Mostafa E . A . Ibrahim | Benha University (original) (raw)

Papers by Mostafa E . A . Ibrahim

Research paper thumbnail of Biometric-Based Human Identification Using Ensemble-Based Technique and ECG Signals

Applied Sciences

User authentication has become necessary in different life domains. Traditional authentication me... more User authentication has become necessary in different life domains. Traditional authentication methods like personal information numbers (PINs), password ID cards, and tokens are vulnerable to attacks. For secure authentication, methods like biometrics have been developed in the past. Biometric information is hard to lose, forget, duplicate, or share because it is a part of the human body. Many authentication methods focused on electrocardiogram (ECG) signals have achieved great success. In this paper, we have developed cardiac biometrics for human identification using a deep learning (DL) approach. Cardiac biometric systems rely on cardiac signals that are captured using the electrocardiogram (ECG), photoplethysmogram (PPG), and phonocardiogram (PCG). This study utilizes the ECG as a biometric modality because ECG signals are a superior choice for accurate, secure, and reliable biometric-based human identification systems, setting them apart from PPG and PCG approaches. To get bett...

Research paper thumbnail of Assist-Dermo: A Lightweight Separable Vision Transformer Model for Multiclass Skin Lesion Classification

Diagnostics

A dermatologist-like automatic classification system is developed in this paper to recognize nine... more A dermatologist-like automatic classification system is developed in this paper to recognize nine different classes of pigmented skin lesions (PSLs), using a separable vision transformer (SVT) technique to assist clinical experts in early skin cancer detection. In the past, researchers have developed a few systems to recognize nine classes of PSLs. However, they often require enormous computations to achieve high performance, which is burdensome to deploy on resource-constrained devices. In this paper, a new approach to designing SVT architecture is developed based on SqueezeNet and depthwise separable CNN models. The primary goal is to find a deep learning architecture with few parameters that has comparable accuracy to state-of-the-art (SOTA) architectures. This paper modifies the SqueezeNet design for improved runtime performance by utilizing depthwise separable convolutions rather than simple conventional units. To develop this Assist-Dermo system, a data augmentation technique ...

Research paper thumbnail of Light-Dermo: A Lightweight Pretrained Convolution Neural Network for the Diagnosis of Multiclass Skin Lesions

Diagnostics

Skin cancer develops due to the unusual growth of skin cells. Early detection is critical for the... more Skin cancer develops due to the unusual growth of skin cells. Early detection is critical for the recognition of multiclass pigmented skin lesions (PSLs). At an early stage, the manual work by ophthalmologists takes time to recognize the PSLs. Therefore, several “computer-aided diagnosis (CAD)” systems are developed by using image processing, machine learning (ML), and deep learning (DL) techniques. Deep-CNN models outperformed traditional ML approaches in extracting complex features from PSLs. In this study, a special transfer learning (TL)-based CNN model is suggested for the diagnosis of seven classes of PSLs. A novel approach (Light-Dermo) is developed that is based on a lightweight CNN model and applies the channelwise attention (CA) mechanism with a focus on computational efficiency. The ShuffleNet architecture is chosen as the backbone, and squeeze-and-excitation (SE) blocks are incorporated as the technique to enhance the original ShuffleNet architecture. Initially, an acces...

Research paper thumbnail of Transfer Learning-based Computer-aided Diagnosis System for Predicting Grades of Diabetic Retinopathy

