Sahar Saleh - Academia.edu (original) (raw)
Papers by Sahar Saleh
Journal of geosciences and geomatics, Jan 23, 2015
Landslides in the Canyon slopes of the lower reach of Watier Valley represent one of the great ha... more Landslides in the Canyon slopes of the lower reach of Watier Valley represent one of the great hazards, which threaten the highway users that extends along the canyon bed between Newieba marine port and the rest of the country, for more than 50 km. In addition, the other human activities inside this reach are susceptible for the landslides hazard, especially, the electric, water networks and scattered Bedouins communities. This study tries to highlight the landslides hazard issue along the canyon reach. In order to analyze, evaluate and mitigate the hazard, a combination of data acquired, manipulated and implemented in the form of geo-informatics package. Fieldwork measurements for the canyon sides slope by using non-prism Total-Station and high-resolution quick-bird images were the main data sources. A GIS Model designed and applied for manipulating, processing and conducting these data. The application of this approach give the opportunity to create a Risk Zones Map for the canyon reach and revealed three main points: 1-Elevation, very steep slopes and rock structure are the main precondition factors and the earthquakes, while, the heavy rain-falls and seismic movements are the triggering main factors for that cause the landslides hazards. 2-The rock fall, toppling, rock sliding and debris flow are the main landslides movement forms. 3- The study suggested some appropriate mitigation methods to reduce the risk of landslide movements and rock stability along the canyon.
Lecture Notes in Computer Science, 2013
8th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2012r, 2012
ABSTRACT Due to the maturing of digital image processing techniques, there are many tools, which ... more ABSTRACT Due to the maturing of digital image processing techniques, there are many tools, which can edit an image easily without leaving obvious traces to the human eyes. So the authentication of digital images is an important issue in our life. In this paper, multi-resolution Weber law descriptors (WLD) based method that detects copy-move image forgery is introduced. The proposed multi-resolution WLD extracts the features from chrominance components, which can give more information that the human eyes cannot notice. A support vector machine is used for classification purpose. The experiments are conducted on a large image database designed for forgery detection. The experimental results show that the accuracy rate of the proposed method can reach up to 91 % with multi-resolution WLD descriptor on the chrominance space of the images.
— In this paper, a multi-resolution Weber law descriptors (WLD) based image forgery detection met... more — In this paper, a multi-resolution Weber law descriptors (WLD) based image forgery detection method is introduced. Due to the maturing of digital image processing techniques, there are many tools, which can edit an image easily without leaving obvious traces to the human eyes. So the authentication of digital images is an important issue in our life. The proposed multi-resolution WLD extracts the features from chrominance components, which can give more information that the human eyes cannot notice. A support vector machine is used for classification purpose. The experiments are conducted on a large image database designed for forgery detection. The experimental results show that the accuracy rate of the proposed method can reach up to 93.33 % with multi-resolution WLD descriptor on the chrominance space of the images.
Journal of the Physical Society of Japan
Proceedings of the 2015 International Conference on Recent Advances in Computer Systems, 2016
2014 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings, 2014
Journal of geosciences and geomatics, Jan 23, 2015
Landslides in the Canyon slopes of the lower reach of Watier Valley represent one of the great ha... more Landslides in the Canyon slopes of the lower reach of Watier Valley represent one of the great hazards, which threaten the highway users that extends along the canyon bed between Newieba marine port and the rest of the country, for more than 50 km. In addition, the other human activities inside this reach are susceptible for the landslides hazard, especially, the electric, water networks and scattered Bedouins communities. This study tries to highlight the landslides hazard issue along the canyon reach. In order to analyze, evaluate and mitigate the hazard, a combination of data acquired, manipulated and implemented in the form of geo-informatics package. Fieldwork measurements for the canyon sides slope by using non-prism Total-Station and high-resolution quick-bird images were the main data sources. A GIS Model designed and applied for manipulating, processing and conducting these data. The application of this approach give the opportunity to create a Risk Zones Map for the canyon reach and revealed three main points: 1-Elevation, very steep slopes and rock structure are the main precondition factors and the earthquakes, while, the heavy rain-falls and seismic movements are the triggering main factors for that cause the landslides hazards. 2-The rock fall, toppling, rock sliding and debris flow are the main landslides movement forms. 3- The study suggested some appropriate mitigation methods to reduce the risk of landslide movements and rock stability along the canyon.
Lecture Notes in Computer Science, 2013
8th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2012r, 2012
ABSTRACT Due to the maturing of digital image processing techniques, there are many tools, which ... more ABSTRACT Due to the maturing of digital image processing techniques, there are many tools, which can edit an image easily without leaving obvious traces to the human eyes. So the authentication of digital images is an important issue in our life. In this paper, multi-resolution Weber law descriptors (WLD) based method that detects copy-move image forgery is introduced. The proposed multi-resolution WLD extracts the features from chrominance components, which can give more information that the human eyes cannot notice. A support vector machine is used for classification purpose. The experiments are conducted on a large image database designed for forgery detection. The experimental results show that the accuracy rate of the proposed method can reach up to 91 % with multi-resolution WLD descriptor on the chrominance space of the images.
— In this paper, a multi-resolution Weber law descriptors (WLD) based image forgery detection met... more — In this paper, a multi-resolution Weber law descriptors (WLD) based image forgery detection method is introduced. Due to the maturing of digital image processing techniques, there are many tools, which can edit an image easily without leaving obvious traces to the human eyes. So the authentication of digital images is an important issue in our life. The proposed multi-resolution WLD extracts the features from chrominance components, which can give more information that the human eyes cannot notice. A support vector machine is used for classification purpose. The experiments are conducted on a large image database designed for forgery detection. The experimental results show that the accuracy rate of the proposed method can reach up to 93.33 % with multi-resolution WLD descriptor on the chrominance space of the images.
Journal of the Physical Society of Japan
Proceedings of the 2015 International Conference on Recent Advances in Computer Systems, 2016
2014 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings, 2014