Pub Date : 2020-09-01DOI: 10.1109/ATSIP49331.2020.9231908
Hajer Walhazi, Lamia Rzouga Haddada, A. Maalej, N. Amara
Latent fingerprints have played a critical role in identifying criminals and suspects. However, latent fingerprint identification is more complicated than plain and rolled fingerprints mainly due to poor ridge quality, complex background noise and overlapped structured noise in latent images. Subsequently, a latent-fingerprint image requires to be segmented to extract the fingerprint region from the background. The paper proposes a novel and efficient technique for latent-fingerprint segmentation. Our approach is based mainly on two fundamental ideas: i) applying the conversion from RGB color model to YCBCR color model and the Gaussian blur technique as a preprocessing before segmentation, and ii) using morphologic active contours without edges to define the fingerprint region based on an evolving contour that starts its rapid evolution in a stable state from the inside fingerprint. The technique is tested on two fingerprint databases: FVC2004 and NIST SD27. Our experimental results evaluate the miss-classified pixels and yield high segmentation accuracy.
{"title":"Preprocessing Latent-Fingerprint Images For Improving Segmentation Using Morphological Snakes","authors":"Hajer Walhazi, Lamia Rzouga Haddada, A. Maalej, N. Amara","doi":"10.1109/ATSIP49331.2020.9231908","DOIUrl":"https://doi.org/10.1109/ATSIP49331.2020.9231908","url":null,"abstract":"Latent fingerprints have played a critical role in identifying criminals and suspects. However, latent fingerprint identification is more complicated than plain and rolled fingerprints mainly due to poor ridge quality, complex background noise and overlapped structured noise in latent images. Subsequently, a latent-fingerprint image requires to be segmented to extract the fingerprint region from the background. The paper proposes a novel and efficient technique for latent-fingerprint segmentation. Our approach is based mainly on two fundamental ideas: i) applying the conversion from RGB color model to YCBCR color model and the Gaussian blur technique as a preprocessing before segmentation, and ii) using morphologic active contours without edges to define the fingerprint region based on an evolving contour that starts its rapid evolution in a stable state from the inside fingerprint. The technique is tested on two fingerprint databases: FVC2004 and NIST SD27. Our experimental results evaluate the miss-classified pixels and yield high segmentation accuracy.","PeriodicalId":384018,"journal":{"name":"2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129619606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ATSIP49331.2020.9231936
N. Abid, T. Ouni, M. Abid
Due to the dramatical grow of road transport, Advanced Driver Assistance Systems (ADAS) are being one of the most popular system. The main challenge of these systems is to improve driving safety and reduce accidents. Robust and effective vehicle detection is a critical step. However, vehicle detection meets many difficulties such as complex background, different size, model and orientations of vehicle. To solve this problem, this paper introduces an approach for traffic vehicle detection based on multi-scale covariance descriptor (MSCOV) for the image description and support vector machine classifier (SVM) for the data classification. This method is evaluated and compared to existing detection approach. The result of this approach outperforms existing vehicle detection system using the same dataset.
{"title":"Vehicle detection for intelligent traffic surveillance system","authors":"N. Abid, T. Ouni, M. Abid","doi":"10.1109/ATSIP49331.2020.9231936","DOIUrl":"https://doi.org/10.1109/ATSIP49331.2020.9231936","url":null,"abstract":"Due to the dramatical grow of road transport, Advanced Driver Assistance Systems (ADAS) are being one of the most popular system. The main challenge of these systems is to improve driving safety and reduce accidents. Robust and effective vehicle detection is a critical step. However, vehicle detection meets many difficulties such as complex background, different size, model and orientations of vehicle. To solve this problem, this paper introduces an approach for traffic vehicle detection based on multi-scale covariance descriptor (MSCOV) for the image description and support vector machine classifier (SVM) for the data classification. This method is evaluated and compared to existing detection approach. The result of this approach outperforms existing vehicle detection system using the same dataset.","PeriodicalId":384018,"journal":{"name":"2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121525529","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ATSIP49331.2020.9231681
Hiba Mzoughi, Ines Njeh, M. Slima, A. Hamida
Manual segmentation during clinical diagnosis, is considered as time-consuming and depend to the neuroradiologists level of expertise, however due to the large spatial and structural variability of brain tumors in shapes and sizes besides to the tumor sub-region voxels’high in-homogeneity could make a reliable and accurate and automated segmentation a challenging task. We proposed in this paper, an efficient and fully automatic deep-learning approach for Gliomas ‘brain tumor segmentation in multi-sequences Magnetic Resonance imaging (MRI). The proposed method is an optimization on the U-Net based on Fully Convolutional Networks (FCNs) called ‘U-Net DFCN’ in which we introduced the fusion of multiple MRI modalities to incorporate features from different scales, furthermore, to address the problem of data heterogeneity due to difference in acquisition algorithms and MRI scanner technologies, we proposed an intensity normalization followed by data augmentation techniques in the preprocessing step which though not conventional (usual) in deep FCN-based segmentation approaches. Our method was evaluated on the Multimodal Brain Tumor Image Segmentation (BRATS 2018) training and validation datasets, experimental resulted showed the good performance of the proposed approach outperforming several recent state-of-the-art segmentation methods, achieving a Dice score Coefficient (DSC) of 0.88, 0.87 and 0.81 for complete tumor, tumor-core and enhancing-tumor respectively.
