Omar Fahmy - Academia.edu (original) (raw)

Papers by Omar Fahmy

2023 40th National Radio Science Conference (NRSC)

2018 35th National Radio Science Conference (NRSC), 2018

Magnifying micro movements of natural videos that are undetectable by human eye, has recently rec... more Magnifying micro movements of natural videos that are undetectable by human eye, has recently received considerable interests, due to its impact in numerous applications. In this paper, we use Dual Tree Complex Wavelet Transform DT-CWT, to analyze video in order to detect and magnify micro movements to make them visible. We use DT-CWT, due to its excellent edge preserving and nearly shift invariant features. We modify the phases of the CWT wavelet coefficients of successive video frames, in order to detect any minor change in object's spatial position. The paper starts by presenting a simple technique to design orthogonal filters that construct this CWT system. Next, it is shown how to modify the phase differences between the CWT coefficients of an arbitrary frame and a reference one, resulting in image spatial magnification. This in turn, makes these micro movements seen and observable. Several simulations are given, for several video sequences, to show that the proposed technique competes very well with the existing micro magnification approaches, as it manages to yield superior video quality in far less computation time.

2021 3rd Novel Intelligent and Leading Emerging Sciences Conference (NILES), 2021

Image denoising is of paramount importance in image processing. In this paper, we propose a new d... more Image denoising is of paramount importance in image processing. In this paper, we propose a new design technique for the design of Double density Discrete Wavelet Transform (DD DWT) AND DD CWT filter bank structure. These filter banks satisfy the perfect reconstruction as well as alias free properties of the DWT. Next, we utilized this filter bank structure in image denoising. Our denoising scheme is based on utilizing the interscale correlation/interscale dependence between wavelet coefficients of a DD DWT of the noisy image. This is known as the Bivariate Shrinkage scheme. More precisely, we update DD DWT of the noisy image at a certain scale, according to their correlations with the next coarser scale. The Maximum Likelihood Estimation are used for this update. Comparisons have been made with classical denoising schemes that threshold the DD DWT coefficient as well as denoising schemes employing Complex Wavelet Transform (CWT) filter banks. Illustrative examples are given to show the superiority of the proposed Bivariate DD DWT technique over current literature techniques.

International Journal of Information and Communication Sciences, 2021

Magnifying micro motion of videos that are undetectable by humans has recently been popular in ma... more Magnifying micro motion of videos that are undetectable by humans has recently been popular in many applications. This is due to its impact in numerous applications. In this paper, we explore this technique in 3D facial video identification, where we try to distinguish between real 3D facial objects in videos and 2D images of faces in a video frame sequence, and utilize this in biometric identification. We present a fast 2D Dual Discrete Wavelet Transform 2D-DWT based video magnification technique that detects micro movements by magnifying the phase differences between subsequent video frame's wavelet coefficients, at different sub bands. Next, in order to overcome shortcoming of 2D-DWT systems, 2D Dual Complex Wavelet Transform 2D-CWT has also been employed to estimate phase changes between subsequent video frames at different spatial locations of Complex Wavelets sub-bands. This latter presented CWT Technique uses the Radon Transform to detect any periodic motion in the video frames. Several simulation results are given to show that our proposed hybrid technique achieves comparable and sometimes superior performance with far less complexity when compared with recent literature in micro motion magnification, such as steerable pyramids STR and Riesz Transform RT based steerable pyramids RT-STR. Both DWT and CWT techniques are combined for 3D facial video identification. The attached videos demonstrate the superior video quality obtained by the proposed technique.

