Khalid A . AlAfandy | Université Abdelmalek Essaâdi (original) (raw)

Papers by Khalid A . AlAfandy

Computers, Materials & Continua, 2022

Remote sensing image processing engaged researchers' attentiveness in recent years, especially cl... more Remote sensing image processing engaged researchers' attentiveness in recent years, especially classification. The main problem in classification is the ratio of the correct predictions after training. Feature extraction is the foremost important step to build high-performance image classifiers. The convolution neural networks can extract images' features that significantly improve the image classifiers' accuracy. This paper proposes two efficient approaches for remote sensing images classification that utilizes the concatenation of two convolution channels' outputs as a features extraction using two classic convolution models; these convolution models are the ResNet 50 and the DenseNet 169. These elicited features have been used by the fully connected neural network classifier and support vector machine classifier as input features. The results of the proposed methods are compared with other antecedent approaches in the same experimental environments. Evaluation is based on learning curves plotted during the training of the proposed classifier that is based on a fully connected neural network and measuring the overall accuracy for the both proposed classifiers. The proposed classifiers are used with their trained weights to predict a big remote sensing scene's classes for a developed test. Experimental results ensure that, compared with the other traditional classifiers, the proposed classifiers are further accurate.

Proceedings of the 4th International Conference on Big Data and Internet of Things, 2019

Approaches and Applications of Deep Learning in Virtual Medical Care, 2022

This chapter provides a comprehensive explanation of deep learning including an introduction to A... more This chapter provides a comprehensive explanation of deep learning including an introduction to ANNs, improving the deep NNs, CNNs, classic networks, and some technical tricks for image classification using deep learning. ANNs, mathematical models for one node ANN, and multi-layers/multi-nodes ANNs are explained followed by the ANNs training algorithm followed by the loss function, the cost function, the activation function with its derivatives, and the back-propagation algorithm. This chapter also outlines the most common training problems with the most common solutions and ANNs improvements. CNNs are explained in this chapter with the convolution filters, pooling filters, stride, padding, and the CNNs mathematical models. This chapter explains the four most commonly used classic networks and ends with some technical tricks that can be used in CNNs model training.

Advances in Science, Technology and Engineering Systems Journal, 2020

Multimedia Tools and Applications, 2018

Digital watermarking is an efficient and promising mechanism for protecting the copyright of the ... more Digital watermarking is an efficient and promising mechanism for protecting the copyright of the transmitted multimedia information. Thus, this paper presents two robust hybrid color image watermarking techniques. The objective of the proposed watermarking techniques is to increase the immunity of the watermarked color images against attacks and to achieve adequate perceptual quality. The first proposed hybrid technique is the homomorphic transform based Singular Value Decomposition (SVD) in Discrete Wavelet Transform (DWT) domain. Firstly, the DWT is employed to divide an image into non-overlapping bands. Then, the reflectance components of the LL sub-bands are extracted using the homomorphic transform of each of the RGB (Red, Green, and Blue) color image components. After that, the watermark is embedded by applying the SVD on these reflectance components. The second proposed hybrid technique is the three-level Discrete Stationary Wavelet Transform (DSWT) in Discrete Cosine Transform (DCT) domain. In this technique, the RGB components of the host color image are separated, and then the DCT is applied on each separated color component. The three-level DSWT is employed to divide the DCT components into four sub-bands. These sub-bands are the A, H, V, and D matrices, which have the same host image size. The watermark image is then embedded into the determined matrix A. The two proposed hybrid watermarking techniques are compared with the current state-of-the-art techniques. This paper also presents a comparative study of the proposed techniques for different color imaging systems to determine their robustness and stability. The comparisons are based on the subjective visual results to detect any degradation in the watermarked image in addition to the objective results of the Peak Signal-to-Noise Ratio (PSNR) of the watermarked image, and the Normalized Correlation (NC) of the extracted watermark to test and evaluate the performance efficiency of the proposed watermarking techniques. Extensive experimental results show that the proposed hybrid watermarking techniques are both robust and have adequate immunity against different types of attacks compared to the traditional watermarking techniques. They achieve not only very good perceptual quality with appreciated PSNR values, but also high correlation coefficient values in the presence of different multimedia attacks.