{"title":"Glioblastomas brain Tumor Segmentation using Optimized U-Net based on Deep Fully Convolutional Networks (D-FCNs)","authors":"Hiba Mzoughi, Ines Njeh, M. Slima, A. Hamida","doi":"10.1109/ATSIP49331.2020.9231681","DOIUrl":"https://doi.org/10.1109/ATSIP49331.2020.9231681","url":null,"abstract":"Manual segmentation during clinical diagnosis, is considered as time-consuming and depend to the neuroradiologists level of expertise, however due to the large spatial and structural variability of brain tumors in shapes and sizes besides to the tumor sub-region voxels’high in-homogeneity could make a reliable and accurate and automated segmentation a challenging task. We proposed in this paper, an efficient and fully automatic deep-learning approach for Gliomas ‘brain tumor segmentation in multi-sequences Magnetic Resonance imaging (MRI). The proposed method is an optimization on the U-Net based on Fully Convolutional Networks (FCNs) called ‘U-Net DFCN’ in which we introduced the fusion of multiple MRI modalities to incorporate features from different scales, furthermore, to address the problem of data heterogeneity due to difference in acquisition algorithms and MRI scanner technologies, we proposed an intensity normalization followed by data augmentation techniques in the preprocessing step which though not conventional (usual) in deep FCN-based segmentation approaches. Our method was evaluated on the Multimodal Brain Tumor Image Segmentation (BRATS 2018) training and validation datasets, experimental resulted showed the good performance of the proposed approach outperforming several recent state-of-the-art segmentation methods, achieving a Dice score Coefficient (DSC) of 0.88, 0.87 and 0.81 for complete tumor, tumor-core and enhancing-tumor respectively.","PeriodicalId":384018,"journal":{"name":"2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115789607","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ATSIP49331.2020.9231799
Raoudha Rahmeni, A. B. Aicha, Y. B. Ayed
Now-a-days, the automatic speaker verification (ASV) systems are weak against attacks specially the voice conversion attacks and the speech synthesis attacks. To improve the robustness of the ASV systems, an anti-spoofing approach are developped to detect the spoofed speech from human speech. In this study, we focus on considering some acoustic features were proposed to differenciate spoofed speech from humain speech. We have used the proposed features with data from ASVspoof 2015 corpora. For the classification, we use Extreme learning machine (ELM) and Support Vector Machines (SVM) to obtain features and classified them to genuine or spoofed.