Expert Opinion on Drug Metabolism & Toxicology, 2010

Background: Central lymph node metastasis (CLNM) occurs frequently in patients with papillary thy... more Background: Central lymph node metastasis (CLNM) occurs frequently in patients with papillary thyroid cancer (PTC), but performing prophylactic central lymph node dissection is still controversial. There are no reliable models for predicting CLNM. This study aimed to develop predictive models for CLNM by machine learning (ML) algorithms. Methods: Patients with PTC who underwent initial thyroid resection at our hospital between January 2018 and December 2019 were enrolled. A total of 22 variables, including clinical characteristics and ultrasonography (US) features, were used for conventional univariate and multivariate analysis and to construct ML-based models. A 5-fold cross validation strategy was used for validation and a feature selection approach was applied to identify risk factors. Results: The areas under the receiver operating characteristic curve (AUC) of 7 models ranged from 0.680 to 0.731. All models performed significantly better than US (AUC=0.623) in predicting CLNM (P<0.05). In decision curve, most of the models also performed better than US. The gradient boosting decision tree model with 7 variables was identified as the best model because of its best performance in both ROC (AUC=0.731) and decision curves. Based on multivariate analysis and feature selection, young age, male sex, low serum thyroid peroxidase antibody and US features such as suspected lymph nodes, microcalcification and tumor size > 1.1 cm were the most contributing predictors for CLNM. Conclusions: It is feasible to develop predictive models of CLNM in PTC patients by incorporating clinical characteristics and US features. The ML algorithm may be a useful tool for the prediction of lymph node metastasis in thyroid cancer.

Sustainability

Predicting the heavy metals adsorption performance from contaminated water is a major environment... more Predicting the heavy metals adsorption performance from contaminated water is a major environment-associated topic, demanding information on different machine learning and artificial intelligence techniques. In this research, nano zero-valent aluminum (nZVAl) was tested to eliminate Cu(II) ions from aqueous solutions, modeling and predicting the Cu(II) removal efficiency (R%) using the adsorption factors. The prepared nZVAl was characterized for elemental composition and surface morphology and texture. It was depicted that, at an initial Cu(II) level (Co) 50 mg/L, nZVAl dose 1.0 g/L, pH 5, mixing speed 150 rpm, and 30 °C, the R% was 53.2 ± 2.4% within 10 min. The adsorption data were well defined by the Langmuir isotherm model (R2: 0.925) and pseudo-second-order (PSO) kinetic model (R2: 0.9957). The best modeling technique used to predict R% was artificial neural network (ANN), followed by support vector regression (SVR) and linear regression (LR). The high accuracy of ANN, with MSE...

2015 International Conference on Systems, Signals and Image Processing (IWSSIP), 2015

International conference on signal, systems and image processing (IWSSIP)-2015, January

Signal, Image and Video Processing, 2016

In multimedia forensics, it is important to identify those images that were captured by a specifi... more In multimedia forensics, it is important to identify those images that were captured by a specific camera from a given set of N data images as well as detecting the tampered region in these images if forged. This paper presents a new technique based on Zernike moments feature extraction for blindly classifying correlated PRNU images as well as locating the tampered regions in image under investigation. The proposed clustering algorithm is based on estimating the Zernike moments and applying a hierarchical clustering for classification. The forgery detection algorithm is based on picking up the peak Euclidean distance between the Zernike moments vector of blocks of the scaled-down forged image and its corresponding ones in the capturing camera PRNU. As Zernike moments are scale and rotational invariant, its feature when computed using scaled-down PRNU images lead to considerable computation time saving. Simulation examples are given to verify the effectiveness of the proposed techniques when compared to other state-of-the-art techniques even in case of very weakly correlated PRNU.

Biosensors

This paper presents the development of a new complete wearable system for detecting breast tumors... more This paper presents the development of a new complete wearable system for detecting breast tumors based on fully textile antenna-based sensors. The proposed sensor is compact and fully made of textiles so that it fits conformably and comfortably on the breasts with dimensions of 24 × 45 × 0.17 mm3 on a cotton substrate. The proposed antenna sensor is fed with a coplanar waveguide feed for easy integration with other systems. It realizes impedance bandwidth from 1.6 GHz up to 10 GHz at |S11| ≤ −6 dB (VSWR ≤ 3) and from 1.8 to 2.4 GHz and from 4 up to 10 GHz at |S11| ≤ −10 dB (VSWR ≤ 2). The proposed sensor acquires a low specific absorption rate (SAR) of 0.55 W/kg and 0.25 W/kg at 1g and 10 g, respectively, at 25 dBm power level over the operating band. Furthermore, the proposed system utilizes machine-learning algorithms (MLA) to differentiate between malignant tumor and benign breast tissues. Simulation examples have been recorded to verify and validate machine-learning algorithms ...