2016 Fourth International Japan-Egypt Conference on Electronics, Communications and Computers (JEC-ECC), 2016

This paper proposes a robust image watermarking approach using homomorphic based SVD in the DWT d... more This paper proposes a robust image watermarking approach using homomorphic based SVD in the DWT domain. The DWT is utilized to divide the host image into non-overlapping bands. The reflectance component of sub-band LL is extracted using homomorphic transform for each color (red, green and blue). The embedding watermark is done by applying SVD on the reflectance component of the sub-band LL. The results of the proposed watermarking approach are compared with those of the other traditional approaches. Evaluation is based on visualization, Peak Signal-to-Noise Ratio of watermarked image (PSNR), Normalized Correlation of watermark after detection (NC). Experimental results ensure that the proposed watermarking approach is both robust and immune to attacks studied in this paper compared with the other traditional approaches.

World Academy of Science, Engineering and Technology, International Journal of Computer, Electrical, Automation, Control and Information Engineering, 2017

Advances in Science, Technology and Engineering Systems Journal, 2020

A R T I C L E I N F O A B S T R A C T Article history: Received: 12 August, 2020 Accepted: 25 Sep... more A R T I C L E I N F O A B S T R A C T Article history: Received: 12 August, 2020 Accepted: 25 September, 2020 Online: 12 October, 2020 This paper presents a comparative study for using the deep classic convolution networks in remote sensing images classification. There are four deep convolution models that used in this comparative study; the DenseNet 196, the NASNet Mobile, the VGG 16, and the ResNet 50 models. These learning convolution models are based on the use of the ImageNet pretrained weights, transfer learning, and then adding a full connected layer that compatible with the used dataset classes. There are two datasets are used in this comparison; the UC Merced land use dataset and the SIRI-WHU dataset. This comparison is based on the inspection of the learning curves to determine how well the training model is and calculating the overall accuracy that determines the model performance. This comparison illustrates that the use of the ResNet 50 model has the highest overall acc...

Digital multimedia is easily duplicated and distributed using many free softwares. It is importan... more Digital multimedia is easily duplicated and distributed using many free softwares. It is important to have copyright protection to save owners copyrights. There are many protection techniques; one of them is watermarking. In watermarking techniques, the objective is to embed a watermark label or image into the original images, audios, or videos. This book presents two robust image watermarking techniques; homomorphic Singular Value Decomposition (SVD) watermarking in Discrete Wavelet Transform (DWT) domain and 3-level Discrete Stationary Wavelet Transform (DSWT) in the Discrete Cosine Transform (DCT) domain. A study for watermarking on different color coordinate systems is included in this book with results

This paper presents a comparative study of using different color systems on watermarking algorith... more This paper presents a comparative study of using different color systems on watermarking algorithms. This comparison aim is to determining the robustness and the stability of the color systems used in the watermarking scheme. The watermarking algorithm that is used in this paper is a hybrid scheme using the Discrete Wavelet Transform (DWT) in the Discrete Cosine Transform (DCT) domain. The DCT-DWT watermarking algorithm is applied using three color systems, the RGB (Red, Green and Blue) color system, the HSV (Hue, Saturation and Value) color system and the YIQ color system. The comparison is based on visualization to detect any degradation in the watermarked image, the Peak Signal-to-Noise Ratio (PSNR) of the watermarked image, the Normalized Correlation (NC) of the extracted watermark after extraction, the embedding algorithm CPU time, and applying different types of attacks and then calculating the PSNR and the NC.

Multimedia Tools and Applications

Digital watermarking is an efficient and promising mechanism for protecting the copyright of the ... more Digital watermarking is an efficient and promising mechanism for protecting the copyright of the transmitted multimedia information. Thus, this paper presents two robust hybrid color image watermarking techniques. The objective of the proposed watermarking techniques is to increase the immunity of the watermarked color images against attacks and to achieve adequate perceptual quality. The first proposed hybrid technique is the homomorphic transform based Singular Value Decomposition (SVD) in Discrete Wavelet Transform (DWT) domain. Firstly, the DWT is employed to divide an image into non-overlapping bands. Then, the reflectance components of the LL sub-bands are extracted using the homomorphic transform of each of the RGB (Red, Green, and Blue) color image components. After that, the watermark is embedded by applying the SVD on these reflectance components. The second proposed hybrid technique is the three-level Discrete Stationary Wavelet Transform (DSWT) in Discrete Cosine Transform (DCT) domain. In this technique, the RGB components of the host color image are separated, and then the DCT is applied on each separated color component. The three-level DSWT is employed to divide the DCT components into four sub-bands. These sub-bands are the A, H, V, and D matrices, which have the same host image size. The watermark image is then embedded into the determined matrix A. The two proposed hybrid watermarking techniques are compared with the current state-of-the-art techniques. This paper also presents a comparative study of the proposed techniques for different color imaging systems to determine their robustness and stability. The comparisons are based on the subjective visual results to detect any degradation in the watermarked image in addition to the objective results of the Peak Signal-to-Noise Ratio (PSNR) of the watermarked image, and the Normalized Correlation (NC) of the extracted watermark to test and evaluate the performance efficiency of the proposed watermarking techniques. Extensive experimental results show that the proposed hybrid watermarking techniques are both robust and have adequate immunity against different types of attacks compared to the traditional watermarking techniques. They achieve not only very good perceptual quality with appreciated PSNR values, but also high correlation coefficient values in the presence of different multimedia attacks.