{"title":"Speech spoofing detection using SVM and ELM technique with acoustic features","authors":"Raoudha Rahmeni, A. B. Aicha, Y. B. Ayed","doi":"10.1109/ATSIP49331.2020.9231799","DOIUrl":"https://doi.org/10.1109/ATSIP49331.2020.9231799","url":null,"abstract":"Now-a-days, the automatic speaker verification (ASV) systems are weak against attacks specially the voice conversion attacks and the speech synthesis attacks. To improve the robustness of the ASV systems, an anti-spoofing approach are developped to detect the spoofed speech from human speech. In this study, we focus on considering some acoustic features were proposed to differenciate spoofed speech from humain speech. We have used the proposed features with data from ASVspoof 2015 corpora. For the classification, we use Extreme learning machine (ELM) and Support Vector Machines (SVM) to obtain features and classified them to genuine or spoofed.","PeriodicalId":384018,"journal":{"name":"2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132247397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ATSIP49331.2020.9231737
W. Mbarki, M. Bouchouicha, Sébastien Frizzi, Frederick Tshibasu, L. Farhat, M. Sayadi
We consider the problem of lower back pain and sciatica due to the loss of the disc’s height and the displacement of vertebrae. Our spine represents a combination of discs and vertebrae; between each two vertebrae, we can find an intervertebral disc. We will be interested in this paper to the lumbar discs, which are the most responsible for the lumbar herniation. Computer Aided Diagnosing (CAD) system for localizing herniated and normal intervertebral discs is a difficult task due to the method for treatment. Magnetic Resonance Imaging (MRI) are widely used to diagnose lower back pain and sciatica. We will be concentrated in this work on the T2-axial view MRI to successfully detect and classify the intervertebral discs which are the most important tasks to discuss in a system CAD. The originality of this paper consists in the development of a new method based on active contour and intuitionistic fuzzy C means (IFS) techniques to localize and extract disc from axial view MRI in order to find the type of herniated lumbar disc as foraminal, median or post lateral, we achieved 0.86 dice similarity index on 185 T2 axial MRI.
{"title":"Semi-automatic segmentation of intervertebral disc for diagnosing herniation using axial view MRI","authors":"W. Mbarki, M. Bouchouicha, Sébastien Frizzi, Frederick Tshibasu, L. Farhat, M. Sayadi","doi":"10.1109/ATSIP49331.2020.9231737","DOIUrl":"https://doi.org/10.1109/ATSIP49331.2020.9231737","url":null,"abstract":"We consider the problem of lower back pain and sciatica due to the loss of the disc’s height and the displacement of vertebrae. Our spine represents a combination of discs and vertebrae; between each two vertebrae, we can find an intervertebral disc. We will be interested in this paper to the lumbar discs, which are the most responsible for the lumbar herniation. Computer Aided Diagnosing (CAD) system for localizing herniated and normal intervertebral discs is a difficult task due to the method for treatment. Magnetic Resonance Imaging (MRI) are widely used to diagnose lower back pain and sciatica. We will be concentrated in this work on the T2-axial view MRI to successfully detect and classify the intervertebral discs which are the most important tasks to discuss in a system CAD. The originality of this paper consists in the development of a new method based on active contour and intuitionistic fuzzy C means (IFS) techniques to localize and extract disc from axial view MRI in order to find the type of herniated lumbar disc as foraminal, median or post lateral, we achieved 0.86 dice similarity index on 185 T2 axial MRI.","PeriodicalId":384018,"journal":{"name":"2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134005962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ATSIP49331.2020.9231697
R. Inoubli, Ali Ben Abbes, I. Farah, V. Singh, T. Tadesse, M. Sattari
Today, drought has become part of the identity as well as the fate of many countries. In fact, drought is considered among the most damaging natural disasters. The severe consequences resulting from drought affect the nature and society at different levels. Proper and efficient management is not possible without accurate prediction of drought and the identification of its various aspects. Thus, the existence of a considerable body of literature on drought monitoring. However, significant growth of remote sensing databases as will an increased amount of available data related to drought have been detected. Therefore, a more adequate approach should be developed. During the past decades, Data Mining (DM) methods have been introduced for drought monitoring. According to the best of our knowledge, a review of drought monitoring using remote sensing data and DM methods is lacking. Thereby, the purpose of this paper is to review and discuss the applications of DM methods. This paper consolidates the finding of drought monitoring, models, tasks, and methodologies.
