KHATT: An open Arabic offline handwritten text database

A comprehensive Arabic handwritten text database is an essential resource for Arabic handwritten text recognition research. This is especially true due to the lack of such database for Arabic handwritten text. In this paper, we report our comprehensive Arabic offline Handwritten Text database (KHATT) consisting of 1000 handwritten forms written by 1000 distinct writers from different countries. The forms were scanned at 200, 300, and 600 dpi resolutions. The database contains 2000 randomly selected paragraphs from 46 sources, 2000 minimal text paragraph covering all the shapes of Arabic characters, and optionally written paragraphs on open subjects. The 2000 random text paragraphs consist of 9327 lines. The database forms were randomly divided into 70%, 15%, and 15% sets for training, testing, and verification, respectively. This enables researchers to use the database and compare their results. A formal verification procedure is implemented to align the handwritten text with its ground truth at the form, paragraph and line levels. The verified ground truth database contains meta-data describing the written text at the page, paragraph, and line levels in text and XML formats. Tools to extract paragraphs from pages and segment paragraphs into lines are developed. In addition we are presenting our experimental results on the database using two classifiers, viz. Hidden Markov Models (HMM) and our novel syntactic classifier.     

Recognition of Arabic (Indian) bank check digits using log-gabor filters

In this paper we present a technique for the automatic recognition of Arabic (Indian) bank check digits based on features extracted by using the Log Gabor filters. The digits are classified by using the K-Nearest Neighbor (K-NN), Hidden Markov Models (HMM) and Support Vector Machines (SVM) classifiers. An extensive experimentation is conducted on the CENPARMI data, a database consisting of 7390 samples of Arabic (Indian) digits for training and 3035 samples for testing extracted from real bank checks. The data is normalized to a height of 64 pixels, maintaining the aspect ratio. Log Gabor filters with several scales and orientations are used. In addition, the filtered images are segmented into different region sizes for feature extraction. Recognition rates of 98.95%, 98.75%, 98.62%, 97.21% and 94.43% are achieved with SVM, 1-NN, 3-NN, HMM and NM classifiers, respectively. These results significantly outperform published work using the same database. The misclassified digits are evaluated subjectively and results indicate that human subjects misclassified 1/3 of these digits. The experimental results, including the subjective evaluation of misclassified digits, indicate the effectiveness of the selected Log Gabor filters parameters, the implemented image segmentation technique, and extracted features for practical recognition of Arabic (Indian) digits.     

Energy-efficient and delay-aware mobile cloud offloading over cellular networks

Telecommunication Systems - The latest mobile applications, such as GPS, games, virus scanning, and face detection and recognition, are compute-intensive applications consuming a lot of energy when...     

Machine-learning based classification of speech and music

The need to classify audio into categories such as speech or music is an important aspect of many multimedia document retrieval systems. In this paper, we investigate audio features that have not been previously used in music-speech classification, such as the mean and variance of the discrete wavelet transform, the variance of Mel-frequency cepstral coefficients, the root mean square of a lowpass signal, and the difference of the maximum and minimum zero-crossings. We, then, employ fuzzy C-means clustering to the problem of selecting a viable set of features that enables better classification accuracy. Three different classification frameworks have been studied:Multi-Layer Perceptron (MLP) Neural Networks, radial basis functions (RBF) Neural Networks, and Hidden Markov Model (HMM), and results of each framework have been reported and compared. Our extensive experimentation have identified a subset of features that contributes most to accurate classification, and have shown that MLP networks are the most suitable classification framework for the problem at hand.     

Free vibration of a paraboloidal shell of revolution including shear deformation and rotary inertia

The governing strain-displacement and curvature-displacement equations for paraboloidal shells including shear deformation and rotary inertia are solved for free vibration of closed shells. The finite element method is used to obtain three-dimensional frequency of vibration solutions for a variety of boundary conditions, free, fixed and simply supported. Assumptions concerning the circumferential vibrational behavior are incorporated that reduce the analysis to a single coordinate and the element shape function is formulated using the meridional coordinate. The results for frequency of vibration compare favorably with the available literature. Selected results for frequency of vibration are presented in tabular form for several shell parameters, including free, pinned and fixed boundary conditions. Representative mode shapes are plotted for a fixed boundary condition.     

Adaptive collision-resolution algorithm and traffic-scheduling mechanism for DOCSIS-based HFC networks

A scheme is proposed that provides high QoS and collision-free data transmission in hybrid fiber-coax (HFC) networks. This scheme ensures effective medium access and creates an effective traffic-scheduling mechanism. To enhance the performance of the proposed scheme, a novel methodology has been adopted. Experiments have been performed to measure the effectiveness of the priority system that use the mean access delay, throughput, and channel utilization as figures of merit. Published in Russian in Radiotekhnika i Elektronika, 2007, Vol. 52, No. 3, pp. 469–479. The text was submitted by the authors in English.     

Improved Software Implementation for Montgomery Elliptic Curve Cryptosystem

The last decade witnessed rapid increase in multimedia and other applications that require transmitting and protecting huge amount of data streams simultaneously. For such applications, a high-performance cryptosystem is compulsory to provide necessary security services. Elliptic curve cryptosystem (ECC) has been introduced as a considerable option. However, the usual sequential implementation of ECC and the standard elliptic curve (EC) form cannot achieve required performance level. Moreover, the widely used Hardware implementation of ECC is costly option and may be not affordable. This research aims to develop a high-performance parallel software implementation for ECC. To achieve this, many experiments were performed to examine several factors affecting ECC performance including the projective coordinates, the scalar multiplication algorithm, the elliptic curve (EC) form, and the parallel implementation. The ECC performance was analyzed using the different factors to tune-up them and select the best choices to increase the speed of the cryptosystem. Experimental results illustrated that parallel Montgomery ECC implementation using homogenous projection achieves the highest performance level, since it scored the shortest time delay for ECC computations. In addition, results showed that NAF algorithm consumes less time to perform encryption and scalar multiplication operations in comparison with Montgomery ladder and binary methods. Java multi-threading technique was adopted to implement ECC computations in parallel. The proposed multithreaded Montgomery ECC implementation significantly improves the performance level compared to previously presented parallel and sequential implementations.