Muhammad Waqas Anwar

Challenges in Baseline Detection of Arabic Script Based Languages

In this chapter, we present baseline detection challenges for Arabic script based languages and targeted Nastaliq and Naskh writing style. Baseline is an important step in the OCR as it directly affects the rest of the steps and increases the performance and efficiency of character segmentation and feature extraction in OCR process. Character recognition on Arabic script is relatively more difficult than Latin text due to the nature of Arabic script, which is cursive, context sensitive and different writing style. In this paper, we provide a comprehensive review of baseline detection methods for Urdu language. The aim of the chapter is to introduce the challenges during baseline detection in cursive script languages for Nastaliq and Naskh script.

A multifaceted independent performance analysis of facial subspace recognition algorithms.

Face recognition has emerged as the fastest growing biometric technology and has expanded a lot in the last few years. Many new algorithms and commercial systems have been proposed and developed. Most of them use Principal Component Analysis (PCA) as a base for their techniques. Different and even conflicting results have been reported by researchers comparing these algorithms. The purpose of this study is to have an independent comparative analysis considering both performance and computational complexity of six appearance based face recognition algorithms namely PCA, 2DPCA, A2DPCA, (2D)2PCA, LPP and 2DLPP under equal working conditions. This study was motivated due to the lack of unbiased comprehensive comparative analysis of some recent subspace methods with diverse distance metric combinations. For comparison with other studies, FERET, ORL and YALE databases have been used with evaluation criteria as of FERET evaluations which closely simulate real life scenarios. A comparison of results with previous studies is performed and anomalies are reported. An important contribution of this study is that it presents the suitable performance conditions for each of the algorithms under consideration.

Modeling and analysis of departure routine in air traffic control based on Petri nets

Departure routine is essential part in the air traffic control and must be formally designed to avoid potential hazards and to verify proper functioning of the underlying processes. This paper addresses the Petri net approach to formally model the departure routine of the aircraft which ensures the organized flow of air traffic during departure. First, the high-level design of the system is presented by identifying key objects involved in departure routine, and then, its detailed model is presented. Moreover, the verification of the underlying methodology has been made using coverability tree. The proposed model is verified to be safe (bounded), potentially reversible and deadlock free which ensures reliability of the system and guarantees the efficient and controlled communication between the aircraft and local and ground controllers.

Feature-based watermarking using discrete orthogonal Hahn moment invariants

Many proposed image watermarking techniques are sensitive to geometric attacks, such as rotation, scaling, translation, or their composites. Even slight geometric distortions can also disable the watermark detector to reliably perform its function. In this paper, we utilize the robust invariant image features and discrete Hahn image moments to design a robust watermarking system that can withstand many geometric-distortions as well as survive a variety of common watermark attacks. Scale-invariant feature transform (SIFT) based bounding boxes and discrete orthogonal Hahn moment-invariants are used to embed watermark information into the selective image patches. Hahn moment-invariants are utilized for watermarking purpose because they are invariant to rotation, scaling, and translation. Watermark detection is performed by synchronizing the SIFT points and then computing the RMS threshold value between the original and the watermarked images. Several tests are performed to check the robustness of the proposed method. Experimental results validate the effectiveness of the scheme as well as prove that the proposed method is robust to several geometric attacks.

On the Security Properties and Attacks against Mobile Agent Graph Head Sealing (MAGHS)

Mobile Agents (MAs) are not fully adopted for implementing distributed system especially in e-commerce application. The main reason is the security issues associated with use of MAs. Providing integrity of execution is considered as the most challenging problem in MAs. Mobile agent Graph Head Sealing (MAGHS) is a technique that aims towards providing integrity of execution. This paper discusses the attacks that can be launched against MAGHS technique and how the security properties for MAs data integrity are fulfilled. We try to model the behavior of a malicious host by launching a series of passive attacks against mobile agent and then see to what extent the security properties for mobile agent can be achieved. The experimental results suggest that MAGHS framework can be used to protect the computations results of mobile agents.

