Pub Date : 2019-12-01DOI: 10.1109/ICTAACS48474.2019.8988129
Soumia Zertal, Zakaria Laboudi, Slimene Bechoua
The development of Cloud computing led to an increase in the number of services ready for use and therefore the number of consumers’ requests. Cloud providers advertise the description of their offered services in different formats on the Internet. This makes the discovery and selection of services more difficult for users. Thus, a uniform description of Cloud services would be needed. The aim of this study is to provide a new ontology for uniform description of Cloud services coming from heterogeneous sources. The proposed model takes into account the different relationships and dependencies between services across Cloud’s layers. These dependencies are represented by the different constraints of composition and deployment. To validate our proposal, qualitative and quantitative evaluations are conducted. The qualitative evaluation is carried out by making comparisons with both state-of-the-art works and the Bitnami platform according to some criteria. For the quantitative evaluation, comparisons are performed with the output results specified by users. Globally, the results are promising and encouraging.
{"title":"A Novel Ontology-based Approach for Describing Cloud Services","authors":"Soumia Zertal, Zakaria Laboudi, Slimene Bechoua","doi":"10.1109/ICTAACS48474.2019.8988129","DOIUrl":"https://doi.org/10.1109/ICTAACS48474.2019.8988129","url":null,"abstract":"The development of Cloud computing led to an increase in the number of services ready for use and therefore the number of consumers’ requests. Cloud providers advertise the description of their offered services in different formats on the Internet. This makes the discovery and selection of services more difficult for users. Thus, a uniform description of Cloud services would be needed. The aim of this study is to provide a new ontology for uniform description of Cloud services coming from heterogeneous sources. The proposed model takes into account the different relationships and dependencies between services across Cloud’s layers. These dependencies are represented by the different constraints of composition and deployment. To validate our proposal, qualitative and quantitative evaluations are conducted. The qualitative evaluation is carried out by making comparisons with both state-of-the-art works and the Bitnami platform according to some criteria. For the quantitative evaluation, comparisons are performed with the output results specified by users. Globally, the results are promising and encouraging.","PeriodicalId":406766,"journal":{"name":"2019 International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127245734","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 : 2019-12-01DOI: 10.1109/ICTAACS48474.2019.8988133
Abdelhakim Hannousse
Traditional development processes fail to be applied effectively to the development of component software. Some features in the design need to be (un)plugged dynamically to software systems and their implementations may require to crosscut the code of components. This is often not possible in component systems due to the nature of used components (black box, signed or encrypted components). In this paper we propose an appropriate process for the development of component software with explicit support for crosscutting and dynamic features. The proposed process covers all software lifecycle activities, follows a top-down approach and stimulates the reuse of pre-existing components. In the proposal, crosscutting and dynamic features are identified earlier in the process and modeled separately using aspect-orientation concepts for reusablity and maintainability purposes. The identification of crosscutting and dynamic features at early stages allows making proper design decisions to improve software modularity and reusability, manage feature conflicts and ensure better maintainability of component software. The proposed process is validated through modeling a case study.
{"title":"A development process for component software with crosscutting and dynamic features","authors":"Abdelhakim Hannousse","doi":"10.1109/ICTAACS48474.2019.8988133","DOIUrl":"https://doi.org/10.1109/ICTAACS48474.2019.8988133","url":null,"abstract":"Traditional development processes fail to be applied effectively to the development of component software. Some features in the design need to be (un)plugged dynamically to software systems and their implementations may require to crosscut the code of components. This is often not possible in component systems due to the nature of used components (black box, signed or encrypted components). In this paper we propose an appropriate process for the development of component software with explicit support for crosscutting and dynamic features. The proposed process covers all software lifecycle activities, follows a top-down approach and stimulates the reuse of pre-existing components. In the proposal, crosscutting and dynamic features are identified earlier in the process and modeled separately using aspect-orientation concepts for reusablity and maintainability purposes. The identification of crosscutting and dynamic features at early stages allows making proper design decisions to improve software modularity and reusability, manage feature conflicts and ensure better maintainability of component software. The proposed process is validated through modeling a case study.","PeriodicalId":406766,"journal":{"name":"2019 International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125030649","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 : 2019-12-01DOI: 10.1109/ICTAACS48474.2019.8988127
Abdeldjaouad Nusayr Medakene, Khadra Bouanane, Mohammed Abdelhadi Eddoud
The Paper-to-Reviewer Assignment Problem is a prevalent and challenging problem within the scientific community and scientific conferences. The large number of reviewers and submitted papers, as well as constraints on reviewers’ loads and papers’ coverage needs, make difficult and very tedious for the committee chair to manually assign submitted papers to suitable reviewers. Any automation of this task must tackle three main issues: modeling reviewers’ and papers’ profiles, estimating the relevance between a paper and a reviewer and finally finding an appropriate assignment.In this paper, we are interested in the two first issues. We propose to build the reviewers profiles on the basis of both pedagogical and research documents, then a formula that takes into account both topics similarity and common references is proposed. Experimental results compared to ground-truth values extracted from ICA2IT’19 data show a good performance of this approach.
