Designing an Arabic Handwritten Segmentation System

SN Computer Science, 2020

The issue of handwritten recognition in Arabic script nature has attracted many researchers from both academic and industrial fields. But their efforts have not reached satisfying outcomes till now. In this paper, a survey has been done in segmentation and recognition of handwritten documents in Arabic script. Most of the previous published works have been analyzed, and some remedies have been suggested. Various strategies used for creating a powerful recognition system have been summarized. This paper presents various algorithms with respect to text, word and characters segmentation and recognition of Arabic document. It analyzes the recognition stage of Arabic script depending on segmentation strategies.

The accuracy of handwritten word segmentation is essential for the recognition results; however, it is extremely complex task. In this work, an enhanced technique for Arabic handwriting segmentation is proposed. This technique is based on a recent technique which is dubbed in this work the base technique. It has two main stages: over-segmentation and neural-validation. Although the base technique gives promising results, it still suffers from many drawback such as the missed and bad segmentation-points(SPs). To alleviate these problems, two enhancements has been integrated in the first stage: word to sub-word segmentation and the thinned word restoration. Additionally, in the neural-validation stage an enhanced area concatenation technique is utilized to handle the segmentation of complex characters such as .س Both techniques were evaluated using the IFN/ENIT database. The results show that the bad and missed SPs have been significantly reduced and the overall performance of the system is increased.

Procedia Computer Science, 2015

Automatic recognition of writing is among the most important axes in the NLP (Natural language processing). Several entities of different areas demonstrated the need in recognition of handwritten Arabic characters; particularly banks check processing, post office for the automation of mail sorting, the insurance for the treatment of forms and many other industries. One of the most important operations in a handwriting recognition system is segmentation. Segmentation of handwritten text is a necessary step in the development of a system of automatic writing recognition. Its goal is to try to extract all areas of the lines of the text, and this operation is made difficult in the case of handwriting, by the presence of irregular gaps or overlap between lines and fluctuations of the guidance of scripture to the horizontal. In this paper, we have developed three approaches of handwritten Arabic text segmentation, then we compared between these three approaches.

2009 10th International Conference on Document Analysis and Recognition, 2009

In this paper, we introduce an on-line Arabic handwritten recognition system based on new stroke segmentation algorithm. The proposed algorithm uses an over segmentation method that has the advantage of giving all correct segments at least. It is based on arbitrary segmentation followed by segmentation enhancement, consecutive joints connection and finally segmentation point locating. The proposed system gives an excellent recognition rate up to 97% and 92% for words and letter recognition.

Automatic off-line Arabic handwriting recognition still faces a big challenges. Due to the cursive nature of the Arabic language, most of published works are based on recognition of a whole word without segmentation. This paper presents a new framework for the recognition of handwritten Arabic words based on segmentation. This framework involves two phases (training phase and testing phase). In the training phase, Arabic handwritten characters were trained to be recognized, while in the testing phase, words were segmented into characters for recognition. Classification is achieved in two steps (classification of the segmented characters and classification of the word). A dictionary is constructed and used to correct any errors occurring during the previous stages of the recognition process. This work has been tested with IFN/ENIT database and a comparison made against some existing methods and promising results have been obtained.

Int. Arab J. Inf. Technol., 2017

Handwriting recognition is an important field as it has many practical applications such as for bank cheque processing, post office address processing and zip code recognition. Most applications are developed exclusively for Latin characters. However, despite tremendous effort by researchers in the past three decades, Arabic handwriting recognition accuracy remains low because of low efficiency in determining the correct segmentation points. This paper presents an approach for character segmentation of unconstrained handwritten Arabic words. First, we seek all possible character segmentation points based on structural features. Next, we develop a novel technique to create several paths for each possible segmentation point. These paths are used in differentiating between different types of segmentation points. Finally, we use heuristic rules and neural networks, utilizing the information related to segmentation points, to select the correct segmentation points. For comparison, we app...

2007

The last two decades witnessed some advances in the development of an Arabic character recognition (CR) system. Arabic CR faces technical problems not encountered in any other language that make Arabic CR systems achieve relatively low accuracy and retards establishing them as market products. We propose the basic stages towards a system that attacks the problem of recognizing online Arabic cursive handwriting. Rule-based methods are used to perform simultaneous segmentation and recognition of word portions in an unconstrained cursively handwritten document using dynamic programming. The output of these stages is in the form of a ranked list of the possible decisions. A new technique for text line separation is also used.

2011

A precise and efficient segmentation for handwritten Arabic text is a vital prerequisite for the accuracy of the subsequent recognition phase. In this paper, we present a dualphase segmentation approach. The proposed approach starts first by detecting and resolving sub-words overlapping, then a topological features based segmentation is applied by means of a set of heuristic rules. Because of its crucial importance, the segmentation phase is preceded by a handwritten specific preprocessing phase, that considers issues like word’s skewand slantcorrection. The proposed approach has been successfully tested on a database of handwritten Arabic words, that contains more than 3000 words images. The results were very promising and indicating the efficiency of our approach. KeywordsArabic Handwriting Segmentation, Handwriting Topological Features, Pattern Recognition.

Mobile Multimedia/Image Processing, Security, and Applications 2012, 2012

This paper is concerned with pre-processing and segmentation tasks that influence the performance of Optical Character Recognition (OCR) systems and handwritten/printed text recognition. In Arabic, these tasks are adversely effected by the fact that many words are made up of sub-words, with many sub-words there associated one or more diacritics that are not connected to the sub-word's body; there could be multiple instances of sub-words overlap. To overcome these problems we investigate and develop segmentation techniques that first segment a document into sub-words, link the diacritics with their sub-words, and removes possible overlapping between words and sub-words. We shall also investigate two approaches for pre-processing tasks to estimate sub-words baseline, and to determine parameters that yield appropriate slope correction, slant removal. We shall investigate the use of linear regression on sub-words pixels to determine their central x and y coordinates, as well as their high density part. We also develop a new incremental rotation procedure to be performed on sub-words that determines the best rotation angle needed to realign baselines. We shall demonstrate the benefits of these proposals by conducting extensive experiments on publicly available databases and in-house created databases. These algorithms help improve character segmentation accuracy by transforming handwritten Arabic text into a form that could benefit from analysis of printed text.

In the literature, two methods for the extraction zones of the document are more used. The first method is based on the Mathematical Morphology (MM). The second is based on Hough Transform (HT). The main contribution of this paper is the application of these methods to extract the handwritten components of the complex document. The second contribution is the combination between the HT and the MM. The third contribution is the use of these three developed methods to automatically extract the handwritten components from CENPARMI bank check: numerical amount, literal amount and date zone. We present a concept for automatic evaluation of the results, based on a label tools for the different part of the used documents. We achieve a correct extraction rate of 98.27% for numerical amount, 91.82% for literal amount, and 99.63% for date, extracted by hybrid method HT-MM.