Nadia Smaoui | Ecole Nationale d'Ingénieurs de Sfax (ENIS) (original) (raw)
Papers by Nadia Smaoui
Journal of Computing Science and Engineering
2018 15th International Multi-Conference on Systems, Signals & Devices (SSD), 2018
The impact and influence of digital images on modern society are enormous, and image processing i... more The impact and influence of digital images on modern society are enormous, and image processing is now a crucial component of science and technology. The quick progress in computer-based medical image reconstruction, and the associated developments in analysis methods and computerized diagnosis, have brought medical imaging into one of the most important sub-fields in scientific imaging. In this context, our paper fits. The work presents a simple method for a preprocessing and an automatic detection of the area of interest in order to make the necessary diagnosis. The proposed approach has been applied for the detection of melanoma. Once detected, the ABeD rule can be applied to conclude on the malignancy of the lesion. The proposed approach is implemented in MATLAB environment and the experiment is based on a PH2 database containing suspicious melanoma skin cancer. Based on the experiment, the accuracy of the developed approach is 92 %, which reflects its reliability.
2020 17th International Multi-Conference on Systems, Signals & Devices (SSD), 2020
Alzheimer's disease (AD) remains a major public health problem. This neurodegenerative pathol... more Alzheimer's disease (AD) remains a major public health problem. This neurodegenerative pathology affects generally old people. Its symptoms are loss of memory followed over the years by more hard ability of expression and various handicaps. Therefore, early detection of AD is become an active research area in recent years. In this paper, we propose a deep based method for the detection of AD (i.e. classify brain images into normal brain or brain with AD). The proposed method contains two main steps. The first step is region of interest extraction; it is based on the partition of the image into separate blocks to extract only the part that contains the hippocampus of the brain. The second step is the classification of images using two deep based techniques namely convolutional neural network (CNN) and Transfer Learning. In one hand, CNN allows extracting the characteristics from brain images, then classifies them into normal brain or AD brain. Transfer Learning, in the other hand, consists of using features acquired from the Alexnet architecture to classify the images. We have assessed the proposed method on Oasis dataset (Open Access Series of Imaging Studies). The obtained results show that the classification of images using Transfer Learning with 92.86 % outperformed the CNN's classification rate.
In recent years, there has been a fairly rapid increase in the number of melanoma skin cancer pat... more In recent years, there has been a fairly rapid increase in the number of melanoma skin cancer patients. Melanoma, this deadliest form of skin cancer, must be diagnosed early for effective treatment. So, it is necessary to develop a computer-aided diagnostic system to facilitate its early detection. In this paper, the proposed work is based on a combination of a segmentation method and an analytical method and aims to improve these two methods in order to develop an interface that can assist dermatologists in the diagnostic phase. As a first step, a sequence of preprocessing is implemented to remove noise and unwanted structures from the image. Then, an automatic segmentation approach locates the skin lesion. The next step is feature extraction followed by the ABCD rule to make the diagnosis through the calculation of the TDV score. In this research, three diagnosis are used which are melanoma, suspicious, and benign skin lesion. The experiment uses 40 images containing suspicious me...
2021 18th International Multi-Conference on Systems, Signals & Devices (SSD), 2021
Alzheimer's disease (AD) detection corresponds one of the most powerful and challenging tasks... more Alzheimer's disease (AD) detection corresponds one of the most powerful and challenging tasks in medical imaging processing. This paper describes the survey of recent AD detection techniques in the last ten years. The process of AD detection can include different stages such as preprocessing, feature extraction, feature selection, dimensionality reduction, segmentation and classification. In this survey, we review the recent findings and future trends and we set out the various types of AD detection techniques with their major contributions. The performances of the most important AD detection techniques are compared and discussed according to the applied algorithms, approaches and databases (e.g. OASIS, ADNI and MIRIAD).
