Pub Date : 2013-11-01DOI: 10.1109/CINTI.2013.6705228
Jihene Boubaker, Zied Elouedi, E. Lefevre
Several rules were proposed in the context of evidence combination to deal with the conflict generated between the combined information sources. However, in the belief function framework, as far as we know only one rule exists for managing dependent bodies of evidence which is the cautious rule. Unfortunately, this rule does not give the conflict its initial alarm role and does not overcome the absorbing effect of the conflictual mass. The Combination With Adapted Conflict (CWAC) was proposed as a solution to this problem but only when dealing with independent information sources. Based on the cautious rule and inspired from the behaviour of CWAC towards the conflict, our contribution in this paper is to propose such a solution in the context of combining dependent sources.
{"title":"Conflict management with dependent information sources in the belief function framework","authors":"Jihene Boubaker, Zied Elouedi, E. Lefevre","doi":"10.1109/CINTI.2013.6705228","DOIUrl":"https://doi.org/10.1109/CINTI.2013.6705228","url":null,"abstract":"Several rules were proposed in the context of evidence combination to deal with the conflict generated between the combined information sources. However, in the belief function framework, as far as we know only one rule exists for managing dependent bodies of evidence which is the cautious rule. Unfortunately, this rule does not give the conflict its initial alarm role and does not overcome the absorbing effect of the conflictual mass. The Combination With Adapted Conflict (CWAC) was proposed as a solution to this problem but only when dealing with independent information sources. Based on the cautious rule and inspired from the behaviour of CWAC towards the conflict, our contribution in this paper is to propose such a solution in the context of combining dependent sources.","PeriodicalId":439949,"journal":{"name":"2013 IEEE 14th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126065841","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 : 2013-11-01DOI: 10.1109/CINTI.2013.6705189
V. M. Lupea
Multi-Value Neuron with a periodic activation function (MVN-P) represents an evolution of the Multi-Value Neuron (MVN) by introducing the concept of l-periodic occurrence of the possible output sectors. Increased efficiency was obtained based on this new approach and it was observed that the l-periodicity parameter has an important impact over the learning process. This paper presents a study of this impact in terms of learning efficiency (error rate and learning epochs).
{"title":"Multi-valued neuron with a periodic activation function — Influence of l-periodic parameter over the learning process","authors":"V. M. Lupea","doi":"10.1109/CINTI.2013.6705189","DOIUrl":"https://doi.org/10.1109/CINTI.2013.6705189","url":null,"abstract":"Multi-Value Neuron with a periodic activation function (MVN-P) represents an evolution of the Multi-Value Neuron (MVN) by introducing the concept of l-periodic occurrence of the possible output sectors. Increased efficiency was obtained based on this new approach and it was observed that the l-periodicity parameter has an important impact over the learning process. This paper presents a study of this impact in terms of learning efficiency (error rate and learning epochs).","PeriodicalId":439949,"journal":{"name":"2013 IEEE 14th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125547235","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 : 2013-11-01DOI: 10.1109/CINTI.2013.6705259
Michal Puheim, M. Bundzel, L. Madarász
In this paper we present the feed-forward neural network controller of robotic arm, which makes use of tracking method applied to stereo-vision cameras mounted on the head of the humanoid robot Nao, in order to touch the tracked object. The Tracking-Learning-Detection (TLD) method, which we use to detect and track the object, is known for its state-of-art performance and high robustness. This method was adjusted to be usable with a stereo-vision camera system, in order to provide 3D spatial coordinates of the object. These coordinates are used as the input for the feed-forward controller, which controls the arm of a humanoid robot. The goal of the controller is to move the hand of the robot to the object by setting arm joints into position corresponding to the object location. The controller is implemented as an artificial neural network and trained using the error back-propagation algorithm. The experiment, which demonstrates the proof of the concept, is also denoted in this paper.