Computers, Materials & Continua

Diabetic retinopathy (DR) diagnosis through digital fundus images requires clinical experts to re... more Diabetic retinopathy (DR) diagnosis through digital fundus images requires clinical experts to recognize the presence and importance of many intricate features. This task is very difficult for ophthalmologists and timeconsuming. Therefore, many computer-aided diagnosis (CAD) systems were developed to automate this screening process of DR. In this paper, a CAD-DR system is proposed based on preprocessing and a pre-train transfer learningbased convolutional neural network (PCNN) to recognize the five stages of DR through retinal fundus images. To develop this CAD-DR system, a preprocessing step is performed in a perceptual-oriented color space to enhance the DR-related lesions and then a standard pre-train PCNN model is improved to get high classification results. The architecture of the PCNN model is based on three main phases. Firstly, the training process of the proposed PCNN is accomplished by using the expected gradient length (EGL) to decrease the image labeling efforts during the training of the CNN model. Secondly, the most informative patches and images were automatically selected using a few pieces of training labeled samples. Thirdly, the PCNN method generated useful masks for prognostication and identified regions of interest. Fourthly, the DR-related lesions involved in the classification task such as micro-aneurysms, hemorrhages, and exudates were detected and then used for recognition of DR. The PCNN model is pre-trained using a high-end graphical processor unit (GPU) on the publicly available Kaggle benchmark. The obtained results demonstrate that the CAD-DR system outperforms compared to other state-of-the-art in terms of sensitivity (SE), specificity (SP), and accuracy (ACC). On the test set of 30,000 images, the CAD-DR system achieved an average SE of 93.20%, SP of 96.10%, and ACC of 98%. This result indicates that the proposed CAD-DR system is appropriate for the screening of the severity-level of DR.

Research paper thumbnail of Colored Petri Net Models for Clustered and Tree-Based Data Aggregation in Wireless Sensor Networks

Colored Petri Net (CPN) is an influential formalism for describing asynchronous distributed syste... more Colored Petri Net (CPN) is an influential formalism for describing asynchronous distributed systems. They are straightforwardly articulate the behavior of systems particularly those that are structured of replicated components that independently act in a similar manner. Wireless sensor network (WSN) is a typical paradigm of those systems. In this paper, two CPN models for two frequently used data aggregation approaches in WSNs: cluster and tree-based are modeled. The developed models are evaluated using state space analysis and performance evaluation techniques. Performances evaluation is applied in terms of end to end delay and power consumption metrics.

Research paper thumbnail of 4 Embedded Systems Code Optimization and Power Consumption

In a growing number of complex heterogeneous embedded systems, the relevance of software componen... more In a growing number of complex heterogeneous embedded systems, the relevance of software components is rapidly increasing. Issues such as development time, flexibility, and reusability are, in fact, better addressed by software-based solutions. Due to the processing regularity of multimedia and DSP applications, statically scheduled devices such as VLIW processors are viable options over dynamically scheduled processors such as state-of-the-art superscalar GPPs. The programs that run on a particular architecture will significantly affect the energy usage of a processor. The manner in which a program exercises certain parts of a processor will vary the contributions of individual structures to the total energy consumption of the processor. Minimizing power dissipation may be handled by hardware or software optimizations; in hardware through circuit design, and in software through compile-time analysis and code reshaping. While hardware optimization techniques have been the foci of se...

Research paper thumbnail of A Comparative Study of Energy Saving Routing Protocols for Wireless Sensor Networks

Routing protocols play a vital role in wireless sensor networks because of its dynamic topology a... more Routing protocols play a vital role in wireless sensor networks because of its dynamic topology and its nodes limited battery lifetime. In wireless sensor context, saving consumed energy is a crucial task that affects the overall network performance. Researchers exert great efforts to develop energy saving protocols that protract the network lifetime. As such, analyzing routing protocols with respect to total energy dissipation, network lifetime is strongly required. This paper provides a comparative study to extract the key features of various energy aware routing protocols. Two of these protocols are implemented to draw an efficient evaluation procedure to design energy saving routing protocols.

Research paper thumbnail of An Automatic Detection and Classification System of Five Stages for Hypertensive Retinopathy Using Semantic and Instance Segmentation in DenseNet Architecture

Sensors, 2021

The stage and duration of hypertension are connected to the occurrence of Hypertensive Retinopath... more The stage and duration of hypertension are connected to the occurrence of Hypertensive Retinopathy (HR) of eye disease. Currently, a few computerized systems have been developed to recognize HR by using only two stages. It is difficult to define specialized features to recognize five grades of HR. In addition, deep features have been used in the past, but the classification accuracy is not up-to-the-mark. In this research, a new hypertensive retinopathy (HYPER-RETINO) framework is developed to grade the HR based on five grades. The HYPER-RETINO system is implemented based on pre-trained HR-related lesions. To develop this HYPER-RETINO system, several steps are implemented such as a preprocessing, the detection of HR-related lesions by semantic and instance-based segmentation and a DenseNet architecture to classify the stages of HR. Overall, the HYPER-RETINO system determined the local regions within input retinal fundus images to recognize five grades of HR. On average, a 10-fold cr...