2019 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)

Magnifying micro movements of natural videos that are undetectable by human eye have recently rec... more Magnifying micro movements of natural videos that are undetectable by human eye have recently received considerable interests. This is due to its impact in numerous applications. In this paper, we present a new technique to estimate accurate phase changes between subsequent video frames at different spatial locations of Complex Wavelets CWT sub bands. This estimation is more accurate compared to recent literature techniques utilizing CWT in micro movement magnification. We also propose to speed up the magnification process through only amplifying small CWT local phase error intervals for each individual frame sub band. A simple block matching technique is also proposed to assess the quality of magnification and localize magnified regions. We applied our proposed technique on both Dual Tree Complex Wavelet Transform DT-CWT as well as Real two-dimensional Dual Tree DWT. Several simulations are given to show that the proposed technique competes very well with the existing micro magnification approaches such as steerable pyramids STR and Riesz Transform based steerable pyramids RT-STR. A detailed comparison of these techniques performance in micro movement magnification is illustrated. The attached video file demonstrates the superior video quality attained by the proposed technique.

2020 International Conference on Computing, Electronics & Communications Engineering (iCCECE), 2020

Magnifying micro changes in motion and brightness of videos that are unnoticeable by the human vi... more Magnifying micro changes in motion and brightness of videos that are unnoticeable by the human visual system have recently been an interesting area to explore. In this paper, we explore this technique in 3D facial video identification, we utilize this technique to identify 3D objects from 2D images. We present a Complex Wavelet Transform CWT, 2D-Dual CWT based technique, to calculate any changes between subsequent video frames of CWT sub-bands at different spatial locations. In this technique, a gradient based method is proposed to determine the orientation of each CWT sub band in addition to the Radon Transform, RT, that is utilized to detect any periodic motion in the video frames. We conducted many simulation results to show that the proposed hybrid technique provides promising results when compared with the existing literature in micro magnification of videos, like steerable pyramids STR or the Riesz Transform based one RT-STR. The proposed technique has been employed to make a ...

2015 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), 2015

International Symposium on signal processing and information technology (ISSPIT)

IET Image Processing, 2017

Magnifying micro-movements from natural video has recently been investigated by several computer ... more Magnifying micro-movements from natural video has recently been investigated by several computer vision researchers, due to its impact in numerous applications. In this study, the authors analyse video signals and try to magnify micro-movements/vibrations to make them visible. These micro-movements are typically undetectable and cannot be seen by basic human vision. They utilise complex wavelets to analyse sequential frames and detect any minor change in object's spatial position. They magnify some specific complex wavelet frequency bands by a multiplication factor and reconstruct back the video signal after some manipulation and modification to make these micro-movements seen and observable. They compare their work with recent techniques in micro-motion magnification (Freeman et al.) and try to show the merits of each technique. These micro-movements can later be utilised in different applications such as medical imaging, structural engineering, mechanical engineering, physical feature analysis and industrial engineering, as will be seen in their experiments.

IEEE International Symposium on Signal Processing and Information Technology, 2013

Exponential spline polynomials (E-splines) represent the best smooth transition between continuou... more Exponential spline polynomials (E-splines) represent the best smooth transition between continuous and discrete domains. As they are constructed from convolution of exponential segments, there are many degrees of freedom to optimally choose the most convenient E-spline, suitable for a specific application. In this paper, the parameters of these Esplines were optimally chosen, to enhance the performance of image de-noising as well as image zooming schemes. The proposed technique is based on minimizing the total variation function of the detail coefficients of the E-spline based wavelet decomposition. In image de-noising schemes, apart from Espline parameter estimations, the thresholding levels of their detail coefficients, are also optimally chosen. In zooming applications, the quality of interpolated images are further improved and sharpened by applying ICA technique to them, in order to remove any dependency. Illustrative examples are given to verify image enhancement of the proposed e-spline scheme, when compared with the existing approaches.

