Abdelmalek B. C. Zidouri

License plate recognition system

License Plate recognition (LPR) system is a key to many traffic related applications such as road traffic monitoring or parking lots access control. This paper proposes an automatic license plate recognition system for Saudi Arabian license plates. The system presents an algorithm for the extraction of license plate and segmentation of characters. Recognition is done using template matching. However the proposed work seems to be the first attempt towards the recognition of Saudi Arabian license plates. The performance of the system has been investigated on real images of about 710 vehicles captured under various illumination conditions. Recognition of about 96% shows that the system is quite efficient.

An approach to offline Arabic character recognition using neural networks

Character recognition system can contribute tremendously towards the advancement of automation process and can be useful in many other applications such as Data Entry, Check Verification etc. This paper presents a technique for the automatic recognition of Arabic Characters. The technique is based on Neural Pattern Recognition Approach. The main features of the system are preprocessing of the text, segmentation of the text to individual characters, Feature extraction using centralized moments technique and recognition using RBF Network. The system is implemented in Java Programming Language under Windows Environment. The System is designed for a single font multi size character set.

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.

A novel approach for skew estimation of document images in OCR system

Optical character recognition (OCR) is an area which has always received special attention. OCR systems are typically built on the strategy of divide and conquer, rather than recognizing documents at one go. They utilize several stages during the course of recognition. There have been many stages in a typical OCR system, preprocessing stage in considered to be indispensable. An input image or information need to be normalized and converted into format acceptable by OCR system. OCR systems typically assume that documents were printed with a single direction of the text and that the acquisition process did not introduce a relevant skew. Practically this assumption is not very strong and printed document could be skewed at some angle with horizontal axis. In this paper, we have proposed a new technique for skew estimation of image document. In the proposed scheme, multiscale properties of an image are utilized together with principal component analysis to estimate the orientation of principal axis of clustered data.

Handwriting synthesis: classifications and techniques

Handwriting synthesis is the automatic generation of data that resemble natural handwriting. Although handwriting synthesis has recently gained increasing interest, the area still lacks a stand-alone review. This paper provides classifications for the different aspects of handwriting synthesis. It presents the applications, techniques, and evaluation methods for handwriting synthesis based on the several aspects that we identify. Then, it discusses various synthesis techniques. To the best of our knowledge, this paper is the only stand-alone survey on this topic, and we believe it can serve as a useful reference for the researchers in the field of handwriting synthesis.

Adaptive dissection based subword segmentation of printed Arabic text

Numerous segmentation and recognition techniques have been proposed in literature for Arabic OCR system. Correct and efficient segmentation of Arabic text into characters is considered to be a fundamental problem. While OCR systems for other languages do not need segmentation for printed text for successful recognition, it is essential to design robust and powerful segmentation algorithms or employ segmentation free recognition schemes for printed Arabic text. Even more, in recognition of handwritten characters, segmentation is considered to be indispensable. Most of current segmentation technique suffers from over segmentation and under segmentation in addition to not being adaptive in nature. In this paper, we have proposed a new sub-word segmentation scheme, which is independent of font size and font type.

Performance analysis of a RLS-based MLP-DFE in time-invariant and time-varying channels

In this work, a recently derived recursive least-square (RLS) algorithm to train multi layer perceptron (MLP) is used in an MLP-based decision feedback equalizer (DFE) instead of the back propagation (BP) algorithm. Its performance is investigated and compared to those of MLP-DFE based on the BP algorithm and the simple DFE based on the least-mean square (LMS) algorithm. The results show improved performance obtained by the new structure in both time-invariant and time-varying channels. As will be detailed in this work, the newly proposed structure is a compromise between complexity and performance.

Analysis of the Sign Regressor Least Mean Fourth Adaptive Algorithm

A novel algorithm, called the signed regressor least mean fourth (SRLMF) adaptive algorithm, that reduces the computational cost and complexity while maintaining good performance is presented. Expressions are derived for the steady-state excess-mean-square error (EMSE) of the SRLMF algorithm in a stationary environment. A sufficient condition for the convergence in the mean of the SRLMF algorithm is derived. Also, expressions are obtained for the tracking EMSE of the SRLMF algorithm in a nonstationary environment, and consequently an optimum value of the step-size is obtained. Moreover, the weighted variance relation has been extended in order to derive expressions for the mean-square error (MSE) and the mean-square deviation (MSD) of the proposed algorithm during the transient phase. Computer simulations are carried out to corroborate the theoretical findings. It is shown that there is a good match between the theoretical and simulated results. It is also shown that the SRLMF algorithm has no performance degradation when compared with the least mean fourth (LMF) algorithm. The results in this study emphasize the usefulness of this algorithm in applications requiring reduced implementation costs for which the LMF algorithm is too complex.

Recognition of Arabic License Plates using NN

License plate recognition (LPR) systems are a key to many traffic related applications such as road traffic monitoring or parking lots access control. We propose an automatic license plate recognition system for GCC license plates. The system presents an algorithm for the extraction of license plate and recognition of Arabic characters and numerals. Preliminary work on the system has been investigated on real images of vehicles captured under various illumination conditions. Real time LPR plays a major role in automatic monitoring of traffic rules and maintaining law enforcement on public roads. The automatic identification of vehicles by the contents of their license plates is important in private transport applications.

PCA-based Arabic Character feature extraction

In this paper we propose two level recognition processes for Arabic characters. Arabic fonts are connected in nature and thus require segmentation for recognition. Document images are segmented into lines, words or subwords and then characters. In the proposed approach, recognition is applied at two levels with different strategies. First level recognition is applied after dasiawordspsila segmentation to recognize isolated characters while second level recognition is applied to segmented characters. The proposed scheme is tested on different font systems which yielded a recognition rate of about 90%.