Research paper thumbnail of Analysis of Energy Saving Approaches in Cloud Computing using Ant Colony and First Fit Algorithms

International Journal of Advanced Computer Science and Applications, 2017

Cloud computing is a style of technology that is increasingly used every day. It requires the use... more Cloud computing is a style of technology that is increasingly used every day. It requires the use of an important amount of resources that is dynamically provided as a service. The growth of energy consumption associated to the process of resource allocation implemented in the cloud computing is an important issue that needs to be taken into consideration. Better performance will be acquired by allowing the same required workload to be performed using a lower number of servers, which could bring to important energy savings. So it is a requirement to adopt efficient techniques in order to save and minimize energy consumed clouds such as virtual machines migration. This paper analyzes two algorithms: First Fit and Ant Colony which address the use of virtual machine migration approaches to improve the cloud performance in terms of reducing the consumed energy.

Research paper thumbnail of An Improved SDR Frequency Tuning Algorithm for Frequency Hopping Systems

Research paper thumbnail of Code transformations and SIMD impact on embedded software energy/power consumption

2009 International Conference on Computer Engineering & Systems, 2009

Research paper thumbnail of Power estimation methodology for VLIW Digital Signal Processors

2008 42nd Asilomar Conference on Signals, Systems and Computers, 2008

In this contribution the modeling of power consumption for the VLIW processor TMS320C6416T is pre... more In this contribution the modeling of power consumption for the VLIW processor TMS320C6416T is presented taking into account typical software algorithms in signal and image processing. The modeling is performed at the functional level making this approach distinctly different from other modeling approaches in low level technique. This means that the power consumption can be identified at an early stage in the design process, enabling the designer to explore different hardware architectures and software algorithms. Some typical signal and image processing algorithms are used for the purpose of validating the proposed model. The estimated power consumption is compared to the physically measured power consumption, achieving a very low resulting average estimation error of 1.05% and a maximum estimation error of only 3.3% This work has been funded by the Christian Doppler Laboratory for Design Methodology of Signal Processing Algorithms.

Research paper thumbnail of A Precise High-Level Power Consumption Model for Embedded Systems Software

EURASIP Journal on Embedded Systems, 2011

Research paper thumbnail of Power consumption model at functional level for VLIW digital signal processors

In this contribution the modeling of power consumption for the VLIW processor TMS320C6416T is pre... more In this contribution the modeling of power consumption for the VLIW processor TMS320C6416T is presented taking into account typical software algorithms in signal processing. The modeling is performed at the functional level making this approach distinctly different from other modeling approaches in low level technique. This means that the power consumption can be identified at an early stage in the design process, enabling the designer to explore different hardware architectures and algorithms. Some typical signal processing algorithms are used for the purpose of validating the proposed model. The estimated power consumption is compared to the physically measured power consumption, achieving a very low resulting average estimation error of 1.75% and a maximum estimation error of only 3.6%.

Research paper thumbnail of Performance evaluation of a new efficient H.264 intraprediction scheme

TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES, 2016

The paper presents a new efficient H.264/AVC 4 × 4 intraprediction scheme. The new prediction sch... more The paper presents a new efficient H.264/AVC 4 × 4 intraprediction scheme. The new prediction scheme is based on the best prediction matrix mode. The main idea behind the new prediction scheme is to combine the most usable intraprediction modes, {vertical-horizontal-DC} , into a new efficient prediction mode. The new prediction scheme is implemented using VHDL and hence it uses the full advantages of inherent parallelism in the hardware. We evaluate the performance of this prediction scheme in terms of compression ratio, peak signal to noise ratio, and bit rate using seven video sequences. Moreover, we analyze the power consumption, the delay, and FPGA area utilization of the implemented H.264 encoder after utilizing the new prediction scheme. The performance measures as well as the area and power consumption are compared to other best known prediction algorithms.