2021 3rd Novel Intelligent and Leading Emerging Sciences Conference (NILES), 2021

Interference management is one of the challenging tasks in Long-Term Evolution (LTE) technologies... more Interference management is one of the challenging tasks in Long-Term Evolution (LTE) technologies in Telecom Networks. One of these tasks is classifying interference problems affecting Uplink (UL) channel into different types. The interference classification problem can be formulated as an image classification task by converting the signal's power spectral density to an image. Convolutional Neural Networks (CNN) proved to have great success in image classification tasks. In this paper, different CNN architectures such as (VGG, MobileNet, RESNET) are used and assessed to classify the type of interference affecting the uplink channel in LTE. CNNs are characterized by their ability to detect and describe the abnormal behavior of UL channel which provided significant improvement over traditional rule-based systems. These rule-based systems rely on extracting domain driven features and classifying the interference using manually created rules by an expert. Our study shows that CNN yields 95% accuracy with training data. The end-to-end solution was deployed in Vodafone Group on Google Cloud Platform (GCP) to serve the different Local Markets.

2021 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT), 2021

The latest trend in multiple object tracking (MOT) is bending to utilize deep learning to improve... more The latest trend in multiple object tracking (MOT) is bending to utilize deep learning to improve tracking performance. With all advanced models such as R-CNN, YOLO, SSD, and RetinaNet, there will always be a time-accuracy trade-off which puts constraints to computer vision advancement. However, it is not trivial to solve those kinds of challenges using end-to-end deep learning models, adopting new strategies to enhance the aforementioned models are appreciated. In this paper we introduce a novel radon transformation based framework, which takes advantage of color space conversion and squeezes the MOT problem to signal domain using radon transformation. Afterwards, the inference of Minkowski distance between sequence of signals is used to estimate the objects' location. Adaptive Region of Interest (ROI) and thresholding criteria have been adopted to ensure the stability of the tracker. We experimentally demonstrated that the proposed method achieved a significant performance improvement in both The Multiple Object Tracking Accuracy (MOTA) and ID F1 (IDF1) with respect to previous state-of-the-art using two public benchmarks.

Journal of King Saud University - Engineering Sciences, 2020

This is a PDF file of an article that has undergone enhancements after acceptance, such as the ad... more This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

IEEE Access, 2022

Although the majority of existing License Plate (LP) recognition techniques have significant impr... more Although the majority of existing License Plate (LP) recognition techniques have significant improvements in accuracy, they are still limited to ideal situations in which training data is correctly annotated with restricted scenarios. Moreover, images or videos are frequently used in monitoring systems that have Low Resolution (LR) quality. In this work, the problem of LP detection in digital images is addressed in the images of a naturalistic environment. Single-stage character segmentation and recognition are combined with adversarial Super-Resolution (SR) approaches to improve the quality of the LP by processing the LR images into High-Resolution (HR) images. This work proposes effective changes to the SRGAN network regarding the number of layers, an activation function, and the appropriate loss regularization using Total Variation (TV) loss. The main paper contribution can be summarized into presenting an end-to-end deep learning framework based on generative adversarial networks (GAN), which is able to generate realistic super-resolution images. Also, proposed adding a TV regularization to the loss function to help the model enhance the resolution of images. The proposed SRGAN can handle tiny 72 × 72 images of LPs. The paper explores how SRGAN performed over different datasets from many aspects, such as visual analysis, PSNR, SSIM, and Optical Character Recognition (OCR). The experiments demonstrate that the suggested SRGAN can generate high-resolution images that improve the accuracy of the license plate recognition stage compared to other systems.

Biology of Blood and Marrow Transplantation, 2013

Signal, Image and Video Processing, 2009

In this paper we propose to develop novel techniques for signal/image decomposition, and reconstr... more In this paper we propose to develop novel techniques for signal/image decomposition, and reconstruction based on the B-spline mathematical functions. Our proposed B-spline based multiscale/resolution representation is based upon a perfect reconstruction analysis/synthesis point of view. Our proposed B-spline analysis can be utilized for different signal/imaging applications such as compression, prediction, and denoising. We also present a straightforward computationally efficient approach for B-spline basis calculations that is based upon matrix multiplication and avoids any extra generated basis. Then we propose a novel technique for enhanced B-spline based compression for different image coders by preprocessing the image prior to the decomposition stage in any image coder. This would reduce the amount of data correlation and would allow for more compression, as will be shown with our correlation metric. Extensive simulations that have been carried on the wellknown SPIHT image coder with and without the proposed correlation removal methodology are presented. Finally, we utilized our proposed B-spline basis for denoising and estimation applications. Illustrative results that demonstrate the efficiency of the proposed approaches are presented.