{"title":"A review of drought monitoring using remote sensing and data mining methods","authors":"R. Inoubli, Ali Ben Abbes, I. Farah, V. Singh, T. Tadesse, M. Sattari","doi":"10.1109/ATSIP49331.2020.9231697","DOIUrl":"https://doi.org/10.1109/ATSIP49331.2020.9231697","url":null,"abstract":"Today, drought has become part of the identity as well as the fate of many countries. In fact, drought is considered among the most damaging natural disasters. The severe consequences resulting from drought affect the nature and society at different levels. Proper and efficient management is not possible without accurate prediction of drought and the identification of its various aspects. Thus, the existence of a considerable body of literature on drought monitoring. However, significant growth of remote sensing databases as will an increased amount of available data related to drought have been detected. Therefore, a more adequate approach should be developed. During the past decades, Data Mining (DM) methods have been introduced for drought monitoring. According to the best of our knowledge, a review of drought monitoring using remote sensing data and DM methods is lacking. Thereby, the purpose of this paper is to review and discuss the applications of DM methods. This paper consolidates the finding of drought monitoring, models, tasks, and methodologies.","PeriodicalId":384018,"journal":{"name":"2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131505555","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ATSIP49331.2020.9231586
Ayoub Mhaouch, W. Elhamzi, Mohamed Atri
The Piccolo block cipher is a lightweight block encryption for hardware use. Hardware devices are equipped with limited computation resources and small memory. In this paper, we propose an implementation to carry out through several trade-offs between area and speed. We implemented the Piccolo block cipher algorithm with 128-bit key in two different architectures on FPGA: the iterative and the 4-bit serial architectures. The proposed implementation was performed on Xilinx Spartan-3. The iterative implementation achieves 76% of resource utilization. This implementation takes 31 clock cycles to perform the encryption or decryption. So, it results in a throughput of 151.1 Mbps. The serial implementation was optimized in terms of area to reduce the cost. It achieves 54% of resource utilization and takes 496 clock cycles resulting in a throughput of 6.39 Mbps.
{"title":"Lightweight Hardware Architectures for the Piccolo Block Cipher in FPGA","authors":"Ayoub Mhaouch, W. Elhamzi, Mohamed Atri","doi":"10.1109/ATSIP49331.2020.9231586","DOIUrl":"https://doi.org/10.1109/ATSIP49331.2020.9231586","url":null,"abstract":"The Piccolo block cipher is a lightweight block encryption for hardware use. Hardware devices are equipped with limited computation resources and small memory. In this paper, we propose an implementation to carry out through several trade-offs between area and speed. We implemented the Piccolo block cipher algorithm with 128-bit key in two different architectures on FPGA: the iterative and the 4-bit serial architectures. The proposed implementation was performed on Xilinx Spartan-3. The iterative implementation achieves 76% of resource utilization. This implementation takes 31 clock cycles to perform the encryption or decryption. So, it results in a throughput of 151.1 Mbps. The serial implementation was optimized in terms of area to reduce the cost. It achieves 54% of resource utilization and takes 496 clock cycles resulting in a throughput of 6.39 Mbps.","PeriodicalId":384018,"journal":{"name":"2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114685986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ATSIP49331.2020.9231671
Marwa Elayni, F. Jemili, O. Korbaa, B. Solaiman
Nowadays, the volume of data considerably increasing, the data is exploding on the scale of the Exabyte and the Zettabyte at an exceptionally high rate. These can be characterized as big data. Hence, the security of the network, Internet, websites, Iot devices and the organizations, of this growth is indispensable. Detecting intrusions in such a big heterogeneous data environment is challenging. In this paper, we will present a new representation of data that can support this big heterogeneous environment. We will use three different datasets and propose an automatically matching algorithm that measures the semantic similarity between each two features existing on different datasets. Thereafter, an approximate vector is created that any type of coming data can be stored. With this representation, we can have subsequently an efficient intrusion detection system that can be able to acknowledge any instance of the existing data in the networks.