Research paper thumbnail of VHDL Realization of Efficient H. 264 Intra Prediction Scheme based on Best Prediction Matrix Mode

International Journal of Computer Applications, 2013

This paper introduces a VHDL realization of a new efficient intra prediction scheme that aims to ... more This paper introduces a VHDL realization of a new efficient intra prediction scheme that aims to enhance the compression efficiency of the H.264 standard. The new proposed algorithm is called Best Prediction Matrix Mode (BPMM). The main idea behind the new prediction scheme is to combine the most usable intra prediction modes, {vertical-horizontal-DC}, into a new efficient prediction mode. The performance of the new proposed prediction scheme with respect to compression ratio, Peak Signal to Noise Ratio (PSNR) and bit rate is evaluated. The results show that the BPMM enhances the compression ratio and correspondingly the bit rate and it noticeably increases the PSNR.

Research paper thumbnail of VHDL Realization of Efficient H. 264 Intra Prediction Scheme based on Best Prediction Matrix Mode

International Journal of Computer Applications, 2013

This paper introduces a VHDL realization of a new efficient intra prediction scheme that aims to ... more This paper introduces a VHDL realization of a new efficient intra prediction scheme that aims to enhance the compression efficiency of the H.264 standard. The new proposed algorithm is called Best Prediction Matrix Mode (BPMM). The main idea behind the new prediction scheme is to combine the most usable intra prediction modes, {vertical -horizontal -DC}, into a new efficient prediction mode. The performance of the new proposed prediction scheme with respect to compression ratio, Peak Signal to Noise Ratio (PSNR) and bit rate is evaluated. The results show that the BPMM enhances the compression ratio and correspondingly the bit rate and it noticeably increases the PSNR.

Research paper thumbnail of Biometric-Based Human Identification Using Ensemble-Based Technique and ECG Signals

Applied Sciences

User authentication has become necessary in different life domains. Traditional authentication me... more User authentication has become necessary in different life domains. Traditional authentication methods like personal information numbers (PINs), password ID cards, and tokens are vulnerable to attacks. For secure authentication, methods like biometrics have been developed in the past. Biometric information is hard to lose, forget, duplicate, or share because it is a part of the human body. Many authentication methods focused on electrocardiogram (ECG) signals have achieved great success. In this paper, we have developed cardiac biometrics for human identification using a deep learning (DL) approach. Cardiac biometric systems rely on cardiac signals that are captured using the electrocardiogram (ECG), photoplethysmogram (PPG), and phonocardiogram (PCG). This study utilizes the ECG as a biometric modality because ECG signals are a superior choice for accurate, secure, and reliable biometric-based human identification systems, setting them apart from PPG and PCG approaches. To get bett...

Research paper thumbnail of Assist-Dermo: A Lightweight Separable Vision Transformer Model for Multiclass Skin Lesion Classification

Diagnostics

A dermatologist-like automatic classification system is developed in this paper to recognize nine... more A dermatologist-like automatic classification system is developed in this paper to recognize nine different classes of pigmented skin lesions (PSLs), using a separable vision transformer (SVT) technique to assist clinical experts in early skin cancer detection. In the past, researchers have developed a few systems to recognize nine classes of PSLs. However, they often require enormous computations to achieve high performance, which is burdensome to deploy on resource-constrained devices. In this paper, a new approach to designing SVT architecture is developed based on SqueezeNet and depthwise separable CNN models. The primary goal is to find a deep learning architecture with few parameters that has comparable accuracy to state-of-the-art (SOTA) architectures. This paper modifies the SqueezeNet design for improved runtime performance by utilizing depthwise separable convolutions rather than simple conventional units. To develop this Assist-Dermo system, a data augmentation technique ...