2023 40th National Radio Science Conference (NRSC)

2018 35th National Radio Science Conference (NRSC), 2018

Magnifying micro movements of natural videos that are undetectable by human eye, has recently rec... more Magnifying micro movements of natural videos that are undetectable by human eye, has recently received considerable interests, due to its impact in numerous applications. In this paper, we use Dual Tree Complex Wavelet Transform DT-CWT, to analyze video in order to detect and magnify micro movements to make them visible. We use DT-CWT, due to its excellent edge preserving and nearly shift invariant features. We modify the phases of the CWT wavelet coefficients of successive video frames, in order to detect any minor change in object's spatial position. The paper starts by presenting a simple technique to design orthogonal filters that construct this CWT system. Next, it is shown how to modify the phase differences between the CWT coefficients of an arbitrary frame and a reference one, resulting in image spatial magnification. This in turn, makes these micro movements seen and observable. Several simulations are given, for several video sequences, to show that the proposed technique competes very well with the existing micro magnification approaches, as it manages to yield superior video quality in far less computation time.

2021 3rd Novel Intelligent and Leading Emerging Sciences Conference (NILES), 2021

Image denoising is of paramount importance in image processing. In this paper, we propose a new d... more Image denoising is of paramount importance in image processing. In this paper, we propose a new design technique for the design of Double density Discrete Wavelet Transform (DD DWT) AND DD CWT filter bank structure. These filter banks satisfy the perfect reconstruction as well as alias free properties of the DWT. Next, we utilized this filter bank structure in image denoising. Our denoising scheme is based on utilizing the interscale correlation/interscale dependence between wavelet coefficients of a DD DWT of the noisy image. This is known as the Bivariate Shrinkage scheme. More precisely, we update DD DWT of the noisy image at a certain scale, according to their correlations with the next coarser scale. The Maximum Likelihood Estimation are used for this update. Comparisons have been made with classical denoising schemes that threshold the DD DWT coefficient as well as denoising schemes employing Complex Wavelet Transform (CWT) filter banks. Illustrative examples are given to show the superiority of the proposed Bivariate DD DWT technique over current literature techniques.

International Journal of Information and Communication Sciences, 2021

Magnifying micro motion of videos that are undetectable by humans has recently been popular in ma... more Magnifying micro motion of videos that are undetectable by humans has recently been popular in many applications. This is due to its impact in numerous applications. In this paper, we explore this technique in 3D facial video identification, where we try to distinguish between real 3D facial objects in videos and 2D images of faces in a video frame sequence, and utilize this in biometric identification. We present a fast 2D Dual Discrete Wavelet Transform 2D-DWT based video magnification technique that detects micro movements by magnifying the phase differences between subsequent video frame's wavelet coefficients, at different sub bands. Next, in order to overcome shortcoming of 2D-DWT systems, 2D Dual Complex Wavelet Transform 2D-CWT has also been employed to estimate phase changes between subsequent video frames at different spatial locations of Complex Wavelets sub-bands. This latter presented CWT Technique uses the Radon Transform to detect any periodic motion in the video frames. Several simulation results are given to show that our proposed hybrid technique achieves comparable and sometimes superior performance with far less complexity when compared with recent literature in micro motion magnification, such as steerable pyramids STR and Riesz Transform RT based steerable pyramids RT-STR. Both DWT and CWT techniques are combined for 3D facial video identification. The attached videos demonstrate the superior video quality obtained by the proposed technique.