Current Medical Imaging Formerly Current Medical Imaging Reviews, 2020
Background: Skin cancer is one of the most common forms of cancers among humans. It can be classi... more Background: Skin cancer is one of the most common forms of cancers among humans. It can be classified as non-melanoma and melanoma. Although melanomas are less common than non-melanomas, the former is the most common cause of mortality. Therefore, it becomes necessary to develop a Computer-aided Diagnosis (CAD) aiming to detect this kind of lesion and enable the diagnosis of the disease at an early stage in order to augment the patient’s survival likelihood. Aims: This paper aims to develop a simple method capable of detecting and classifying skin lesions using dermoscopy images based on ABCD rules. Methods: The proposed approach follows four steps. 1) The preprocessing stage consists of filtering and contrast enhancing algorithms. 2) The segmentation stage aims at detecting the lesion. 3) The feature extraction stage based on the calculation of the four parameters which are asymmetry, border irregularity, color and diameter. 4) The classification stage based on the summation of the...
International Journal of Digital Signals and Smart Systems, 2018
2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), 2020
Nowadays, high-resolution fingerprint images are more and more used in the fingerprint recognitio... more Nowadays, high-resolution fingerprint images are more and more used in the fingerprint recognition systems thanks to the recognition accuracy that they provide. Indeed, they offer more sufficient details such as sweat pores, ridges, contours, and other details. Pores have been adopted to be one of the brilliant nominees in improving the efficiency of automated fingerprint identification systems to maintain a high level of security. However, the geometric transformations, that occur during the acquisition phase, can cause several defects on the result of the matching process, hence they decline the accuracy of the recognition. To overcome this problem, alignment is often needed. This image pretreatment is classically based on complex geometric operations that are time-consuming. Otherwise, for pore matching, the majority of approaches are based only on pore coordinates. In this paper, we propose a novel pore matching method based, firstly, on only one of the singular points, namely t...
ISSN: 2186-1390 (Online) http://CenNSER.org/IJCVSP Abstract In recent years, there has been a fai... more ISSN: 2186-1390 (Online) http://CenNSER.org/IJCVSP Abstract In recent years, there has been a fairly rapid increase in the number of melanoma skin cancer patients. Melanoma, this deadliest form of skin cancer, must be diagnosed early for effective treatment. So, it is necessary to develop a computer-aided diagnostic system to facilitate its early detection. In this paper, the proposed work is based on a combination of a segmentation method and an analytical method and aims to improve these two methods in order to develop an interface that can assist dermatologists in the diagnostic phase. As a first step, a sequence of preprocessing is implemented to remove noise and unwanted structures from the image. Then, an automatic segmentation approach locates the skin lesion. The next step is feature extraction followed by the ABCD rule to make the diagnosis through the calculation of the TDV score. In this research, three diagnosis are used which are melanoma, suspicious, and benign skin le...
2016 13th International Multi-Conference on Systems, Signals & Devices (SSD), 2016
Advanced Methods for Human Biometrics
2019 16th International Multi-Conference on Systems, Signals & Devices (SSD)
International Journal of Computer Applications, Nov 10, 2010
Watershed algorithm as was introduced by Vincent and Soille is a segmentation algorithm based on ... more Watershed algorithm as was introduced by Vincent and Soille is a segmentation algorithm based on the inundation process of the image gradient which is observed as a relief. It aims at finding the peaks in the image gradient called watersheds and identifying them as the image contours. Due to its flexibility and rapidity, this algorithm is used in several applications. However, its main drawback is the over segmentation .In this paper, we improve this technique by introducing a histogram driven methodology. The developed architecture is applied on an empirical basis for research on image segmentation and boundary detection in order to be compared with other segmentation algorithms. The simulation results show that the performance of our algorithm is superior to the other segmentation techniques. Finally, the whole design is implemented on a Virtex 5 platform based on a codesign methodology leading to 147 MHz frequency and 76% of hardware resource occupation for an image of the size of 128*128.
International Image Processing, Applications and Systems Conference, 2014
In recent years, there has been a fairly rapid increase in the number of melanoma skin cancer pat... more In recent years, there has been a fairly rapid increase in the number of melanoma skin cancer patients. Despite the immense danger that this disease presents, the more early it is treated, the more rapidly, it is cured. So, it is necessary to develop computer-aided diagnosis system to facilitate early detection of this cancer. In this paper, we have tried to develop such system. As a first step, a sequence of preprocessing is implemented to remove noise and unwanted structures from the image. Then, an automatic segmentation approach locates the skin lesion. The next step is feature extraction followed by the ABCD rule to make the diagnosis by calculating the TDV score. In this research, three diagnosis are used which are melanoma, suspicious, and benign skin lesion. The experiment uses 40 images containing suspicious melanoma skin cancer. Based on the experiment, the accuracy of the system is 92% which reflects its fiability.