2016 4th IEEE International Colloquium on Information Science and Technology (CiSt), 2016

This paper proposes a hybrid robust image watermarking scheme based on three levels of Discrete S... more This paper proposes a hybrid robust image watermarking scheme based on three levels of Discrete Stationary Wavelet Transform (DSWT) in the Discrete Cosine Transform (DCT) domain. The host image colors (red, green and blue) are separated, and then the DCT is applied on each color after separation. The DSWT is utilized to divide the DCT output into four sub-bands (3 levels). These sub-bands are (A, H, V, D) matrices with the same image size. The watermark is embedded on matrix A. The results of the proposed watermarking scheme are compared with other state-of-the-art schemes. The comparison is based on visualization to detect any degradation of the watermarked image, Peak Signal-to-Noise Ratio (PSNR) of the watermarked image, Normal Correlation (NC) of the extracted watermark after detection, applying attacks, and then calculating the PSNR and NC.

Advances in Science, Technology and Engineering Systems Journal

Feature extraction is an important process in image classification for achieving an efficient acc... more Feature extraction is an important process in image classification for achieving an efficient accuracy for the classification learning models. One of these methods is using the convolution neural networks. The use of the trained classic deep convolution neural networks as features extraction gives a considerable results in the remote sensing images classification models. So, this paper proposes three classification approaches using the support vector machine where based on the use of the ImageNet pre-trained weights classic deep convolution neural networks as features extraction from the remote sensing images. There are three convolution models that used in this paper; the Densenet 169, the VGG 16, and the ResNet 50 models. A comparative study is done by extract features using the outputs of the mentioned ImageNet pre-trained weights convolution models after transfer learning, and then use these extracted features as input features for the support vector machine classifier. The used datasets in this paper are the UC Merced land use dataset and the SIRI-WHU dataset. The comparison is based on calculating the overall accuracy to assess the classification model performance.

2016 4th IEEE International Colloquium on Information Science and Technology (CiSt), 2016

Computers, Materials & Continua, 2022

Remote sensing image processing engaged researchers' attentiveness in recent years, especially cl... more Remote sensing image processing engaged researchers' attentiveness in recent years, especially classification. The main problem in classification is the ratio of the correct predictions after training. Feature extraction is the foremost important step to build high-performance image classifiers. The convolution neural networks can extract images' features that significantly improve the image classifiers' accuracy. This paper proposes two efficient approaches for remote sensing images classification that utilizes the concatenation of two convolution channels' outputs as a features extraction using two classic convolution models; these convolution models are the ResNet 50 and the DenseNet 169. These elicited features have been used by the fully connected neural network classifier and support vector machine classifier as input features. The results of the proposed methods are compared with other antecedent approaches in the same experimental environments. Evaluation is based on learning curves plotted during the training of the proposed classifier that is based on a fully connected neural network and measuring the overall accuracy for the both proposed classifiers. The proposed classifiers are used with their trained weights to predict a big remote sensing scene's classes for a developed test. Experimental results ensure that, compared with the other traditional classifiers, the proposed classifiers are further accurate.

Proceedings of the 4th International Conference on Big Data and Internet of Things, 2019

Approaches and Applications of Deep Learning in Virtual Medical Care, 2022

This chapter provides a comprehensive explanation of deep learning including an introduction to A... more This chapter provides a comprehensive explanation of deep learning including an introduction to ANNs, improving the deep NNs, CNNs, classic networks, and some technical tricks for image classification using deep learning. ANNs, mathematical models for one node ANN, and multi-layers/multi-nodes ANNs are explained followed by the ANNs training algorithm followed by the loss function, the cost function, the activation function with its derivatives, and the back-propagation algorithm. This chapter also outlines the most common training problems with the most common solutions and ANNs improvements. CNNs are explained in this chapter with the convolution filters, pooling filters, stride, padding, and the CNNs mathematical models. This chapter explains the four most commonly used classic networks and ends with some technical tricks that can be used in CNNs model training.

