Sameh Awaida

An Arabic handwriting synthesis system

Abstract In this paper, we present an Arabic handwriting synthesis system. Two concatenation models to synthesize Arabic words from segmented characters are adopted: Extended-Glyphs connection and Synthetic-Extensions connection. We use our system to synthesize handwriting from a collected dataset and inject it into an expanded dataset. We experiment by training a state-of-the-art Arabic handwriting recognition system on the collected dataset, as well as on the expanded dataset, and test it on the IFN/ENIT Arabic benchmark dataset. We show significant improvement in recognition performance due to the data that was synthesized by our system.

WRITER IDENTIFICATION OF ARABIC TEXT USING STATISTICAL AND STRUCTURAL FEATURES

This article addresses writer identification of handwritten Arabic text. Several types of structural and statistical features were extracted from Arabic handwriting text. A novel approach was used to extract structural features that build on some of the main characteristics of the Arabic language. Connected component features for Arabic handwritten text as well as gradient distribution features, windowed gradient distribution features, contour chain code distribution features, and windowed contour chain code distribution features were extracted. A nearest neighbor (NN) classifier was used with the Euclidean distance measure. Data reduction algorithms (viz. principal component analysis [PCA], linear discriminant analysis [LDA], multiple discriminant analysis [MDA], multidimensional scaling [MDS], and forward/backward feature selection algorithm) were used. A database of 500 paragraphs handwritten in Arabic by 250 writers was used. The paragraphs used were randomly generated from a large corpus. NN provided the best accuracy in text-independent writer identification with top-1 result of 88.0%, top-5 result of 96.0%, and top-10 result of 98.5% for the first 100 writers. Extending the work to include all 250 writers and with the backward feature selection algorithm (using 54 out of 83 features), the system attained a top-1 result of 75.0%, top-5 result of 91.8%, and top-10 result of 95.4%.

ICFHR2014 Competition on Arabic Writer Identification Using AHTID/MW and KHATT Databases

This paper describes the first edition of the Arabic writer identification competition using AHTID/MW and KHATT databases held in the context of the 14th International Conference on Frontiers in Handwriting Recognition (ICFHR2014). This competition has used the new freely available Arabic Handwritten Text Images Database written by Multiple Writers (AHTID/MW) and the Arabic handwritten text database called KHATT presented in ICFHR2012. We propose three tasks in this Arabic writer identification competition: the first and second are based respectively on word and text line level using the AHTID/MW database and the third one is paragraph based using the KHATT database. We received one system for the second task, three systems for the third task and none for the first task. All systems are tested in a blind manner using a set of images kept internal. A short description of the participating groups, their systems, the experimental setup, and the observed results are presented.

Arabic ligatures: Analysis and application in text recognition

The Arabic script allows the replacement of certain character sequences by more compact forms called ligatures. Such ligatures lack a systematic analysis despite their importance in Arabic text recognition research. In this paper, we present analysis of ligatures and compile a comprehensive list of Arabic ligatures. Then, we perform recognition experiments on a benchmark database to show the impact of ligatures annotation in Arabic databases. Finally, we propose several guidelines for the design of representative and compact Arabic databases from the aspect of ligatures.

Arabic and Farsi Font Recognition: Survey

Font Recognition (FR) is useful in improving optical text recognition accuracy and time. In addition, it can be used to restore the original document text fonts, styles and sizes. In this paper, we survey the literature of Arabic and Farsi FR research and used databases. The main phases of FR systems are surveyed (viz. preprocessing, classification techniques and used features). All published work of Arabic and Farsi FR, which the authors are aware of, are surveyed. To our knowledge, this is the first survey of Arabic/Farsi FR and used databases. In addition, the paper addresses the strengths and limitations of the presented techniques and specified areas of research that are not, so far, addressed in Arabic/Farsi FR as well as areas of possible improvement.

Automatic Check Digits Recognition for Arabic Using Multi-Scale Features, HMM and SVM Classifiers

We propose in this work two Automatic Arabic (Indian) digits recognition systems using a real-life dataset of 3000 bank checks. The systems extracts features from training-set images of 7390 isolated digits (0-9). These features are multi-scale in which they capture narrow, intermediate, and large-scale qualities of the image. The gradient features correspond to the narrow scale, the structural features correspond to the intermediate scale, and the concavity features correspond to the large-scale. These features are employed by two different statistical classifiers; Hidden Markov Models (HMM) and Support Vector Machines (SVM). The two independent recognition systems utilize the proficient CENPARMI Arabic bank check database for training and testing. In order to select the optimal parameters for feature extraction and for the HMM classifier, the CENPARMI training dataset is divided into training and verification subsets. After adapting the two systems’ parameters, they are tested on unobserved 3035 digit images. The average recognition rates for the HMM and SVM systems are 97.86% and 99.04%, respectively. The presented systems provides state-of-the-art recognition results on the CENPARMI database, as they reported a higher recognition rates when compared to twelve previously published systems, especially for the SVM system. After analyzing the classification errors, the authors conclude that some of these errors are inevitable as they are most probably attributed to errors in labeling the original database, distinct writing styles of certain digits, and genuine faults.

Text independent writer identification of Arabic manuscripts and the effects of writers increase

This article addresses text-independent writer identification of Arabic manuscripts. Several types of statistical features are extracted from historical Arabic manuscripts. Gradient distribution features for Arabic handwritten text as well as windowed gradient distribution features, contour chain code distribution features, and windowed contour chain code distribution features are extracted. A nearest neighbor (NN) classifier is used with the Euclidean distance measure. Due to the lack of publicly available Arabic manuscript database, this work designed and collected a database of 10,000 Arabic manuscript images handwritten by 200 different historical scholars. Using 8,000 images for training and 2,000 images for testing, the proposed writer identification classifier achieved a top-1, top-5, and top-10 recognition rates of 93.95%, 98.30%, and 99.10%, respectively. The effects of increasing the number of writers on the accuracy results are presented and analyzed.