{"title":"A New Approach for Computing the Matching Degree in the Paper-to-Reviewer Assignment Problem","authors":"Abdeldjaouad Nusayr Medakene, Khadra Bouanane, Mohammed Abdelhadi Eddoud","doi":"10.1109/ICTAACS48474.2019.8988127","DOIUrl":"https://doi.org/10.1109/ICTAACS48474.2019.8988127","url":null,"abstract":"The Paper-to-Reviewer Assignment Problem is a prevalent and challenging problem within the scientific community and scientific conferences. The large number of reviewers and submitted papers, as well as constraints on reviewers’ loads and papers’ coverage needs, make difficult and very tedious for the committee chair to manually assign submitted papers to suitable reviewers. Any automation of this task must tackle three main issues: modeling reviewers’ and papers’ profiles, estimating the relevance between a paper and a reviewer and finally finding an appropriate assignment.In this paper, we are interested in the two first issues. We propose to build the reviewers profiles on the basis of both pedagogical and research documents, then a formula that takes into account both topics similarity and common references is proposed. Experimental results compared to ground-truth values extracted from ICA2IT’19 data show a good performance of this approach.","PeriodicalId":406766,"journal":{"name":"2019 International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114513253","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 : 2019-12-01DOI: 10.1109/ICTAACS48474.2019.8988136
Soumia Bellaouar, M. Guerroumi, S. Moussaoui
In Vehicular Sensor Networks (VSNs), road safety applications are important to ensure the safety of motorists by broadcasting alert messages in this network. The dissemination process is the use of adaptive broadcasting algorithms that make efficient use of vehicular communications avoiding the problem of broadcast storms. Therefore, an effective warning message broadcast protocol should represent the appropriate transmission node for each message, maximizing the number of vehicles informed by the hazard of the situation, while simultaneously reducing the time needed to inform them and the amount of traffic generated in the wireless channel. In this work, we propose safety messages dissemination protocol based on QoS metrics as delay, link quality and flow for the choice of a reliable, fast and efficient broadcaster. Our experiments proved the efficiency of our proposal compared to other existing solutions in the literature and using the OMNETT ++ simulator.
