Recognize printed Arabic letter using new geometrical features

Lecture Notes in Computer Science, 1997

The main theme of this paper is the automatic recognition of Arabic printed text using an artificial neural networks in addition to conventional techniques. This approach has a number of advantages: it combines rule-based (structural) and classification tests; and feature extraction is inexpensive and execution time is independent of character font and size. The technique can be divided into three major steps: The first step is pre-processing in which the original image is transformed into a binary image utilizing a 300 dpi scanner and then forming the connected component. Second, global features of the input Arabic word are then extracted such as number subwords, number of peaks within the subword, number and position of the complementary character, etc.. Finally, an artificial neural networks is used for character classification. The algorithm was implemented on a powerful MS-DOS based microcomputer and written in C.

IIUM Press eBooks, 2011

Optical Character Recognition (OCR) is the process of recognizing printed or handwritten text on paper documents. This paper proposes an OCR system for Arabic characters. In addition to the preprocessing phase, the proposed recognition system consists mainly of three phases. In the first phase, we employ word segmentation to extract characters. In the second phase, Histograms of Oriented Gradient (HOG) are used for feature extraction. The final phase employs Support Vector Machine (SVM) for classifying characters. We have applied the proposed method for the recognition of Jordanian city, town, and village names as a case study, in addition to many other words that offers the characters shapes that are not covered with Jordan cites. The set has carefully been selected to include every Arabic character in its all four forms. To this end, we have built our own dataset consisting of more than 43.000 handwritten Arabic words (30000 used in the training stage and 13000 used in the testing stage). Experimental results showed a great success of our recognition method compared to the state of the art techniques, where we could achieve very high recognition rates exceeding 99%.

INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY, 2012

In this paper, we propose simple classifiers for printed Arabic characters based on statistical analysis. 109 printed Arabic character images are created for each one of transparent, simplified and traditional Arabic fonts. Images are preprocessed by the binarization and followed by sequence of morphological operations. A non-linear filter is applied on the thinned ridge map to extract termination and bifurcation features. The thinned ridge map vectors (TRMVs) are created using a freeman chain code template. The spatial distribution and statistical properties of the extracted features are calculated.

Handheld devices are looding the market, and their use is becoming essential among people. Hence, the need for fast and accurate character recognition methods that ease the data entry process for users arises. There are many methods developed for handwriting character recognition especially for Latin-based languages. On the other hand, character recognition methods for Arabic language are lacking and rare. The Arabic language has many traits that diferentiate it from other languages: irst, the writing process is from right to left; second, the leter changes shape according to the position in the work; and third, the writing is cursive. Such traits compel to produce a special character recognition method that helps in producing applications for Arabic language. This research proposes a deterministic algorithm that recognizes Arabic alphabet letters. The algorithm is based on four categorizations of Arabic alphabet leters. Then, the research suggested a deterministic algorithm composed of 34 rules that can predict the character based on the use of all of categorizations as atributes assembled in a matrix for this purpose.

International Journal of …, 2011

This paper proposes and contributes towards designing a complete system for off-line Arabic character recognition. The proposed system is specifically meant for Arabic handwriting recognition, but it equally works for the typed character recognition. It has various phases including preprocessing and segmentation. It also includes thinning phase and finds vertical and horizontal projection profiles. The recognition phase is managed by genetic algorithm. The genetic algorithm stands on feature extraction algorithm that defines six features for each segment. The algorithm, for Arabic handwriting recognition, obtained 90.46 recognition rate. The proposed system has been compared with other systems in the literature. It has achieved the second best recognition rate.

The issue of handwritten character recognition is still a big challenge to the scientific community. Several approaches to address this challenge have been attempted in the last years, mostly focusing on the English pre-printed or handwritten characters space. Thus, the need to attempt a research related to Arabic handwritten text recognition. Algorithms based on neural networks have proved to give better results than conventional methods when applied to problems where the decision rules of the classification problem are not clearly defined. Two neural networks were built to classify already segmented characters of handwritten Arabic text. The two neural networks correctly recognized 73% of the characters. However, one hurdle was encountered in the above scenario, which can be summarized as follows: there are a lot of handwritten characters that can be segmented and classified into two or more different classes depending on whether they are looked at separately, or in a word, or even in a sentence. In other words, character classification, especially handwritten Arabic characters, depends largely on contextual information, not only on topographic features extracted from these characters.

Recognizing Arabic handwritten words is a difficult problem due to the deformations of different writing styles. Moreover, the cursive nature of the Arabic writing makes correct segmentation of characters an almost impossible task. While there are many sub systems in an Arabic words recognition system, in this work we develop a sub system to recognize Part of Arabic Words (PAW). We try to solve this problem using three different approaches, implicit segmentation and two variants of holistic approach. While Rothacker found similar conclusions while this work is being prepared, we report the difficulty in locating characters in PAW using Scale Invariant Feature Transforms under the first approach. In the second and third approaches, we use holistic approach to recognize PAW using Support Vector Machine (SVM) and Active Shape Models (ASM). While there are few works that use SVM to recognize PAW, they use a small dataset; we use a large dataset and a different set of features. We also explain the errors SVM and ASM make and propose some remedies to these errors as future work.

International Journal of Machine Learning and Computing, 2012

On-line handwriting recognition is one of the most successful applications in the area of pattern recognition. Though this field is quite matured, yet the research issues are still challenging, particularly in handwriting character recognition, where the problems are still wide open. The OCR system for printed characters is almost done, though it cannot guarantee for 100% accuracy. However, the research works in recognition of Arabic handwriting are still at the beginning and require more attention. This paper presents the novel on-line Arabic handwriting character recognition. An efficient approach is introduced here to divide it into some particular component. A set of features are extracted from these components, and then encoded for the classification stage. The system classification is implemented by using two processes, i.e. weight initialization in back propagation, and with multilayer perceptron neural network. Finally, the proposed system was tested on a database of Arabic handwritten samples.

Pattern Recognition, 1990

Character recognition systems can contribute tremendously to the advancement of automation process, and can improve the interface between man and machine (computers) in many applications, including office automation and data entry. In this report we present a recognition system for typed Arabic text, which involves a statistical approach for character recognition. This approach uses "Accumulative Invariant Moments" as an identifier, which helped in the segmentation of connected and overlapping Arabic characters. However, Invariant Moments proved to be very sensitive to slight changes in a character shape. These changes are normally due to typing and the scanning process, and cannot be avoided. The recognition zone was defined based on the mean and standard deviation for the moments of a large sample of each character. However, this zone was increased, using an empirical multiplier, to improve recognition rate. The system was implemented on a mainframe in APL programming language for ease of experimentation, and then transported to a PC environment in BASIC for better portability. The recognition rate achieved was 94%, with a recognition speed of 10.6 characters/minute, running on a PC/AT with a math co-processor.

This paper presents a comparative study for Arabic optical character recognition techniques according to statistic approach. So, the current work consists in experimenting character image characterization and matching to show the most robust and reliable techniques. For features extraction phase, we test invariant moments, affine moment invariants, Tsirikolias-Mertzios moments, Zernike moments, Fourier-Mellin transform and Fourier descriptors. And for the classification phase, we use k-Nearest Neighbors and Support Vector Machine. Our data collection encloses 3 datasets. The first contains 2320 multi-font and multi-scale printed samples. The second contains 9280 multi-font, multi-scale and multi-oriented printed samples. And, the third contains 2900 handwritten samples which are extracted from the IFN/ENIT data. The aim was to cover a wide spectrum of Arabic characters complexity. The best performance rates found for each dataset are 99.91%, 99.26% and 66.68% respectively.