Journal of Computing Science and Engineering
2018 15th International Multi-Conference on Systems, Signals & Devices (SSD), 2018
The impact and influence of digital images on modern society are enormous, and image processing i... more The impact and influence of digital images on modern society are enormous, and image processing is now a crucial component of science and technology. The quick progress in computer-based medical image reconstruction, and the associated developments in analysis methods and computerized diagnosis, have brought medical imaging into one of the most important sub-fields in scientific imaging. In this context, our paper fits. The work presents a simple method for a preprocessing and an automatic detection of the area of interest in order to make the necessary diagnosis. The proposed approach has been applied for the detection of melanoma. Once detected, the ABeD rule can be applied to conclude on the malignancy of the lesion. The proposed approach is implemented in MATLAB environment and the experiment is based on a PH2 database containing suspicious melanoma skin cancer. Based on the experiment, the accuracy of the developed approach is 92 %, which reflects its reliability.
2020 17th International Multi-Conference on Systems, Signals & Devices (SSD), 2020
Alzheimer's disease (AD) remains a major public health problem. This neurodegenerative pathol... more Alzheimer's disease (AD) remains a major public health problem. This neurodegenerative pathology affects generally old people. Its symptoms are loss of memory followed over the years by more hard ability of expression and various handicaps. Therefore, early detection of AD is become an active research area in recent years. In this paper, we propose a deep based method for the detection of AD (i.e. classify brain images into normal brain or brain with AD). The proposed method contains two main steps. The first step is region of interest extraction; it is based on the partition of the image into separate blocks to extract only the part that contains the hippocampus of the brain. The second step is the classification of images using two deep based techniques namely convolutional neural network (CNN) and Transfer Learning. In one hand, CNN allows extracting the characteristics from brain images, then classifies them into normal brain or AD brain. Transfer Learning, in the other hand, consists of using features acquired from the Alexnet architecture to classify the images. We have assessed the proposed method on Oasis dataset (Open Access Series of Imaging Studies). The obtained results show that the classification of images using Transfer Learning with 92.86 % outperformed the CNN's classification rate.
In recent years, there has been a fairly rapid increase in the number of melanoma skin cancer pat... more In recent years, there has been a fairly rapid increase in the number of melanoma skin cancer patients. Melanoma, this deadliest form of skin cancer, must be diagnosed early for effective treatment. So, it is necessary to develop a computer-aided diagnostic system to facilitate its early detection. In this paper, the proposed work is based on a combination of a segmentation method and an analytical method and aims to improve these two methods in order to develop an interface that can assist dermatologists in the diagnostic phase. As a first step, a sequence of preprocessing is implemented to remove noise and unwanted structures from the image. Then, an automatic segmentation approach locates the skin lesion. The next step is feature extraction followed by the ABCD rule to make the diagnosis through the calculation of the TDV score. In this research, three diagnosis are used which are melanoma, suspicious, and benign skin lesion. The experiment uses 40 images containing suspicious me...
2021 18th International Multi-Conference on Systems, Signals & Devices (SSD), 2021
Alzheimer's disease (AD) detection corresponds one of the most powerful and challenging tasks... more Alzheimer's disease (AD) detection corresponds one of the most powerful and challenging tasks in medical imaging processing. This paper describes the survey of recent AD detection techniques in the last ten years. The process of AD detection can include different stages such as preprocessing, feature extraction, feature selection, dimensionality reduction, segmentation and classification. In this survey, we review the recent findings and future trends and we set out the various types of AD detection techniques with their major contributions. The performances of the most important AD detection techniques are compared and discussed according to the applied algorithms, approaches and databases (e.g. OASIS, ADNI and MIRIAD).
Current Medical Imaging Formerly Current Medical Imaging Reviews, 2020
Background: Skin cancer is one of the most common forms of cancers among humans. It can be classi... more Background: Skin cancer is one of the most common forms of cancers among humans. It can be classified as non-melanoma and melanoma. Although melanomas are less common than non-melanomas, the former is the most common cause of mortality. Therefore, it becomes necessary to develop a Computer-aided Diagnosis (CAD) aiming to detect this kind of lesion and enable the diagnosis of the disease at an early stage in order to augment the patient’s survival likelihood. Aims: This paper aims to develop a simple method capable of detecting and classifying skin lesions using dermoscopy images based on ABCD rules. Methods: The proposed approach follows four steps. 1) The preprocessing stage consists of filtering and contrast enhancing algorithms. 2) The segmentation stage aims at detecting the lesion. 3) The feature extraction stage based on the calculation of the four parameters which are asymmetry, border irregularity, color and diameter. 4) The classification stage based on the summation of the...