Expert Opinion on Drug Metabolism & Toxicology, 2010

Background: Central lymph node metastasis (CLNM) occurs frequently in patients with papillary thy... more Background: Central lymph node metastasis (CLNM) occurs frequently in patients with papillary thyroid cancer (PTC), but performing prophylactic central lymph node dissection is still controversial. There are no reliable models for predicting CLNM. This study aimed to develop predictive models for CLNM by machine learning (ML) algorithms. Methods: Patients with PTC who underwent initial thyroid resection at our hospital between January 2018 and December 2019 were enrolled. A total of 22 variables, including clinical characteristics and ultrasonography (US) features, were used for conventional univariate and multivariate analysis and to construct ML-based models. A 5-fold cross validation strategy was used for validation and a feature selection approach was applied to identify risk factors. Results: The areas under the receiver operating characteristic curve (AUC) of 7 models ranged from 0.680 to 0.731. All models performed significantly better than US (AUC=0.623) in predicting CLNM (P<0.05). In decision curve, most of the models also performed better than US. The gradient boosting decision tree model with 7 variables was identified as the best model because of its best performance in both ROC (AUC=0.731) and decision curves. Based on multivariate analysis and feature selection, young age, male sex, low serum thyroid peroxidase antibody and US features such as suspected lymph nodes, microcalcification and tumor size > 1.1 cm were the most contributing predictors for CLNM. Conclusions: It is feasible to develop predictive models of CLNM in PTC patients by incorporating clinical characteristics and US features. The ML algorithm may be a useful tool for the prediction of lymph node metastasis in thyroid cancer.

Sustainability

Predicting the heavy metals adsorption performance from contaminated water is a major environment... more Predicting the heavy metals adsorption performance from contaminated water is a major environment-associated topic, demanding information on different machine learning and artificial intelligence techniques. In this research, nano zero-valent aluminum (nZVAl) was tested to eliminate Cu(II) ions from aqueous solutions, modeling and predicting the Cu(II) removal efficiency (R%) using the adsorption factors. The prepared nZVAl was characterized for elemental composition and surface morphology and texture. It was depicted that, at an initial Cu(II) level (Co) 50 mg/L, nZVAl dose 1.0 g/L, pH 5, mixing speed 150 rpm, and 30 °C, the R% was 53.2 ± 2.4% within 10 min. The adsorption data were well defined by the Langmuir isotherm model (R2: 0.925) and pseudo-second-order (PSO) kinetic model (R2: 0.9957). The best modeling technique used to predict R% was artificial neural network (ANN), followed by support vector regression (SVR) and linear regression (LR). The high accuracy of ANN, with MSE...

2015 International Conference on Systems, Signals and Image Processing (IWSSIP), 2015

International conference on signal, systems and image processing (IWSSIP)-2015, January

Signal, Image and Video Processing, 2016

In multimedia forensics, it is important to identify those images that were captured by a specifi... more In multimedia forensics, it is important to identify those images that were captured by a specific camera from a given set of N data images as well as detecting the tampered region in these images if forged. This paper presents a new technique based on Zernike moments feature extraction for blindly classifying correlated PRNU images as well as locating the tampered regions in image under investigation. The proposed clustering algorithm is based on estimating the Zernike moments and applying a hierarchical clustering for classification. The forgery detection algorithm is based on picking up the peak Euclidean distance between the Zernike moments vector of blocks of the scaled-down forged image and its corresponding ones in the capturing camera PRNU. As Zernike moments are scale and rotational invariant, its feature when computed using scaled-down PRNU images lead to considerable computation time saving. Simulation examples are given to verify the effectiveness of the proposed techniques when compared to other state-of-the-art techniques even in case of very weakly correlated PRNU.

Biosensors

This paper presents the development of a new complete wearable system for detecting breast tumors... more This paper presents the development of a new complete wearable system for detecting breast tumors based on fully textile antenna-based sensors. The proposed sensor is compact and fully made of textiles so that it fits conformably and comfortably on the breasts with dimensions of 24 × 45 × 0.17 mm3 on a cotton substrate. The proposed antenna sensor is fed with a coplanar waveguide feed for easy integration with other systems. It realizes impedance bandwidth from 1.6 GHz up to 10 GHz at |S11| ≤ −6 dB (VSWR ≤ 3) and from 1.8 to 2.4 GHz and from 4 up to 10 GHz at |S11| ≤ −10 dB (VSWR ≤ 2). The proposed sensor acquires a low specific absorption rate (SAR) of 0.55 W/kg and 0.25 W/kg at 1g and 10 g, respectively, at 25 dBm power level over the operating band. Furthermore, the proposed system utilizes machine-learning algorithms (MLA) to differentiate between malignant tumor and benign breast tissues. Simulation examples have been recorded to verify and validate machine-learning algorithms ...