Development of a disposable electrochemical sensor for detection of cholesterol using differential pulse voltammetry

Graphical abstract Figure. No caption available. HighlightsA non‐enzymatic cholesterol electrochemical was developed.Multi‐walled carbon nanotubes functioned as the signal‐enhancing platform.&bgr;‐cyclodextrin was used as recognition element.The electrochemical sensor exhibits good selectivity and limit of detection.Practical applications were demonstrated with human serum samples. ABSTRACT In this study, a sensitive and selective electrochemical sensor was fabricated by using a screen printed carbon electrode (SPCE), multi‐walled carbon nanotubes (MWCNTs) and &bgr;‐cyclodextrin (&bgr;‐CD) for detecting cholesterol. MWCNTs were functionalized with benzoic acid moiety by employing diazonium salt chemistry, and, subsequently, a thin film of functionalized CNTs were coated on the surface of SPCE. Afterwards, &bgr;‐CD was immobilized on functionalized MWCNTs modified SPCE which acts as a host to recognize guest (cholesterol) molecule specifically. Under the optimal experimental conditions and using differential pulse voltammetry (DPV) as transduction technique the sensor was able to detect cholesterol level ranges from 1 nM to 3 &mgr;M, with a detection limit of 0.5 nM. Specificity of the developed sensor towards target analyte (cholesterol) was confirmed in the presence of common interfering species including glucose, uric acid and ascorbic acid. The applicability of proposed sensor was also demonstrated for cholesterol determination in human serum samples with good recovery results (94–96%) and maximum RSD (relative standard deviation) of 4.5%.

Design of a portable luminescence bio-tool for on-site analysis of heavy metals in water samples

ABSTRACT In this work, we report an innovative tool for heavy metal screening in water samples. This new chemiluminescent set-up screens the light generated from luminol oxidation by horseradish peroxidase (HRP) in the presence of hydrogen peroxide (H2O2). The pollutant concentrations in real water samples were calculated by studying the effect of metal ions on chemiluminescence signal. Owing to its simplicity, portability and low cost, this approach presents a real alternative to classical optical methods. It is constructed with simple materials: a black box containing a cuvette and a micro-camera. When the enzymatic reaction takes place, the luminescence is captured by the camera placed in upright position. The image can be saved automatically in a computer for further analysis using a MATLAB interface. The RGB diagram is then established to determine the analyte concentrations in the tested samples. This method was successfully applied for the determination of mercury (Hg), lead (Pb) and cadmium (Cd) in lake and field water samples. In these experiments, three concentrations of each analytes were tested (5, 25 and 50 µg/L). We noted a good proportionality between the analyte concentration and the chemiluminescent detection intensity. Detection of binary and tertiary combinations of heavy metals has been also investigated. The developed biosensor showed low detection limits for the tested heavy metals: 1, 0.7 and 0.02 for Hg2+, Pb2+ and Cd2+, respectively. Finally, excellent recoveries ranging from 98% to 104% were obtained for the HRP-inhibition assay.

Printed Urdu Nastalique Script Recognition Using Analytical Approach

Urdu as a language, is gaining popularity because lot many people around the world e.g, India, Pakistan, Bangladesh, etc., speak and understand it. Like other languages e.g, Latin, Chinese, Japanese, Persian, Arabic, etc., Urdu is also under consideration of research community for developing Optical Character Recognition (OCR) Systems. Like Arabic, Urdu script comes with a number of fonts e.g, Nasakh, Nastalique, Noori, etc. The presented work uses analytical approach to recognize machine written Urdu Nastalique script. The methodology includes 3 major modules, (1) Preprocessing that uses binarization and filtering on the input image, (2) Main Process that includes sub phases Line Segmentation, Baseline Detection, Thinning, Segmentation, Smoothing, Dot Recognition from preprocessed image, and (3) Recognition that normalizes the processed image into a standard size of 50×32 and makes a row vector of 1600 using row-major order. Finally it uses Feed Forward Neural Network to recognize the processed input image as one of the 271 ligature classes. The neural network has 1600 neurons in input layer, 60 hidden neurons, and 271 output neurons. The methodology is evaluated on 10 images, 69 lines, and 1292 ligatures. The overall recognition rate is 87%.