International Journal of Digital Signals and Smart Systems, 2018
2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP), 2020
Nowadays, high-resolution fingerprint images are more and more used in the fingerprint recognitio... more Nowadays, high-resolution fingerprint images are more and more used in the fingerprint recognition systems thanks to the recognition accuracy that they provide. Indeed, they offer more sufficient details such as sweat pores, ridges, contours, and other details. Pores have been adopted to be one of the brilliant nominees in improving the efficiency of automated fingerprint identification systems to maintain a high level of security. However, the geometric transformations, that occur during the acquisition phase, can cause several defects on the result of the matching process, hence they decline the accuracy of the recognition. To overcome this problem, alignment is often needed. This image pretreatment is classically based on complex geometric operations that are time-consuming. Otherwise, for pore matching, the majority of approaches are based only on pore coordinates. In this paper, we propose a novel pore matching method based, firstly, on only one of the singular points, namely t...
ISSN: 2186-1390 (Online) http://CenNSER.org/IJCVSP Abstract In recent years, there has been a fai... more ISSN: 2186-1390 (Online) http://CenNSER.org/IJCVSP Abstract In recent years, there has been a fairly rapid increase in the number of melanoma skin cancer patients. Melanoma, this deadliest form of skin cancer, must be diagnosed early for effective treatment. So, it is necessary to develop a computer-aided diagnostic system to facilitate its early detection. In this paper, the proposed work is based on a combination of a segmentation method and an analytical method and aims to improve these two methods in order to develop an interface that can assist dermatologists in the diagnostic phase. As a first step, a sequence of preprocessing is implemented to remove noise and unwanted structures from the image. Then, an automatic segmentation approach locates the skin lesion. The next step is feature extraction followed by the ABCD rule to make the diagnosis through the calculation of the TDV score. In this research, three diagnosis are used which are melanoma, suspicious, and benign skin le...
2016 13th International Multi-Conference on Systems, Signals & Devices (SSD), 2016
Advanced Methods for Human Biometrics
2019 16th International Multi-Conference on Systems, Signals & Devices (SSD)
International Journal of Computer Applications, Nov 10, 2010
Watershed algorithm as was introduced by Vincent and Soille is a segmentation algorithm based on ... more Watershed algorithm as was introduced by Vincent and Soille is a segmentation algorithm based on the inundation process of the image gradient which is observed as a relief. It aims at finding the peaks in the image gradient called watersheds and identifying them as the image contours. Due to its flexibility and rapidity, this algorithm is used in several applications. However, its main drawback is the over segmentation .In this paper, we improve this technique by introducing a histogram driven methodology. The developed architecture is applied on an empirical basis for research on image segmentation and boundary detection in order to be compared with other segmentation algorithms. The simulation results show that the performance of our algorithm is superior to the other segmentation techniques. Finally, the whole design is implemented on a Virtex 5 platform based on a codesign methodology leading to 147 MHz frequency and 76% of hardware resource occupation for an image of the size of 128*128.
International Image Processing, Applications and Systems Conference, 2014
In recent years, there has been a fairly rapid increase in the number of melanoma skin cancer pat... more In recent years, there has been a fairly rapid increase in the number of melanoma skin cancer patients. Despite the immense danger that this disease presents, the more early it is treated, the more rapidly, it is cured. So, it is necessary to develop computer-aided diagnosis system to facilitate early detection of this cancer. In this paper, we have tried to develop such system. As a first step, a sequence of preprocessing is implemented to remove noise and unwanted structures from the image. Then, an automatic segmentation approach locates the skin lesion. The next step is feature extraction followed by the ABCD rule to make the diagnosis by calculating the TDV score. In this research, three diagnosis are used which are melanoma, suspicious, and benign skin lesion. The experiment uses 40 images containing suspicious melanoma skin cancer. Based on the experiment, the accuracy of the system is 92% which reflects its fiability.