2019 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)

Magnifying micro movements of natural videos that are undetectable by human eye have recently rec... more Magnifying micro movements of natural videos that are undetectable by human eye have recently received considerable interests. This is due to its impact in numerous applications. In this paper, we present a new technique to estimate accurate phase changes between subsequent video frames at different spatial locations of Complex Wavelets CWT sub bands. This estimation is more accurate compared to recent literature techniques utilizing CWT in micro movement magnification. We also propose to speed up the magnification process through only amplifying small CWT local phase error intervals for each individual frame sub band. A simple block matching technique is also proposed to assess the quality of magnification and localize magnified regions. We applied our proposed technique on both Dual Tree Complex Wavelet Transform DT-CWT as well as Real two-dimensional Dual Tree DWT. Several simulations are given to show that the proposed technique competes very well with the existing micro magnification approaches such as steerable pyramids STR and Riesz Transform based steerable pyramids RT-STR. A detailed comparison of these techniques performance in micro movement magnification is illustrated. The attached video file demonstrates the superior video quality attained by the proposed technique.

2020 International Conference on Computing, Electronics & Communications Engineering (iCCECE), 2020

Magnifying micro changes in motion and brightness of videos that are unnoticeable by the human vi... more Magnifying micro changes in motion and brightness of videos that are unnoticeable by the human visual system have recently been an interesting area to explore. In this paper, we explore this technique in 3D facial video identification, we utilize this technique to identify 3D objects from 2D images. We present a Complex Wavelet Transform CWT, 2D-Dual CWT based technique, to calculate any changes between subsequent video frames of CWT sub-bands at different spatial locations. In this technique, a gradient based method is proposed to determine the orientation of each CWT sub band in addition to the Radon Transform, RT, that is utilized to detect any periodic motion in the video frames. We conducted many simulation results to show that the proposed hybrid technique provides promising results when compared with the existing literature in micro magnification of videos, like steerable pyramids STR or the Riesz Transform based one RT-STR. The proposed technique has been employed to make a ...

2015 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), 2015

International Symposium on signal processing and information technology (ISSPIT)

IET Image Processing, 2017

Magnifying micro-movements from natural video has recently been investigated by several computer ... more Magnifying micro-movements from natural video has recently been investigated by several computer vision researchers, due to its impact in numerous applications. In this study, the authors analyse video signals and try to magnify micro-movements/vibrations to make them visible. These micro-movements are typically undetectable and cannot be seen by basic human vision. They utilise complex wavelets to analyse sequential frames and detect any minor change in object's spatial position. They magnify some specific complex wavelet frequency bands by a multiplication factor and reconstruct back the video signal after some manipulation and modification to make these micro-movements seen and observable. They compare their work with recent techniques in micro-motion magnification (Freeman et al.) and try to show the merits of each technique. These micro-movements can later be utilised in different applications such as medical imaging, structural engineering, mechanical engineering, physical feature analysis and industrial engineering, as will be seen in their experiments.

IEEE International Symposium on Signal Processing and Information Technology, 2013

Exponential spline polynomials (E-splines) represent the best smooth transition between continuou... more Exponential spline polynomials (E-splines) represent the best smooth transition between continuous and discrete domains. As they are constructed from convolution of exponential segments, there are many degrees of freedom to optimally choose the most convenient E-spline, suitable for a specific application. In this paper, the parameters of these Esplines were optimally chosen, to enhance the performance of image de-noising as well as image zooming schemes. The proposed technique is based on minimizing the total variation function of the detail coefficients of the E-spline based wavelet decomposition. In image de-noising schemes, apart from Espline parameter estimations, the thresholding levels of their detail coefficients, are also optimally chosen. In zooming applications, the quality of interpolated images are further improved and sharpened by applying ICA technique to them, in order to remove any dependency. Illustrative examples are given to verify image enhancement of the proposed e-spline scheme, when compared with the existing approaches.