{"title":"QoS based Safety Message Dissemination Protocol For VSN in Smart City","authors":"Soumia Bellaouar, M. Guerroumi, S. Moussaoui","doi":"10.1109/ICTAACS48474.2019.8988136","DOIUrl":"https://doi.org/10.1109/ICTAACS48474.2019.8988136","url":null,"abstract":"In Vehicular Sensor Networks (VSNs), road safety applications are important to ensure the safety of motorists by broadcasting alert messages in this network. The dissemination process is the use of adaptive broadcasting algorithms that make efficient use of vehicular communications avoiding the problem of broadcast storms. Therefore, an effective warning message broadcast protocol should represent the appropriate transmission node for each message, maximizing the number of vehicles informed by the hazard of the situation, while simultaneously reducing the time needed to inform them and the amount of traffic generated in the wireless channel. In this work, we propose safety messages dissemination protocol based on QoS metrics as delay, link quality and flow for the choice of a reliable, fast and efficient broadcaster. Our experiments proved the efficiency of our proposal compared to other existing solutions in the literature and using the OMNETT ++ simulator.","PeriodicalId":406766,"journal":{"name":"2019 International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126426096","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 : 2019-12-01DOI: 10.1109/ICTAACS48474.2019.8988124
Abdessamed Ouessai, M. Salem, Antonio M. Mora
Online planning is an important research area focusing on the problem of real-time decision making, using information extracted from the environment. The aim is to compute, at each decision point, the best decision possible that contributes to the realization of a fixed objective. Relevant application domains include robotics, control engineering and computer games. Real-time strategy (RTS) games pose considerable challenges to artificial intelligence techniques, due to their dynamic, complex and adversarial aspects, where online planning plays a prominent role. They also constitute an ideal research platform and test-bed for online planning. μRTS is an open-source AI research platform that features a minimalistic, yet complete RTS implementation, used by AI researchers for developing and testing intelligent RTS game-playing agents. The unique characteristics of μRTS helped for the emergence of interesting online adversarial planning techniques, dealing with multiple levels of abstraction. This paper presents the major μRTS online planning approaches to date, categorized by the degree of abstraction, in fully and partially observable environments.
{"title":"Online Adversarial Planning in μRTS : A Survey","authors":"Abdessamed Ouessai, M. Salem, Antonio M. Mora","doi":"10.1109/ICTAACS48474.2019.8988124","DOIUrl":"https://doi.org/10.1109/ICTAACS48474.2019.8988124","url":null,"abstract":"Online planning is an important research area focusing on the problem of real-time decision making, using information extracted from the environment. The aim is to compute, at each decision point, the best decision possible that contributes to the realization of a fixed objective. Relevant application domains include robotics, control engineering and computer games. Real-time strategy (RTS) games pose considerable challenges to artificial intelligence techniques, due to their dynamic, complex and adversarial aspects, where online planning plays a prominent role. They also constitute an ideal research platform and test-bed for online planning. μRTS is an open-source AI research platform that features a minimalistic, yet complete RTS implementation, used by AI researchers for developing and testing intelligent RTS game-playing agents. The unique characteristics of μRTS helped for the emergence of interesting online adversarial planning techniques, dealing with multiple levels of abstraction. This paper presents the major μRTS online planning approaches to date, categorized by the degree of abstraction, in fully and partially observable environments.","PeriodicalId":406766,"journal":{"name":"2019 International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114330592","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 : 2019-12-01DOI: 10.1109/ICTAACS48474.2019.8988132
Imene Mezenner, Samia Bouyakoub, F. M. Bouyakoub
Web of Things is a new paradigm, it constitutes the heart of a great research activity. However, most of this work does not take into account its temporal aspect, whereas it is a critical dimension directly related to customer satisfaction, optimization and is considered as a very effective strategy for cost reduction. For this matter, we propose a tool to edit and verify the time constraints added to an abstract BPEL specification. Furthermore, the editor allows the user to edit abstract BPEL specification that orchestrates Web services offered by objects connected to the Web of Things. Through the latter, the input specification is enriched with constraints and time attributes. Then, a temporal verification and validation process is applied to detect any temporal errors or conflicts.
{"title":"Towards a time editor for orchestrating connected objects in the Web of Things","authors":"Imene Mezenner, Samia Bouyakoub, F. M. Bouyakoub","doi":"10.1109/ICTAACS48474.2019.8988132","DOIUrl":"https://doi.org/10.1109/ICTAACS48474.2019.8988132","url":null,"abstract":"Web of Things is a new paradigm, it constitutes the heart of a great research activity. However, most of this work does not take into account its temporal aspect, whereas it is a critical dimension directly related to customer satisfaction, optimization and is considered as a very effective strategy for cost reduction. For this matter, we propose a tool to edit and verify the time constraints added to an abstract BPEL specification. Furthermore, the editor allows the user to edit abstract BPEL specification that orchestrates Web services offered by objects connected to the Web of Things. Through the latter, the input specification is enriched with constraints and time attributes. Then, a temporal verification and validation process is applied to detect any temporal errors or conflicts.","PeriodicalId":406766,"journal":{"name":"2019 International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131963162","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 : 2019-12-01DOI: 10.1109/ICTAACS48474.2019.8988138
Sarra Boukria, M. Guerroumi
Software Defined Network (SDN) is considered as the main component of the next generation network. Security, in this environment, has very challenges and risks. Attacking SDN controller or injecting false flow rules could affect the network and block the entire services. To enhance the SDN network security, we propose an anomaly-based intrusion detection system using deep learning approach. This solution aims to protect the communication channel between the SDN control layer and the SDN infrastructure layer against false data injection attack, and to detect any attempt of attack in SND southbound side. We analyze the flows that circulate in the SDN network, we use the logarithm function followed by the Min/Max scalar technique to normalize the flows features. For the flow classification, we exploit the Relu and Softmax functions. We test the proposed system with CICIDS2017 dataset on an experimental platform combining Mininet environment and ONOS controller. The evaluation results demonstrate the effectiveness and efficiency of the proposed security solution.