{"title":"Forward control of robotic arm using the information from stereo-vision tracking system","authors":"Michal Puheim, M. Bundzel, L. Madarász","doi":"10.1109/CINTI.2013.6705259","DOIUrl":"https://doi.org/10.1109/CINTI.2013.6705259","url":null,"abstract":"In this paper we present the feed-forward neural network controller of robotic arm, which makes use of tracking method applied to stereo-vision cameras mounted on the head of the humanoid robot Nao, in order to touch the tracked object. The Tracking-Learning-Detection (TLD) method, which we use to detect and track the object, is known for its state-of-art performance and high robustness. This method was adjusted to be usable with a stereo-vision camera system, in order to provide 3D spatial coordinates of the object. These coordinates are used as the input for the feed-forward controller, which controls the arm of a humanoid robot. The goal of the controller is to move the hand of the robot to the object by setting arm joints into position corresponding to the object location. The controller is implemented as an artificial neural network and trained using the error back-propagation algorithm. The experiment, which demonstrates the proof of the concept, is also denoted in this paper.","PeriodicalId":439949,"journal":{"name":"2013 IEEE 14th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122106563","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 : 2013-11-01DOI: 10.1109/CINTI.2013.6705207
V. Jonas, M. Kozlovszky, B. Molnár
Both digital imaging, and image processing in certain areas of medical sciences is evolving quickly nowadays. Pathology is one of these fields. A digital slide is the digitized version of the good old glass slides used in pathology at least from the 1850s. These digital slides are possibly the near future of pathology in terms of repeatability of diagnosis, storage, and possibility of (tele)consultation. This paper targets the measurement of DNA content in the specimen. The significance of this measurement is, that there is a healthy ratio of cells being in the phase of mitosis (i.e. the phase of reproduction), in a living person, at a given moment. The increased ratio is a cancer marker. Consequently, the ratio is proportional to the tumor aggressivity level. Quickly growing tumor areas consist of quickly reproducing cells, so at a time more cells are reproducing, than in a healthy tissue. This measurement can probably be used to decide if the tissue (and patient) in question is healthy or has cancer. It is even possible that from the aggressivity of growth the type of cancer or the urgency of treatment can be presumed.
{"title":"Ploidy analysis on digital slides","authors":"V. Jonas, M. Kozlovszky, B. Molnár","doi":"10.1109/CINTI.2013.6705207","DOIUrl":"https://doi.org/10.1109/CINTI.2013.6705207","url":null,"abstract":"Both digital imaging, and image processing in certain areas of medical sciences is evolving quickly nowadays. Pathology is one of these fields. A digital slide is the digitized version of the good old glass slides used in pathology at least from the 1850s. These digital slides are possibly the near future of pathology in terms of repeatability of diagnosis, storage, and possibility of (tele)consultation. This paper targets the measurement of DNA content in the specimen. The significance of this measurement is, that there is a healthy ratio of cells being in the phase of mitosis (i.e. the phase of reproduction), in a living person, at a given moment. The increased ratio is a cancer marker. Consequently, the ratio is proportional to the tumor aggressivity level. Quickly growing tumor areas consist of quickly reproducing cells, so at a time more cells are reproducing, than in a healthy tissue. This measurement can probably be used to decide if the tissue (and patient) in question is healthy or has cancer. It is even possible that from the aggressivity of growth the type of cancer or the urgency of treatment can be presumed.","PeriodicalId":439949,"journal":{"name":"2013 IEEE 14th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129588979","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 : 2013-11-01DOI: 10.1109/CINTI.2013.6705254
Š. Korečko, Tomas Herich
Emotions are one of those phenomena which are rarely seen in connection with exact disciplines such as computer science or information technologies. However, with the widespread use of computer systems we see nowadays, the demand to include emotions to reasoning of artificial systems emerged and formalized emotional models have been created. In this paper we deal with an emotional engine we developed on the basis of the OCC model of emotions and its revised form. The emotional engine has been implemented as a conservative extension of the Jadex BDI agent platform. The paper describes basic concepts of the engine, namely a closed feedback loop between emotional and BDI part of a BDI agent and an emotional state representation.
{"title":"On some concepts of emotional engine for BDI agent system","authors":"Š. Korečko, Tomas Herich","doi":"10.1109/CINTI.2013.6705254","DOIUrl":"https://doi.org/10.1109/CINTI.2013.6705254","url":null,"abstract":"Emotions are one of those phenomena which are rarely seen in connection with exact disciplines such as computer science or information technologies. However, with the widespread use of computer systems we see nowadays, the demand to include emotions to reasoning of artificial systems emerged and formalized emotional models have been created. In this paper we deal with an emotional engine we developed on the basis of the OCC model of emotions and its revised form. The emotional engine has been implemented as a conservative extension of the Jadex BDI agent platform. The paper describes basic concepts of the engine, namely a closed feedback loop between emotional and BDI part of a BDI agent and an emotional state representation.","PeriodicalId":439949,"journal":{"name":"2013 IEEE 14th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129773299","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 : 2013-11-01DOI: 10.1109/CINTI.2013.6705243
D. Ganea, R. Bogdan, V. Ancușa, M. Popa
This paper describes a solution to automatically obtaining test scenarios in an automotive project concerning wheel pressure, acceleration and temperature controller emulators. A reliability assessment is performed so as to evidence the presented solution's improvement.