Research paper thumbnail of Light-Dermo: A Lightweight Pretrained Convolution Neural Network for the Diagnosis of Multiclass Skin Lesions

Diagnostics

Skin cancer develops due to the unusual growth of skin cells. Early detection is critical for the... more Skin cancer develops due to the unusual growth of skin cells. Early detection is critical for the recognition of multiclass pigmented skin lesions (PSLs). At an early stage, the manual work by ophthalmologists takes time to recognize the PSLs. Therefore, several “computer-aided diagnosis (CAD)” systems are developed by using image processing, machine learning (ML), and deep learning (DL) techniques. Deep-CNN models outperformed traditional ML approaches in extracting complex features from PSLs. In this study, a special transfer learning (TL)-based CNN model is suggested for the diagnosis of seven classes of PSLs. A novel approach (Light-Dermo) is developed that is based on a lightweight CNN model and applies the channelwise attention (CA) mechanism with a focus on computational efficiency. The ShuffleNet architecture is chosen as the backbone, and squeeze-and-excitation (SE) blocks are incorporated as the technique to enhance the original ShuffleNet architecture. Initially, an acces...

Research paper thumbnail of Transfer Learning-based Computer-aided Diagnosis System for Predicting Grades of Diabetic Retinopathy

Computers, Materials & Continua

Diabetic retinopathy (DR) diagnosis through digital fundus images requires clinical experts to re... more Diabetic retinopathy (DR) diagnosis through digital fundus images requires clinical experts to recognize the presence and importance of many intricate features. This task is very difficult for ophthalmologists and timeconsuming. Therefore, many computer-aided diagnosis (CAD) systems were developed to automate this screening process of DR. In this paper, a CAD-DR system is proposed based on preprocessing and a pre-train transfer learningbased convolutional neural network (PCNN) to recognize the five stages of DR through retinal fundus images. To develop this CAD-DR system, a preprocessing step is performed in a perceptual-oriented color space to enhance the DR-related lesions and then a standard pre-train PCNN model is improved to get high classification results. The architecture of the PCNN model is based on three main phases. Firstly, the training process of the proposed PCNN is accomplished by using the expected gradient length (EGL) to decrease the image labeling efforts during the training of the CNN model. Secondly, the most informative patches and images were automatically selected using a few pieces of training labeled samples. Thirdly, the PCNN method generated useful masks for prognostication and identified regions of interest. Fourthly, the DR-related lesions involved in the classification task such as micro-aneurysms, hemorrhages, and exudates were detected and then used for recognition of DR. The PCNN model is pre-trained using a high-end graphical processor unit (GPU) on the publicly available Kaggle benchmark. The obtained results demonstrate that the CAD-DR system outperforms compared to other state-of-the-art in terms of sensitivity (SE), specificity (SP), and accuracy (ACC). On the test set of 30,000 images, the CAD-DR system achieved an average SE of 93.20%, SP of 96.10%, and ACC of 98%. This result indicates that the proposed CAD-DR system is appropriate for the screening of the severity-level of DR.

Research paper thumbnail of Colored Petri Net Models for Clustered and Tree-Based Data Aggregation in Wireless Sensor Networks

Colored Petri Net (CPN) is an influential formalism for describing asynchronous distributed syste... more Colored Petri Net (CPN) is an influential formalism for describing asynchronous distributed systems. They are straightforwardly articulate the behavior of systems particularly those that are structured of replicated components that independently act in a similar manner. Wireless sensor network (WSN) is a typical paradigm of those systems. In this paper, two CPN models for two frequently used data aggregation approaches in WSNs: cluster and tree-based are modeled. The developed models are evaluated using state space analysis and performance evaluation techniques. Performances evaluation is applied in terms of end to end delay and power consumption metrics.