{"title":"Intrusion detection system for SDN network using deep learning approach","authors":"Sarra Boukria, M. Guerroumi","doi":"10.1109/ICTAACS48474.2019.8988138","DOIUrl":"https://doi.org/10.1109/ICTAACS48474.2019.8988138","url":null,"abstract":"Software Defined Network (SDN) is considered as the main component of the next generation network. Security, in this environment, has very challenges and risks. Attacking SDN controller or injecting false flow rules could affect the network and block the entire services. To enhance the SDN network security, we propose an anomaly-based intrusion detection system using deep learning approach. This solution aims to protect the communication channel between the SDN control layer and the SDN infrastructure layer against false data injection attack, and to detect any attempt of attack in SND southbound side. We analyze the flows that circulate in the SDN network, we use the logarithm function followed by the Min/Max scalar technique to normalize the flows features. For the flow classification, we exploit the Relu and Softmax functions. We test the proposed system with CICIDS2017 dataset on an experimental platform combining Mininet environment and ONOS controller. The evaluation results demonstrate the effectiveness and efficiency of the proposed security solution.","PeriodicalId":406766,"journal":{"name":"2019 International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS)","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116198024","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 : 2019-12-01DOI: 10.1109/ICTAACS48474.2019.8988121
M. E. Djebbar, Mustapha Réda Senouci, M. E. Boudaren
Compressive Sensing (CS) is a new sampling theory. It states that we can reconstruct a signal from very few measurements taken by projecting the signal rather than point sampling it. The signal can be reconstructed if it is sparse or sparse in some domain. This theory was employed recently in [1] to accelerate the rendering of ray-traced images, by rendering just a subset of pixels then applying the CS reconstruction to fill the missing ones using wavelet as a transform domain to seek the signal sparsity condition. In this paper, we use a learned dictionary rather than standard wavelet to better sparsify our images and hence improve the CS reconstruction. We also inject cheap geometry information (depth) to accurately reconstruct our images. Finally, we post-process our images by applying a modified version of the bilateral filter to improve the overall quality. Obtained results show a clear improvement in the quality of the image reconstruction while accelerating the rendering time as compared to [1].
{"title":"Geometry-aware Compressive Dictionary Learning based Rendering","authors":"M. E. Djebbar, Mustapha Réda Senouci, M. E. Boudaren","doi":"10.1109/ICTAACS48474.2019.8988121","DOIUrl":"https://doi.org/10.1109/ICTAACS48474.2019.8988121","url":null,"abstract":"Compressive Sensing (CS) is a new sampling theory. It states that we can reconstruct a signal from very few measurements taken by projecting the signal rather than point sampling it. The signal can be reconstructed if it is sparse or sparse in some domain. This theory was employed recently in [1] to accelerate the rendering of ray-traced images, by rendering just a subset of pixels then applying the CS reconstruction to fill the missing ones using wavelet as a transform domain to seek the signal sparsity condition. In this paper, we use a learned dictionary rather than standard wavelet to better sparsify our images and hence improve the CS reconstruction. We also inject cheap geometry information (depth) to accurately reconstruct our images. Finally, we post-process our images by applying a modified version of the bilateral filter to improve the overall quality. Obtained results show a clear improvement in the quality of the image reconstruction while accelerating the rendering time as compared to [1].","PeriodicalId":406766,"journal":{"name":"2019 International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130484915","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 : 2019-12-01DOI: 10.1109/ICTAACS48474.2019.8988134
Mustapha Salim Ghitri, Mohamed Messabihi, A. Benamar
Software systems are becoming more complex and their implementation requires more rigorous modeling approaches, for this reason the OMG (Object Management Group) has implemented the SysML standard to model complex systems. Sequence diagram is one of the fundamental diagrams of SysML because it allows behavioral specification of systems. However, SysML still has a lack of formal semantics following his semi-formal definition, which makes it impossible to directly apply the simulation and verification methods to these diagrams. The model transformation community offers several solutions to transform the SysML specification into formal methods in order to bridge the gap between them, this community is divided into two principal’s axes, the first ones working on the formalization of structural diagrams, and the others have worked on behavioral diagrams. Our work contributes to behavioral modeling and aims to combine all the highlights of the other approaches in a single framework for formal verification of SDs, using TAN and Uppaal model checker. The proposed approach has been tested through a case study of an interaction between ATM and Bank to prove their reliability.
