy and speed.
ICDAR 2009 Handwriting Recognition Competition
116 Citations2009Emmanuèle Grosicki, Haikal El Abed
This paper describes the handwriting recognition competition held at ICDAR 2009, based on the RIMES-database, with French written text documents, which shows interesting results.
Pattern Recognition LettersOff-line handwritten word recognition using multi-stream hidden Markov models
101 Citations2009Yousri Kessentini, Thierry Paquet +1 more
A multi-stream approach for off-line handwritten word recognition that combines low level feature streams namely, density based features extracted from 2 different sliding windows with different widths, and contours extracted from upper and lower contours is presented.
ICDAR 2009 Online Arabic Handwriting Recognition Competition
71 Citations2009Haikal El Abed, Volker Märgner +2 more
This paper describes the Online Arabic handwriting recognition competition held at ICDAR 2009, which uses the ADAB-database with Arabic online handwritten words and compares the systems on the most important characteristic of classification systems, the recognition rate.
Combining Multiple HMMs Using On-line and Off-line Features for Off-line Arabic Handwriting Recognition
71 Citations2009Mahdi Hamdani, Haikal El Abed +2 more
Modified MMI/MPE
60 Citations2008Georg Heigold, Thomas Deselaers +2 more
This paper shows how common speech recognition training criteria such as the Minimum Phone Error criterion or the Maximum Mutual Information criterion can be extended to incorporate a margin term, and shows that the proposed criteria are equivalent to Support Vector Machines with suitable smooth loss functions.
Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern RecognitionWhite-space models for offline Arabic handwriting recognition
57 Citations2008Philippe Dreuw, Stephan Jonas +1 more
A separate character model for white-spaces in combination with a lexicon using different writing variants and character model length adaptation is proposed for Arabic handwriting recognition.
The IFN/ENIT-database - a tool to develop Arabic handwriting recognition systems
56 Citations2007Haikal El Abed, Volker Märgner
The IFN/ENIT-database of handwritten Tunisian town names is used by many research groups working on recognition systems and an example of using the data for developing baseline estimation methods is given.
Combination of local and global vision modelling for Arabic handwritten words recognition
54 Citations2003Samia Snoussi Maddouri, Hossein Amiri
An Arabic handwritten word recognition system based on the idea of the PERCEPTRO system developed by Cote (Cote et al. (1998) for Latin word recognition is proposed, combining a global and a local vision modeling of the word.
Arabic Handwriting Recognition Using Restored Stroke Chronology
50 Citations2009Abdelkarim Elbaati, Houcine Boubaker +4 more
This work uses a genetic algorithm to optimize the sequences of handwritten strokes and uses the beta-elliptical modelling which is developed in on-line systems to calculate other characteristics of the off-line handwriting recognition.
A neural network-hidden Markov model hybrid for cursive word recognition
46 Citations2002S. Knerr, E. Augustin
A neural network-hidden Markov model hybrid for the recognition of cursive words which are represented as left-right sequences of graphemes is presented, showing recognition rates close to 93% for the 30 word vocabulary relevant for French legal amounts.
Pattern Recognition LettersLexicon reduction using dots for off-line Farsi/Arabic handwritten word recognition
41 Citations2007Saeed Mozaffari, Karim Faez +2 more
A new concept of using dots in a cursively handwritten Farsi/Arabic word is introduced for lexicon reduction and a fast method for extracting dots is presented, which achieves the speedup factor of 2 as well as 13% improvement in recognition rate.
ICDAR 2007 - Arabic Handwriting Recognition Competition
39 Citations2007Martin A. Volker
This paper describes the Arabic handwriting recognition competition held at ICDAR 2007, which again uses the IFN/ENITdatabase with Arabic handwritten Tunisian town names and describes the participating groups, their systems, and the results achieved.
Confidence-Based Discriminative Training for Model Adaptation in Offline Arabic Handwriting Recognition
31 Citations2009Philippe Dreuw, Georg Heigold +1 more
An unsupervised confidence-based discriminative training for model adaptation approach for an HMM based Arabic handwriting recognition system to handle different handwriting styles and their variations is presented.
Model length adaptation of an HMM based cursive word recognition system
23 Citations2004Marc-Peter Schambach
A method for the visualization of letter HMMs shows the plausibility of most results, but also the limitations of the proposed method, however, these are mostly due to given restrictions of the training and recognition method of the underlying system.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIEImprovement of Arabic handwriting recognition systems; combination and/or reject?
16 Citations2008Haikal El Abed, Volker Märgner
A comparison between two different combination schemes for the improvement of the performance of Arabic handwriting recognition systems based on fixed fusion using logical rules and trainable rules is presented.
HAL (Le Centre pour la Communication Scientifique Directe)Un système de reconnaissance de mots arabes manuscrits hors-ligne sans signes diacritiques
7 Citations2008F. Menasri, N. Vincent +2 more
HAL (Le Centre pour la Communication Scientifique Directe)Reconnaissance de l'écriture arabe cursive : combinaison de classifieurs MMCs à fenêtres orientées
2 Citations2006Ramy Al-Hajj, Chafic Mokbel +1 more