Arabic Writer Identification Research Articles

Using Deep Learning for Arabic Writer Identification

Using Deep Learning for Arabic Writer Identification

Improving Arabic writer identification using score‐level fusion of textural descriptors

This paper investigates the problem of writer identification from handwriting samples in Arabic. The proposed technique relies on extracting small fragments of writing which are characterised using two textural descriptors, Histogram of Oriented Gradients (HOG) and Gray Level Run Length (GLRL) Matrices. Similarity scores realised using HOG and GLRL features are combined using a number of fusion rules. The system is evaluated on three well-known Arabic handwriting databases, the IFN/ENIT database with 411 writers, the KHATT database with 1000 writers, and QUWI database with 1,017 writers. Fusion using the ‘sum’ rule reports the highest identification rates reading 96.86, 85.40, and 76.27% on IFN/ENIT, KHATT, and QUWI databases, respectively. The results realised on the KHATT database are comparable to the state of the art while those reported on the IFN/ENIT and QUWI databases are the highest to the best of authors' knowledge.

Fuzzy ARTMAP Approach for Arabic Writer Identification using Novel Features Fusion

Arabic writer identification and associated tasks are still fresh due to huge variety of Arabic writer's styles. Current research presents a fusion of statistical features, extracted from fragments of Arabic handwriting samples to identify the writer using fuzzy ARTMAP classifier. Fuzzy ARTMP is supervised neural model, especially suited to classification problems. It is faster to train and need less number of training epochs to learn from input data for generalization. The extracted features are fed to Fuzzy ARTMP for training and testing. Fuzzy ARTMAP is employed for the first time along with a novel fusion of statistical features for Arabic writer identification. The entire IFN/ENIT database is used in experiments such that 75% handwritten Arabic words from 411 writers are employed in training and 25% for testing the system at random. Several combinations of extracted features are tested using fuzzy ARTMAP classifier and finally one combination exhibited promising accuracy of 94.724% for Arabic writer identification on IFN/ENIT benchmark database.

A model-based approach to offline text-independent Arabic writer identification and verification

Rapid movement generation models are described in the literature as an efficient tool to apprehend the handwriting behavior. Fields of application are diverse, including handwriting description, regeneration, and more recently OCR. In this paper, we propose a grapheme-based approach to offline Arabic writer identification and verification. Rather than extracting naturel graphemes from a training corpus using segmentation and clustering, it synthesizes its own graphemes based on the beta-elliptic model. Originality lies in the independence of the grapheme codebook from any training process, and the use of a model instead. One full and four partial codebooks are generated and tested. Using feature selection, raw codebooks are reduced in size with respect to FDR, FDR and cross-correlation, and random subsampling criteria. A total of 60 feature vectors are extracted using template matching, and evaluated with 411 individual writers from the IFN/ENIT database. The results presented in this study demonstrated the wide representativity and the good generalization capability of synthetic codebooks. We obtained a top1 rate=90.02% and a top5 rate=96.35% for writer identification, and an EER=2.1% for writer verification. Our approach showed better properties than most of the surveyed techniques in terms of supported corpus size and identification rates. To the best of our knowledge, this study is among the first to exploit the concept of model-based synthetic codebooks in writer identification and verification.

Text‐Dependent Writer Identification for Arabic Handwriting

This paper proposes a system for text‐dependent writer identification based on Arabic handwriting. First, a database of words was assembled and used as a test base. Next, features vectors were extracted from writers′ word images. Prior to the feature extraction process, normalization operations were applied to the word or text line under analysis. In this work, we studied the feature extraction and recognition operations of Arabic text on the identification rate of writers. Because there is no well‐known database containing Arabic handwritten words for researchers to test, we have built a new database of offline Arabic handwriting text to be used by the writer identification research community. The database of Arabic handwritten words collected from 100 writers is intended to provide training and testing sets for Arabic writer identification research. We evaluated the performance of edge‐based directional probability distributions as features, among other characteristics, in Arabic writer identification. Results suggest that longer Arabic words and phrases have higher impact on writer identification.

Off-line Arabic Character-Based Writer Identification – a Survey

Off-line writer identification requires transferring the text under consideration into an image file. This represents the only available solution to bring the printed materials to the electronic media. However, the transferring process causes the system to lose the temporal information of that text, which it can be gathered in on-line writer identification. Various techniques have been implemented to achieve high identification rates. These techniques have tackled different aspects of the identification system. Importance of writer identification system is to help mainly in forensic fields, historical document analysis and handwriting recognition system enhancement. Unfortunately, the Arabic writer identification system not achieves a satisfaction rate yet whereas certain process of features and classification still not recognized.

Arabic writer identification based on hybrid spectral–statistical measures

Many techniques have been reported for handwriting-based writer identification. None of these techniques assume that the written text is in Arabic. In this paper we present a new technique for feature extraction based on hybrid spectral–statistical measures (SSMs) of texture. We show its effectiveness compared with multiple-channel (Gabor) filters and the grey-level co-occurrence matrix (GLCM), which are well-known techniques yielding a high performance in writer identification in Roman handwriting. Texture features were extracted for wide range of frequency and orientation because of the nature of the spread of Arabic handwriting compared with Roman handwriting, and the most discriminant features were selected with a model for feature selection using hybrid support vector machine–genetic algorithm techniques. Four classification techniques were used: linear discriminant classifier (LDC), support vector machine (SVM), weighted Euclidean distance (WED), and the K nearest neighbours (K_NN) classifier. Experiments were performed using Arabic handwriting samples from 20 different people and very promising results of 90.0% correct identification were achieved.