Refaey, M. A. A., "Moment Invariants-Based Face Recognition", International Journal of Scientific & Engineering Research (IJSER), vol. 7, issue 11, 2016.
Refaey, M. A. A., "Finger Print Extraction Using a Local Varying Thresholding on Mobile Devices", The Second International Conference on Electronics and Software Science (ICESS2016), Japan, pp. 65-70, 2016. Abstract

Technology producers are in a race to present the high-end products on mobile devices, and so the services presenters, the matter that needs authentication in many of the services. One of the most used authentication ways is the finger print. In this work we introduce a novel method to extract the finger print from an image taken by a mobile device’s camera. The area of interest is converted to a grey-level image, and then the algorithm uses a local varying threshold to extract the finger print details, where is traced row by row, and column by column making a lowpass filtering, and then determine a threshold dynamically according to the ridges and valleys’ intensity values which can vary due to many reasons like illumination changes. The results compared with the ink-and-paper method shows that the introduced method is a promising software-based solution for extracting the finger print using mobile devices.

Refaey, M. A. A., "Automatic Generation of Membership Functions and Rules in a Fuzzy Logic System", Fifth International Conference on Informatics and Applications, Japan, pp. 117-122, 2016. Abstract

Fuzzy logic is playing a significant role in many control and classification systems. This arises from its simplicity, natural language based construction, dealing with ambiguity, and its ability to model linear and non-linear complex systems. But, with larger number of input and output variables, the building process of fuzzy system manually becomes daunting and error-prone process. In this work we suggest new methods for automatically creation and generation of fuzzy membership functions and fuzzy rule base respectively. The membership functions are created adaptively from the training data set using histogram of each feature individually. And in the beginning, a rule is generated for each membership function, then according to the weight assigned to each rule and membership function, the membership functions are merged according to successiveness of their domain or support. Also, the rules are started to be co-operated and merged to enhance the classification process. The resulted system is flexible, and is able to receive more rules and/or membership functions if needed.

Kotb, M. A., H. N. Elmahdy, F. E. Z. Mostafa, M. E. Falaki, C. W. Shaker, M. A. Refaey, and K. Rjoob, "Improving the Recognition of Heart Murmur", International Journal of Advanced Computer Science and Applications (IJACSA), vol. 7, no. 7, pp. 283-287, 2016. Abstract

Diagnosis of congenital cardiac defects is challenging, with some being diagnosed during pregnancy while others are diagnosed after birth or later on during childhood. Prompt diagnosis allows early intervention and best prognosis. Contemporary diagnosis relies upon the history, clinical examination, pulse oximetery, chest X-ray, electrocardiogram (ECG), echocardiography (ECHO), computed tomography (CT) and cardiac catheterization. These diagnostic modalities reliable upon recording electrical activity or sound waves or upon radiation. Yet, congenital heart diseases are still liable to misdiagnosis because of level of operator expertise and other multiple factors. In an attempt to minimize effect of operator expertise this paper built a classification model for heart murmur recognition using Hidden Markov Model (HMM). This paper used Mel Frequency Cepestral coefficient (MFCC) as a feature and 13 MFCC coefficients. The machine learning model built by studying 1069 different heart sounds covering normal heart sounds, ventricular septal defect (VSD), mitral regurgitation (MR), aortic stenosis (AS), aortic regurgitation (AR), patent ductus arteriosus (PDA), pulmonary regurgitation (PR), and pulmonary stenosis (PS). MFCC feature used to extract feature matrix for each type of heart sounds after separation according to amplitude threshold. The frequency of normal heart sound (range= 1Hz to 139Hz) was specific without overlap with any of the studied defects (ranged= 156-556Hz). The frequency ranges for each of these defects was typical without overlap according to examined heart area (aortic, pulmonary, tricuspid and mitral area). The overall correct classification rate (CCR) using this model was 96% and sensitivity 98%. This model has great potential for prompt screening and specific defect detection. Effect of cardiac contractility, cardiomegaly or cardiac electrical activity on this novel detection system needs to be verified in future works.

Abdel-Hadi, M. E. A., R. A. El-Khoribi, M. I. Shoman, and M. M. Refaey, "Classification of motor imagery tasks with LS-SVM in EEG-based self-paced BCI", 2015 Fifth International Conference on Digital Information Processing and Communications (ICDIPC), pp. 244-249, Oct, 2015. Abstract

Motivated by the need to deal with critical disorders that involve death of neurons, such as Amyotrophic Lateral Sclerosis (ALS) and brainstem stroke, interpretation of the brain’s Motor Imagery (MI) activities is highly needed. Brain signals can be translated into control commands. Electroencephalography (EEG) is considered in this work, EEG is a low-cost non-invasive technique. A big challenge is faced due to the poor signal-to-noise ratio of EEG signals. The dataset used in this work is based on asynchronous or self-paced motor imagery problem. The used self-paced Brain Computer Interface (BCI) problem poses a considerable challenge by introducing an additional class, a relax class, or non-intentional control periods that are not included in the training set and should be classified. In this work, a number of subject dependent parameters and their values are determined. These parameters are: the best frequency range, the best Common Spatial Pattern (CSP) channels, and the number of these CSP channels. System parameters are determined dynamically in the offline training phase. Energy based features are extracted afterwards from the best selected signals. The Least-Squares Support Vector Machine (LS-SVM) classifier is used as a classification back end. Results of the proposed system show superiority over the previously introduced systems in terms of the Mean Square Error (MSE) when tested on the Berlin BCI (BBCI) competition IV dataset 1.

Refaey, M. A. A., "Ruled lines detection and removal in grey level handwritten image documents", Information and Communication Systems (ICICS), 2015 6th International Conference on, pp. 218-221, April, 2015. Abstract


Refaey, M. A. A., "Background Ruled-Lines Detection and Removal in Full-Colored Handwritten Image Documents", International Journal of Image and Graphics, vol. 15, no. 02, pp. 1540006, 2015. AbstractWebsite


Refaey, M. A. A., "Fast Detection and Removal Algorithms for Ruled Lines in Full-Color Scanned Handwritten Documents", International Conference on Computer Science, Computer Engineering, and Social Media (ICCSCESM2016), pp. 77-80, 2014. Abstract

Converting handwritten documents into its machine written counterpart automatically requires several processes including removing background noise and ruled lines, then Optical Character Recognition. In this paper, we present a fast detection and removal algorithms for ruled lines in colored scanned handwritten documents. The ruled lines detection is based on Hough transform of the centralized 1/9th image rectangle. Once the ruled lines are detected, the removal process or text isolation has been developed based on the hue histogram segmentation in full-color image documents. The early results show a very promising effectiveness and reliability of the proposed method.

Refaey, M. A., K. M. Elsayed, S. M. Hanafy, and L. S. Davis, "Concurrent transition and shot detection in football videos using Fuzzy Logic", Image Processing (ICIP), 2009 16th IEEE International Conference on, pp. 4341-4344, Nov, 2009. Abstract


Refaey, M. A., W. Abd-Almageed, and L. S. Davis, "A Logic Framework for Sports Video Summarization Using Text-Based Semantic Annotation", Semantic Media Adaptation and Personalization, 2008. SMAP ’08. Third International Workshop on, pp. 69-75, Dec, 2008. Abstract