2021 3rd Novel Intelligent and Leading Emerging Sciences Conference (NILES), 2021

Interference management is one of the challenging tasks in Long-Term Evolution (LTE) technologies... more Interference management is one of the challenging tasks in Long-Term Evolution (LTE) technologies in Telecom Networks. One of these tasks is classifying interference problems affecting Uplink (UL) channel into different types. The interference classification problem can be formulated as an image classification task by converting the signal's power spectral density to an image. Convolutional Neural Networks (CNN) proved to have great success in image classification tasks. In this paper, different CNN architectures such as (VGG, MobileNet, RESNET) are used and assessed to classify the type of interference affecting the uplink channel in LTE. CNNs are characterized by their ability to detect and describe the abnormal behavior of UL channel which provided significant improvement over traditional rule-based systems. These rule-based systems rely on extracting domain driven features and classifying the interference using manually created rules by an expert. Our study shows that CNN yields 95% accuracy with training data. The end-to-end solution was deployed in Vodafone Group on Google Cloud Platform (GCP) to serve the different Local Markets.

2021 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT), 2021

The latest trend in multiple object tracking (MOT) is bending to utilize deep learning to improve... more The latest trend in multiple object tracking (MOT) is bending to utilize deep learning to improve tracking performance. With all advanced models such as R-CNN, YOLO, SSD, and RetinaNet, there will always be a time-accuracy trade-off which puts constraints to computer vision advancement. However, it is not trivial to solve those kinds of challenges using end-to-end deep learning models, adopting new strategies to enhance the aforementioned models are appreciated. In this paper we introduce a novel radon transformation based framework, which takes advantage of color space conversion and squeezes the MOT problem to signal domain using radon transformation. Afterwards, the inference of Minkowski distance between sequence of signals is used to estimate the objects' location. Adaptive Region of Interest (ROI) and thresholding criteria have been adopted to ensure the stability of the tracker. We experimentally demonstrated that the proposed method achieved a significant performance improvement in both The Multiple Object Tracking Accuracy (MOTA) and ID F1 (IDF1) with respect to previous state-of-the-art using two public benchmarks.

Journal of King Saud University - Engineering Sciences, 2020

This is a PDF file of an article that has undergone enhancements after acceptance, such as the ad... more This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

IEEE Access, 2022

Although the majority of existing License Plate (LP) recognition techniques have significant impr... more Although the majority of existing License Plate (LP) recognition techniques have significant improvements in accuracy, they are still limited to ideal situations in which training data is correctly annotated with restricted scenarios. Moreover, images or videos are frequently used in monitoring systems that have Low Resolution (LR) quality. In this work, the problem of LP detection in digital images is addressed in the images of a naturalistic environment. Single-stage character segmentation and recognition are combined with adversarial Super-Resolution (SR) approaches to improve the quality of the LP by processing the LR images into High-Resolution (HR) images. This work proposes effective changes to the SRGAN network regarding the number of layers, an activation function, and the appropriate loss regularization using Total Variation (TV) loss. The main paper contribution can be summarized into presenting an end-to-end deep learning framework based on generative adversarial networks (GAN), which is able to generate realistic super-resolution images. Also, proposed adding a TV regularization to the loss function to help the model enhance the resolution of images. The proposed SRGAN can handle tiny 72 × 72 images of LPs. The paper explores how SRGAN performed over different datasets from many aspects, such as visual analysis, PSNR, SSIM, and Optical Character Recognition (OCR). The experiments demonstrate that the suggested SRGAN can generate high-resolution images that improve the accuracy of the license plate recognition stage compared to other systems.

Biology of Blood and Marrow Transplantation, 2013

Signal, Image and Video Processing, 2009

In this paper we propose to develop novel techniques for signal/image decomposition, and reconstr... more In this paper we propose to develop novel techniques for signal/image decomposition, and reconstruction based on the B-spline mathematical functions. Our proposed B-spline based multiscale/resolution representation is based upon a perfect reconstruction analysis/synthesis point of view. Our proposed B-spline analysis can be utilized for different signal/imaging applications such as compression, prediction, and denoising. We also present a straightforward computationally efficient approach for B-spline basis calculations that is based upon matrix multiplication and avoids any extra generated basis. Then we propose a novel technique for enhanced B-spline based compression for different image coders by preprocessing the image prior to the decomposition stage in any image coder. This would reduce the amount of data correlation and would allow for more compression, as will be shown with our correlation metric. Extensive simulations that have been carried on the wellknown SPIHT image coder with and without the proposed correlation removal methodology are presented. Finally, we utilized our proposed B-spline basis for denoising and estimation applications. Illustrative results that demonstrate the efficiency of the proposed approaches are presented.