Research paper thumbnail of 4 Embedded Systems Code Optimization and Power Consumption

In a growing number of complex heterogeneous embedded systems, the relevance of software componen... more In a growing number of complex heterogeneous embedded systems, the relevance of software components is rapidly increasing. Issues such as development time, flexibility, and reusability are, in fact, better addressed by software-based solutions. Due to the processing regularity of multimedia and DSP applications, statically scheduled devices such as VLIW processors are viable options over dynamically scheduled processors such as state-of-the-art superscalar GPPs. The programs that run on a particular architecture will significantly affect the energy usage of a processor. The manner in which a program exercises certain parts of a processor will vary the contributions of individual structures to the total energy consumption of the processor. Minimizing power dissipation may be handled by hardware or software optimizations; in hardware through circuit design, and in software through compile-time analysis and code reshaping. While hardware optimization techniques have been the foci of se...

Research paper thumbnail of A Comparative Study of Energy Saving Routing Protocols for Wireless Sensor Networks

Routing protocols play a vital role in wireless sensor networks because of its dynamic topology a... more Routing protocols play a vital role in wireless sensor networks because of its dynamic topology and its nodes limited battery lifetime. In wireless sensor context, saving consumed energy is a crucial task that affects the overall network performance. Researchers exert great efforts to develop energy saving protocols that protract the network lifetime. As such, analyzing routing protocols with respect to total energy dissipation, network lifetime is strongly required. This paper provides a comparative study to extract the key features of various energy aware routing protocols. Two of these protocols are implemented to draw an efficient evaluation procedure to design energy saving routing protocols.

Research paper thumbnail of An Automatic Detection and Classification System of Five Stages for Hypertensive Retinopathy Using Semantic and Instance Segmentation in DenseNet Architecture

Sensors, 2021

The stage and duration of hypertension are connected to the occurrence of Hypertensive Retinopath... more The stage and duration of hypertension are connected to the occurrence of Hypertensive Retinopathy (HR) of eye disease. Currently, a few computerized systems have been developed to recognize HR by using only two stages. It is difficult to define specialized features to recognize five grades of HR. In addition, deep features have been used in the past, but the classification accuracy is not up-to-the-mark. In this research, a new hypertensive retinopathy (HYPER-RETINO) framework is developed to grade the HR based on five grades. The HYPER-RETINO system is implemented based on pre-trained HR-related lesions. To develop this HYPER-RETINO system, several steps are implemented such as a preprocessing, the detection of HR-related lesions by semantic and instance-based segmentation and a DenseNet architecture to classify the stages of HR. Overall, the HYPER-RETINO system determined the local regions within input retinal fundus images to recognize five grades of HR. On average, a 10-fold cr...

Research paper thumbnail of Analysis of Energy Saving Approaches in Cloud Computing using Ant Colony and First Fit Algorithms

International Journal of Advanced Computer Science and Applications, 2017

Cloud computing is a style of technology that is increasingly used every day. It requires the use... more Cloud computing is a style of technology that is increasingly used every day. It requires the use of an important amount of resources that is dynamically provided as a service. The growth of energy consumption associated to the process of resource allocation implemented in the cloud computing is an important issue that needs to be taken into consideration. Better performance will be acquired by allowing the same required workload to be performed using a lower number of servers, which could bring to important energy savings. So it is a requirement to adopt efficient techniques in order to save and minimize energy consumed clouds such as virtual machines migration. This paper analyzes two algorithms: First Fit and Ant Colony which address the use of virtual machine migration approaches to improve the cloud performance in terms of reducing the consumed energy.

Research paper thumbnail of An Improved SDR Frequency Tuning Algorithm for Frequency Hopping Systems

Research paper thumbnail of Code transformations and SIMD impact on embedded software energy/power consumption

2009 International Conference on Computer Engineering & Systems, 2009

Research paper thumbnail of Power estimation methodology for VLIW Digital Signal Processors

2008 42nd Asilomar Conference on Signals, Systems and Computers, 2008

In this contribution the modeling of power consumption for the VLIW processor TMS320C6416T is pre... more In this contribution the modeling of power consumption for the VLIW processor TMS320C6416T is presented taking into account typical software algorithms in signal and image processing. The modeling is performed at the functional level making this approach distinctly different from other modeling approaches in low level technique. This means that the power consumption can be identified at an early stage in the design process, enabling the designer to explore different hardware architectures and software algorithms. Some typical signal and image processing algorithms are used for the purpose of validating the proposed model. The estimated power consumption is compared to the physically measured power consumption, achieving a very low resulting average estimation error of 1.05% and a maximum estimation error of only 3.3% This work has been funded by the Christian Doppler Laboratory for Design Methodology of Signal Processing Algorithms.