{"title":"Tooled approach for formal verification of components interactions modeled in SysML","authors":"Mustapha Salim Ghitri, Mohamed Messabihi, A. Benamar","doi":"10.1109/ICTAACS48474.2019.8988134","DOIUrl":"https://doi.org/10.1109/ICTAACS48474.2019.8988134","url":null,"abstract":"Software systems are becoming more complex and their implementation requires more rigorous modeling approaches, for this reason the OMG (Object Management Group) has implemented the SysML standard to model complex systems. Sequence diagram is one of the fundamental diagrams of SysML because it allows behavioral specification of systems. However, SysML still has a lack of formal semantics following his semi-formal definition, which makes it impossible to directly apply the simulation and verification methods to these diagrams. The model transformation community offers several solutions to transform the SysML specification into formal methods in order to bridge the gap between them, this community is divided into two principal’s axes, the first ones working on the formalization of structural diagrams, and the others have worked on behavioral diagrams. Our work contributes to behavioral modeling and aims to combine all the highlights of the other approaches in a single framework for formal verification of SDs, using TAN and Uppaal model checker. The proposed approach has been tested through a case study of an interaction between ATM and Bank to prove their reliability.","PeriodicalId":406766,"journal":{"name":"2019 International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS)","volume":"329 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123661892","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 : 2019-12-01DOI: 10.1109/ICTAACS48474.2019.8988126
Cheribet Mohamed, M. Smaine
Image segmentation is a crucial step in any image analysis process. It consists in preparing the image to make it more usable by an automatic process, such interpreting and understanding its content. In this paper, we introduce a novel method for range image segmentation. The proposed method proceeds by adapting the principle of the Canny filter, commonly utilized for greyscale and colour images, to be applied for range images, where depths in these images should be differently handled. Instead of using raw image data, a new image of angles between normal vectors according some given directions is computed and then used to compute a new gradient image. Canny steps are then applied on the latter image, producing precise and well located edges. Experimentation on real images from the ABW database shows that edges in range images are correctly detected.
{"title":"Edge Detection in Range Images Using a Modified Canny Filter","authors":"Cheribet Mohamed, M. Smaine","doi":"10.1109/ICTAACS48474.2019.8988126","DOIUrl":"https://doi.org/10.1109/ICTAACS48474.2019.8988126","url":null,"abstract":"Image segmentation is a crucial step in any image analysis process. It consists in preparing the image to make it more usable by an automatic process, such interpreting and understanding its content. In this paper, we introduce a novel method for range image segmentation. The proposed method proceeds by adapting the principle of the Canny filter, commonly utilized for greyscale and colour images, to be applied for range images, where depths in these images should be differently handled. Instead of using raw image data, a new image of angles between normal vectors according some given directions is computed and then used to compute a new gradient image. Canny steps are then applied on the latter image, producing precise and well located edges. Experimentation on real images from the ABW database shows that edges in range images are correctly detected.","PeriodicalId":406766,"journal":{"name":"2019 International Conference on Theoretical and Applicative Aspects of Computer Science (ICTAACS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132712525","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：