Recurrent neural networks are powerful sequence learners. They are able to incorporate context information in a flexible way, and are robust to localised distortions of the input data. These properties make them well suited to sequence labelling, where input sequences are transcribed with streams of labels. The aim of this thesis is to advance the state-of-the-art in supervised sequence labelling with recurrent networks. Its two main contributions are (1) 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 (2) an extension of the long short-term memory network architecture to multidimensional data, such as images and video sequences.

https://mediatum.ub.tum.de/doc/673554/file.pdf

Supervised Sequence Labelling with Recurrent Neural Networks

Offline handwriting recognition—the automatic transcription of images of handwritten text—is a challenging task that combines computer vision with sequence learning. In most systems the two elements are handled separately, with sophisticated preprocessing techniques used to extract the image features and sequential models such as HMMs used to provide the transcriptions. By combining two recent innovations in neural networks—multidimensional recurrent neural networks and connectionist temporal classification—this paper introduces a globally trained offline handwriting recogniser that takes raw pixel data as input. Unlike competing systems, it does not require any alphabet specific preprocessing, and can therefore be used unchanged for any language. Evidence of its generality and power is provided by data from a recent international Arabic recognition competition, where it outperformed all entries (91.4% accuracy compared to 87.2% for the competition winner) despite the fact that neither author understands a word of Arabic.

/pdf/offline-handwriting-recognition-with-multidimensional-4710cm0ru0.pdf

Offline Handwriting Recognition with Multidimensional Recurrent Neural Networks

Using recurrent neural network models for early detection of heart failure onset.

The automatic recognition of text on scanned images has enabled many applications such as searching for words in large volumes of documents, automatic sorting of postal mail, and convenient editing of previously printed documents. The domain of handwriting in the Arabic script presents unique technical challenges and has been addressed more recently than other domains. Many different methods have been proposed and applied to various types of images. This paper provides a comprehensive review of these methods. It is the first survey to focus on Arabic handwriting recognition and the first Arabic character recognition survey to provide recognition rates and descriptions of test data for the approaches discussed. It includes background on the field, discussion of the methods, and future research directions.

Offline Arabic handwriting recognition: a survey

Recurrent neural networks (RNNs) with Long Short-Term memory cells currently hold the best known results in unconstrained handwriting recognition. We show that their performance can be greatly improved using dropout - a recently proposed regularization method for deep architectures. While previous works showed that dropout gave superior performance in the context of convolutional networks, it had never been applied to RNNs. In our approach, dropout is carefully used in the network so that it does not affect the recurrent connections, hence the power of RNNs in modeling sequences is preserved. Extensive experiments on a broad range of handwritten databases confirm the effectiveness of dropout on deep architectures even when the network mainly consists of recurrent and shared connections.

/pdf/dropout-improves-recurrent-neural-networks-for-handwriting-2di6lmbs26.pdf

Dropout Improves Recurrent Neural Networks for Handwriting Recognition

Standard databases play essential roles for evaluating and comparing results obtained by different groups of researchers. In this paper, an Arabic Handwritten Text Images Database written by Multiple Writers (AHTID/MW) is introduced. This database can be used for research in the recognition of Arabic handwritten text with open vocabulary, word segmentation and writer identification. The AHTID/MW contains 3710 text lines and 22896 words written by 53 native writers of Arabic. In addition, ground truth annotation is provided for each text image. The database is freely available for worldwide researchers.

/pdf/a-database-for-arabic-handwritten-text-image-recognition-and-1n5eym4joo.pdf

A Database for Arabic Handwritten Text Image Recognition and Writer Identification

This paper describes the on-line Arabic handwriting recognition competition held at tenth International Conference on Document Analysis and Recognition (ICDAR in Proceedings of the 10th international conference on document analysis and recognition, vol 3, pp 1388–1392, 2009). This first competition uses the so-called ADAB database with Arabic on-line handwritten words. At this first competition, 3 groups with 7 different systems have participated. The systems were tested on known data (training datasets made available for the participants, sets 1 to 3) and on one test dataset that is unknown to all participants (set 4). The systems are compared on the most important characteristic of classification systems, the recognition rate. Additionally, the relative speed of the different systems was compared. A short description of the participating groups, their systems, the experimental setup, and the performed results is presented.

On-line Arabic handwriting recognition competition: ADAB database and participating systems

In this paper we present a system of the off-line handwriting recognition. Our recognition system is based on temporal order restoration of the off-line trajectory. For this task we use a genetic algorithm (GA) to optimize the sequences of handwritten strokes. To benefit from dynamic informations we make a sampling operation by the consideration of trajectory curvatures. We proceed to calculate the curvilinear velocity signal and use the beta-elliptical modelling which is developed in on-line systems to calculate other characteristics. Our approach is validated by Hmm Tool Kit (HTK) recognition system using IFN/ENIT database.

http://www.cvc.uab.es/icdar2009/papers/3725a411.pdf

Arabic Handwriting Recognition Using Restored Stroke Chronology

The great success and high recognition rates of both OCR systems and recognition systems for handwritten words are unconceivable without the availability of huge datasets of real world data. This chapter gives a short survey of datasets used for recognition with special focus on their application. The main part of this chapter deals with Arabic handwriting, datasets for recognition systems, and their availability. A description of different datasets and their usability is given, and the results of a competition are presented. Finally, a strategy for the development of Arabic handwriting recognition systems based on datasets and competitions is presented.

Databases and competitions: strategies to improve Arabic recognition systems

This paper describes the Arabic handwriting recognition competition held at International Conference on Document Analysis and Recognition (ICDAR) 2011. This fifth competition again used the IfN/ENIT-database with Arabic handwritten Tunisian town names. Today, more than 110 research groups from universities, research centers, and industry are working with this database worldwide. This year, 4 groups with 4 systems were participating in the competition. The systems were tested on known data (sets d and e) and on two data sets which are unknown to the participants (sets f and s). The systems were compared based on the most important characteristic: the recognition rate. A short description of the participating groups, their systems, and the results achieved are finally presented.

/pdf/icdar-2011-arabic-handwriting-recognition-competition-1mj96whl75.pdf

Haikal El Abed

Papers

A Database for Arabic Handwritten Text Image Recognition and Writer Identification

On-line Arabic handwriting recognition competition: ADAB database and participating systems

Arabic Handwriting Recognition Using Restored Stroke Chronology

Databases and competitions: strategies to improve Arabic recognition systems

ICDAR 2011 - Arabic Handwriting Recognition Competition