Research paper thumbnail of A Precise High-Level Power Consumption Model for Embedded Systems Software

EURASIP Journal on Embedded Systems, 2011

Research paper thumbnail of Power consumption model at functional level for VLIW digital signal processors

In this contribution the modeling of power consumption for the VLIW processor TMS320C6416T is pre... more In this contribution the modeling of power consumption for the VLIW processor TMS320C6416T is presented taking into account typical software algorithms in signal processing. The modeling is performed at the functional level making this approach distinctly different from other modeling approaches in low level technique. This means that the power consumption can be identified at an early stage in the design process, enabling the designer to explore different hardware architectures and algorithms. Some typical signal processing algorithms are used for the purpose of validating the proposed model. The estimated power consumption is compared to the physically measured power consumption, achieving a very low resulting average estimation error of 1.75% and a maximum estimation error of only 3.6%.

Research paper thumbnail of Performance evaluation of a new efficient H.264 intraprediction scheme

TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES, 2016

The paper presents a new efficient H.264/AVC 4 × 4 intraprediction scheme. The new prediction sch... more The paper presents a new efficient H.264/AVC 4 × 4 intraprediction scheme. The new prediction scheme is based on the best prediction matrix mode. The main idea behind the new prediction scheme is to combine the most usable intraprediction modes, {vertical-horizontal-DC} , into a new efficient prediction mode. The new prediction scheme is implemented using VHDL and hence it uses the full advantages of inherent parallelism in the hardware. We evaluate the performance of this prediction scheme in terms of compression ratio, peak signal to noise ratio, and bit rate using seven video sequences. Moreover, we analyze the power consumption, the delay, and FPGA area utilization of the implemented H.264 encoder after utilizing the new prediction scheme. The performance measures as well as the area and power consumption are compared to other best known prediction algorithms.

Research paper thumbnail of VHDL Realization of Efficient H. 264 Intra Prediction Scheme based on Best Prediction Matrix Mode

International Journal of Computer Applications, 2013

This paper introduces a VHDL realization of a new efficient intra prediction scheme that aims to ... more This paper introduces a VHDL realization of a new efficient intra prediction scheme that aims to enhance the compression efficiency of the H.264 standard. The new proposed algorithm is called Best Prediction Matrix Mode (BPMM). The main idea behind the new prediction scheme is to combine the most usable intra prediction modes, {vertical-horizontal-DC}, into a new efficient prediction mode. The performance of the new proposed prediction scheme with respect to compression ratio, Peak Signal to Noise Ratio (PSNR) and bit rate is evaluated. The results show that the BPMM enhances the compression ratio and correspondingly the bit rate and it noticeably increases the PSNR.

Research paper thumbnail of VHDL Realization of Efficient H. 264 Intra Prediction Scheme based on Best Prediction Matrix Mode

International Journal of Computer Applications, 2013

This paper introduces a VHDL realization of a new efficient intra prediction scheme that aims to ... more This paper introduces a VHDL realization of a new efficient intra prediction scheme that aims to enhance the compression efficiency of the H.264 standard. The new proposed algorithm is called Best Prediction Matrix Mode (BPMM). The main idea behind the new prediction scheme is to combine the most usable intra prediction modes, {vertical -horizontal -DC}, into a new efficient prediction mode. The performance of the new proposed prediction scheme with respect to compression ratio, Peak Signal to Noise Ratio (PSNR) and bit rate is evaluated. The results show that the BPMM enhances the compression ratio and correspondingly the bit rate and it noticeably increases the PSNR.