{"title":"A case study of automated testing implementation in the automotive industry","authors":"D. Ganea, R. Bogdan, V. Ancușa, M. Popa","doi":"10.1109/CINTI.2013.6705243","DOIUrl":"https://doi.org/10.1109/CINTI.2013.6705243","url":null,"abstract":"This paper describes a solution to automatically obtaining test scenarios in an automotive project concerning wheel pressure, acceleration and temperature controller emulators. A reliability assessment is performed so as to evidence the presented solution's improvement.","PeriodicalId":439949,"journal":{"name":"2013 IEEE 14th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126681450","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 : 2013-11-01DOI: 10.1109/CINTI.2013.6705194
Izumi Suzuki
The classifications when a target is not properly extracted due to improper segmentation include the multi-class case, in which the target contains objects belonging to different classes. In this paper, a method is applied to transform the multiclass case to a single-label classification by creating merged classes. To train merged classes, each feature must be defined in a very small domain, and the range of each feature must be binary, i.e., {0, 1}. It is not a contradiction to consider that the range of each feature is binary when the naïve Bayes classifier is employed in the bag-of-keypoints method. Thus, a fuzzy extension technique is proposed that enables us to consider the range of each feature as continuous, i.e., [0, 1]. By using the weighted average operation of the fuzzy vector, the ordinary Bayes classifier can be applied to solve multiclass cases. The experimental results verify that the classifier correctly detects 1) multi-class targets, and 2) targets in the incomplete case, in which the target is not properly extracted.
{"title":"Pattern classification using bag-of-keypoints for improper object extraction","authors":"Izumi Suzuki","doi":"10.1109/CINTI.2013.6705194","DOIUrl":"https://doi.org/10.1109/CINTI.2013.6705194","url":null,"abstract":"The classifications when a target is not properly extracted due to improper segmentation include the multi-class case, in which the target contains objects belonging to different classes. In this paper, a method is applied to transform the multiclass case to a single-label classification by creating merged classes. To train merged classes, each feature must be defined in a very small domain, and the range of each feature must be binary, i.e., {0, 1}. It is not a contradiction to consider that the range of each feature is binary when the naïve Bayes classifier is employed in the bag-of-keypoints method. Thus, a fuzzy extension technique is proposed that enables us to consider the range of each feature as continuous, i.e., [0, 1]. By using the weighted average operation of the fuzzy vector, the ordinary Bayes classifier can be applied to solve multiclass cases. The experimental results verify that the classifier correctly detects 1) multi-class targets, and 2) targets in the incomplete case, in which the target is not properly extracted.","PeriodicalId":439949,"journal":{"name":"2013 IEEE 14th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123345687","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 : 2013-11-01DOI: 10.1109/CINTI.2013.6705246
P. Lacko, Miroslav Ort, Michal Kyznansky, Adrian Kollar, Filip Pakan, M. Osvat, Jana Branisová
Simulation of human behavior in various situations is nowadays heavily used in miscellaneous research fields (e.g. emergency exits design, psychology, riot or humanitarian help simulation). The Holy Grail is to identify key elements of human beings that drive our behavior and be able to sufficiently simulate them and replicate in artificial computer environment. This work is focused on riot simulation in city conditions with multiple defense components. Behavior of agents/protesters is driven by PECS (Physical Conditions, Emotional State, Cognitive Capabilities and Social Status) psychological model and movement is adjusted by sophisticated collision avoidance system RVO2 (Reciprocal Collision Avoidance for RealTime Multi-Agent Simulation). Created simulation proposes several scenarios that resemble real demonstrations and can be parameterized for further studies.
在各种情况下的人类行为模拟如今被大量用于各种研究领域(例如紧急出口设计，心理学，暴乱或人道主义援助模拟)。“圣杯”是找出驱动人类行为的关键因素，并能够充分模拟它们，并在人工计算机环境中进行复制。这项工作的重点是在具有多个防御组件的城市条件下进行暴乱模拟。主体/抗议者的行为由PECS (Physical Conditions, Emotional State, Cognitive Capabilities and Social Status)心理模型驱动，运动由复杂的碰撞避免系统RVO2 (Reciprocal collision avoidance for RealTime Multi-Agent Simulation)调节。创建的模拟提出了几个类似于真实演示的场景，可以参数化以供进一步研究。
{"title":"Riot simulation in urban areas","authors":"P. Lacko, Miroslav Ort, Michal Kyznansky, Adrian Kollar, Filip Pakan, M. Osvat, Jana Branisová","doi":"10.1109/CINTI.2013.6705246","DOIUrl":"https://doi.org/10.1109/CINTI.2013.6705246","url":null,"abstract":"Simulation of human behavior in various situations is nowadays heavily used in miscellaneous research fields (e.g. emergency exits design, psychology, riot or humanitarian help simulation). The Holy Grail is to identify key elements of human beings that drive our behavior and be able to sufficiently simulate them and replicate in artificial computer environment. This work is focused on riot simulation in city conditions with multiple defense components. Behavior of agents/protesters is driven by PECS (Physical Conditions, Emotional State, Cognitive Capabilities and Social Status) psychological model and movement is adjusted by sophisticated collision avoidance system RVO2 (Reciprocal Collision Avoidance for RealTime Multi-Agent Simulation). Created simulation proposes several scenarios that resemble real demonstrations and can be parameterized for further studies.","PeriodicalId":439949,"journal":{"name":"2013 IEEE 14th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121145198","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 : 2013-11-01DOI: 10.1109/CINTI.2013.6705234