Advances in Science, Technology and Engineering Systems Journal, 2020

Multimedia Tools and Applications, 2018

Digital watermarking is an efficient and promising mechanism for protecting the copyright of the ... more Digital watermarking is an efficient and promising mechanism for protecting the copyright of the transmitted multimedia information. Thus, this paper presents two robust hybrid color image watermarking techniques. The objective of the proposed watermarking techniques is to increase the immunity of the watermarked color images against attacks and to achieve adequate perceptual quality. The first proposed hybrid technique is the homomorphic transform based Singular Value Decomposition (SVD) in Discrete Wavelet Transform (DWT) domain. Firstly, the DWT is employed to divide an image into non-overlapping bands. Then, the reflectance components of the LL sub-bands are extracted using the homomorphic transform of each of the RGB (Red, Green, and Blue) color image components. After that, the watermark is embedded by applying the SVD on these reflectance components. The second proposed hybrid technique is the three-level Discrete Stationary Wavelet Transform (DSWT) in Discrete Cosine Transform (DCT) domain. In this technique, the RGB components of the host color image are separated, and then the DCT is applied on each separated color component. The three-level DSWT is employed to divide the DCT components into four sub-bands. These sub-bands are the A, H, V, and D matrices, which have the same host image size. The watermark image is then embedded into the determined matrix A. The two proposed hybrid watermarking techniques are compared with the current state-of-the-art techniques. This paper also presents a comparative study of the proposed techniques for different color imaging systems to determine their robustness and stability. The comparisons are based on the subjective visual results to detect any degradation in the watermarked image in addition to the objective results of the Peak Signal-to-Noise Ratio (PSNR) of the watermarked image, and the Normalized Correlation (NC) of the extracted watermark to test and evaluate the performance efficiency of the proposed watermarking techniques. Extensive experimental results show that the proposed hybrid watermarking techniques are both robust and have adequate immunity against different types of attacks compared to the traditional watermarking techniques. They achieve not only very good perceptual quality with appreciated PSNR values, but also high correlation coefficient values in the presence of different multimedia attacks.

2016 Fourth International Japan-Egypt Conference on Electronics, Communications and Computers (JEC-ECC), 2016

This paper proposes a robust image watermarking approach using homomorphic based SVD in the DWT d... more This paper proposes a robust image watermarking approach using homomorphic based SVD in the DWT domain. The DWT is utilized to divide the host image into non-overlapping bands. The reflectance component of sub-band LL is extracted using homomorphic transform for each color (red, green and blue). The embedding watermark is done by applying SVD on the reflectance component of the sub-band LL. The results of the proposed watermarking approach are compared with those of the other traditional approaches. Evaluation is based on visualization, Peak Signal-to-Noise Ratio of watermarked image (PSNR), Normalized Correlation of watermark after detection (NC). Experimental results ensure that the proposed watermarking approach is both robust and immune to attacks studied in this paper compared with the other traditional approaches.

World Academy of Science, Engineering and Technology, International Journal of Computer, Electrical, Automation, Control and Information Engineering, 2017

Advances in Science, Technology and Engineering Systems Journal, 2020

A R T I C L E I N F O A B S T R A C T Article history: Received: 12 August, 2020 Accepted: 25 Sep... more A R T I C L E I N F O A B S T R A C T Article history: Received: 12 August, 2020 Accepted: 25 September, 2020 Online: 12 October, 2020 This paper presents a comparative study for using the deep classic convolution networks in remote sensing images classification. There are four deep convolution models that used in this comparative study; the DenseNet 196, the NASNet Mobile, the VGG 16, and the ResNet 50 models. These learning convolution models are based on the use of the ImageNet pretrained weights, transfer learning, and then adding a full connected layer that compatible with the used dataset classes. There are two datasets are used in this comparison; the UC Merced land use dataset and the SIRI-WHU dataset. This comparison is based on the inspection of the learning curves to determine how well the training model is and calculating the overall accuracy that determines the model performance. This comparison illustrates that the use of the ResNet 50 model has the highest overall acc...

Digital multimedia is easily duplicated and distributed using many free softwares. It is importan... more Digital multimedia is easily duplicated and distributed using many free softwares. It is important to have copyright protection to save owners copyrights. There are many protection techniques; one of them is watermarking. In watermarking techniques, the objective is to embed a watermark label or image into the original images, audios, or videos. This book presents two robust image watermarking techniques; homomorphic Singular Value Decomposition (SVD) watermarking in Discrete Wavelet Transform (DWT) domain and 3-level Discrete Stationary Wavelet Transform (DSWT) in the Discrete Cosine Transform (DCT) domain. A study for watermarking on different color coordinate systems is included in this book with results

This paper presents a comparative study of using different color systems on watermarking algorith... more This paper presents a comparative study of using different color systems on watermarking algorithms. This comparison aim is to determining the robustness and the stability of the color systems used in the watermarking scheme. The watermarking algorithm that is used in this paper is a hybrid scheme using the Discrete Wavelet Transform (DWT) in the Discrete Cosine Transform (DCT) domain. The DCT-DWT watermarking algorithm is applied using three color systems, the RGB (Red, Green and Blue) color system, the HSV (Hue, Saturation and Value) color system and the YIQ color system. The comparison is based on visualization to detect any degradation in the watermarked image, the Peak Signal-to-Noise Ratio (PSNR) of the watermarked image, the Normalized Correlation (NC) of the extracted watermark after extraction, the embedding algorithm CPU time, and applying different types of attacks and then calculating the PSNR and the NC.