{"title":"A new features vector matching for big heterogeneous data in intrusion detection context","authors":"Marwa Elayni, F. Jemili, O. Korbaa, B. Solaiman","doi":"10.1109/ATSIP49331.2020.9231671","DOIUrl":"https://doi.org/10.1109/ATSIP49331.2020.9231671","url":null,"abstract":"Nowadays, the volume of data considerably increasing, the data is exploding on the scale of the Exabyte and the Zettabyte at an exceptionally high rate. These can be characterized as big data. Hence, the security of the network, Internet, websites, Iot devices and the organizations, of this growth is indispensable. Detecting intrusions in such a big heterogeneous data environment is challenging. In this paper, we will present a new representation of data that can support this big heterogeneous environment. We will use three different datasets and propose an automatically matching algorithm that measures the semantic similarity between each two features existing on different datasets. Thereafter, an approximate vector is created that any type of coming data can be stored. With this representation, we can have subsequently an efficient intrusion detection system that can be able to acknowledge any instance of the existing data in the networks.","PeriodicalId":384018,"journal":{"name":"2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125789171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ATSIP49331.2020.9231790
Besma Mnassri, M. Sahnoun, A. Hamida
Among neurological diseases, Multiple Sclerosis (MS) is the leading cause of disability in young adults. Several researches have been carried out to explore this disease and detect MS lesions in Magnetic Resonance (MR) images. In fact, lesions segmentation in MR images is very important for accurate diagnosis, adequate treatment and for monitoring the patient with MS. Spinal cord (SC) atrophy occurs at the onset of MS and there is a correlation between atrophy and disability development. Generally, Magnetic Resonance Imaging (MRI) is the most sensitive method, which allows the visualization of demyelination plaques and the quantification of spinal cord atrophy. Detection and quantification of SC atrophy in MRI images are the key to the assessment of the states of MS patients. In this paper, we present a comparative study between different spinal cord segmentation methods aiming to quantify spinal cord atrophy.
{"title":"Comparison Study for Spinal Cord Segmentation Methods aiming to detect SC Atrophy in MRI images: case of Multiple Sclerosis","authors":"Besma Mnassri, M. Sahnoun, A. Hamida","doi":"10.1109/ATSIP49331.2020.9231790","DOIUrl":"https://doi.org/10.1109/ATSIP49331.2020.9231790","url":null,"abstract":"Among neurological diseases, Multiple Sclerosis (MS) is the leading cause of disability in young adults. Several researches have been carried out to explore this disease and detect MS lesions in Magnetic Resonance (MR) images. In fact, lesions segmentation in MR images is very important for accurate diagnosis, adequate treatment and for monitoring the patient with MS. Spinal cord (SC) atrophy occurs at the onset of MS and there is a correlation between atrophy and disability development. Generally, Magnetic Resonance Imaging (MRI) is the most sensitive method, which allows the visualization of demyelination plaques and the quantification of spinal cord atrophy. Detection and quantification of SC atrophy in MRI images are the key to the assessment of the states of MS patients. In this paper, we present a comparative study between different spinal cord segmentation methods aiming to quantify spinal cord atrophy.","PeriodicalId":384018,"journal":{"name":"2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126998616","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-09-01DOI: 10.1109/ATSIP49331.2020.9231858
M. Sahnoun, F. Kallel, M. Dammak, O. Kammoun, C. Mhiri, K. B. Mahfoudh, A. Hamida
One of the most primary concern in Medical Image analyses is the detection of infected tumor in order to execute accurate treatment plan. In this paper, to segment lesions in Multiple Sclerosis (MS) pathology, we have investigated two preprocessing steps based on skull stripping (SS) and contrast enhancement (CE) which are two important steps for improving the quality rate of the MS lesion segmentation. After preprocessing step, a segmentation approach based on Expectation Maximization (EM) method have been applied to extract MS lesions. Qualitative and quantitative results of proposed method based on Dice score and Peak Signal to Noise Ratio was considered and tested on T2-F1air brain MR images.
{"title":"Contrast-Enhanced Image Analysis for MRI Based Multiple Sclerosis Lesion Segmentation","authors":"M. Sahnoun, F. Kallel, M. Dammak, O. Kammoun, C. Mhiri, K. B. Mahfoudh, A. Hamida","doi":"10.1109/ATSIP49331.2020.9231858","DOIUrl":"https://doi.org/10.1109/ATSIP49331.2020.9231858","url":null,"abstract":"One of the most primary concern in Medical Image analyses is the detection of infected tumor in order to execute accurate treatment plan. In this paper, to segment lesions in Multiple Sclerosis (MS) pathology, we have investigated two preprocessing steps based on skull stripping (SS) and contrast enhancement (CE) which are two important steps for improving the quality rate of the MS lesion segmentation. After preprocessing step, a segmentation approach based on Expectation Maximization (EM) method have been applied to extract MS lesions. Qualitative and quantitative results of proposed method based on Dice score and Peak Signal to Noise Ratio was considered and tested on T2-F1air brain MR images.","PeriodicalId":384018,"journal":{"name":"2020 5th International Conference on Advanced Technologies for Signal and Image Processing (ATSIP)","volume":"35 11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126948498","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：