Multimedia Tools and Applications

Digital watermarking is an efficient and promising mechanism for protecting the copyright of the ... more Digital watermarking is an efficient and promising mechanism for protecting the copyright of the transmitted multimedia information. Thus, this paper presents two robust hybrid color image watermarking techniques. The objective of the proposed watermarking techniques is to increase the immunity of the watermarked color images against attacks and to achieve adequate perceptual quality. The first proposed hybrid technique is the homomorphic transform based Singular Value Decomposition (SVD) in Discrete Wavelet Transform (DWT) domain. Firstly, the DWT is employed to divide an image into non-overlapping bands. Then, the reflectance components of the LL sub-bands are extracted using the homomorphic transform of each of the RGB (Red, Green, and Blue) color image components. After that, the watermark is embedded by applying the SVD on these reflectance components. The second proposed hybrid technique is the three-level Discrete Stationary Wavelet Transform (DSWT) in Discrete Cosine Transform (DCT) domain. In this technique, the RGB components of the host color image are separated, and then the DCT is applied on each separated color component. The three-level DSWT is employed to divide the DCT components into four sub-bands. These sub-bands are the A, H, V, and D matrices, which have the same host image size. The watermark image is then embedded into the determined matrix A. The two proposed hybrid watermarking techniques are compared with the current state-of-the-art techniques. This paper also presents a comparative study of the proposed techniques for different color imaging systems to determine their robustness and stability. The comparisons are based on the subjective visual results to detect any degradation in the watermarked image in addition to the objective results of the Peak Signal-to-Noise Ratio (PSNR) of the watermarked image, and the Normalized Correlation (NC) of the extracted watermark to test and evaluate the performance efficiency of the proposed watermarking techniques. Extensive experimental results show that the proposed hybrid watermarking techniques are both robust and have adequate immunity against different types of attacks compared to the traditional watermarking techniques. They achieve not only very good perceptual quality with appreciated PSNR values, but also high correlation coefficient values in the presence of different multimedia attacks.

2016 4th IEEE International Colloquium on Information Science and Technology (CiSt), 2016

This paper proposes a hybrid robust image watermarking scheme based on three levels of Discrete S... more This paper proposes a hybrid robust image watermarking scheme based on three levels of Discrete Stationary Wavelet Transform (DSWT) in the Discrete Cosine Transform (DCT) domain. The host image colors (red, green and blue) are separated, and then the DCT is applied on each color after separation. The DSWT is utilized to divide the DCT output into four sub-bands (3 levels). These sub-bands are (A, H, V, D) matrices with the same image size. The watermark is embedded on matrix A. The results of the proposed watermarking scheme are compared with other state-of-the-art schemes. The comparison is based on visualization to detect any degradation of the watermarked image, Peak Signal-to-Noise Ratio (PSNR) of the watermarked image, Normal Correlation (NC) of the extracted watermark after detection, applying attacks, and then calculating the PSNR and NC.

Advances in Science, Technology and Engineering Systems Journal

Feature extraction is an important process in image classification for achieving an efficient acc... more Feature extraction is an important process in image classification for achieving an efficient accuracy for the classification learning models. One of these methods is using the convolution neural networks. The use of the trained classic deep convolution neural networks as features extraction gives a considerable results in the remote sensing images classification models. So, this paper proposes three classification approaches using the support vector machine where based on the use of the ImageNet pre-trained weights classic deep convolution neural networks as features extraction from the remote sensing images. There are three convolution models that used in this paper; the Densenet 169, the VGG 16, and the ResNet 50 models. A comparative study is done by extract features using the outputs of the mentioned ImageNet pre-trained weights convolution models after transfer learning, and then use these extracted features as input features for the support vector machine classifier. The used datasets in this paper are the UC Merced land use dataset and the SIRI-WHU dataset. The comparison is based on calculating the overall accuracy to assess the classification model performance.

2016 4th IEEE International Colloquium on Information Science and Technology (CiSt), 2016