Ugur Çekmez, Mustafa Ozsiginan, O. K. Sahingoz
The vehicle routing problem (VRP) is one of the most challenging combinatorial optimization problems, which has been studied for several decades. The number of solutions for VRP increases exponentially while the number of points, which must be visited increases. There are 3.0×10^64 different solutions for 50 visiting points in a direct solution, and it is practically impossible to try out all these permutations. Some approaches like evolutionary algorithms allow finding feasible solutions in an acceptable time. However, if the number of visiting points increases, these algorithms require high performance computing, and they remain insufficient for finding a feasible solution quickly. Graphics Processing Units (GPUs) have tremendous computational power by allowing parallel processing over lots of computing grids, and they can lead to significant performance gains compared with typical CPU implementations. In this paper, it is aimed to present efficient implementation of Genetic Algorithm, which is an evolutionary algorithm that is inspired by processes observed in the biological evolution of living organisms to find approximate solutions for optimization problems such as Traveling Salesman Problem, on GPU. A 1-Thread in 1-Position (1T1P) approach is developed to improve the performance through maximizing efficiency, which then yielded a significant acceleration by using GPUs. Performance of implemented system is measured with the different parameters and the corresponding CPU implementation.
{"title":"Adapting the GA approach to solve Traveling Salesman Problems on CUDA architecture","authors":"Ugur Çekmez, Mustafa Ozsiginan, O. K. Sahingoz","doi":"10.1109/CINTI.2013.6705234","DOIUrl":"https://doi.org/10.1109/CINTI.2013.6705234","url":null,"abstract":"The vehicle routing problem (VRP) is one of the most challenging combinatorial optimization problems, which has been studied for several decades. The number of solutions for VRP increases exponentially while the number of points, which must be visited increases. There are 3.0×10^64 different solutions for 50 visiting points in a direct solution, and it is practically impossible to try out all these permutations. Some approaches like evolutionary algorithms allow finding feasible solutions in an acceptable time. However, if the number of visiting points increases, these algorithms require high performance computing, and they remain insufficient for finding a feasible solution quickly. Graphics Processing Units (GPUs) have tremendous computational power by allowing parallel processing over lots of computing grids, and they can lead to significant performance gains compared with typical CPU implementations. In this paper, it is aimed to present efficient implementation of Genetic Algorithm, which is an evolutionary algorithm that is inspired by processes observed in the biological evolution of living organisms to find approximate solutions for optimization problems such as Traveling Salesman Problem, on GPU. A 1-Thread in 1-Position (1T1P) approach is developed to improve the performance through maximizing efficiency, which then yielded a significant acceleration by using GPUs. Performance of implemented system is measured with the different parameters and the corresponding CPU implementation.","PeriodicalId":439949,"journal":{"name":"2013 IEEE 14th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"202 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127581270","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 : 2013-11-01DOI: 10.1109/CINTI.2013.6705168
T. Tóth, Viktória Rajťúková, J. Živčák
Various types of 3D scanners are used for digitalization of objects. These are mostly different types of optical or laser 3D scanners. The presented article deals with the comparison of the Steinbichler Comet L3D optical scanner and the Creaform HandyScan EXAscan laser scanner. For scanners comparison, a specimen was designed that satisfies scanning criteria for both types of the 3D scanners; i.e. it does not contain complicated shapes or parts that are not possible to scan using the chosen technologies (deep apertures with a small diameter, corners, etc.). The designed specimen was scanned 3 times using both types of 3D scanners. The obtained images were then cleaned (elimination of unwanted artifacts) and exported to STL files. The data was evaluated in VolumeGraphics VGStudio MAX 2.2. In the comparison selected dimensions, shape and orientational deviations were evaluated and the scanned image obtained was compared to the CAD model.
各种类型的三维扫描仪用于物体的数字化。这些大多是不同类型的光学或激光3D扫描仪。本文对Steinbichler Comet L3D光学扫描仪和Creaform HandyScan EXAscan激光扫描仪进行了比较。为了对扫描仪进行比较，设计了满足两种类型3D扫描仪扫描标准的样品;也就是说，它不包含使用所选技术无法扫描的复杂形状或部件(直径小的深孔，角落等)。设计的样品使用两种类型的3D扫描仪扫描3次。然后清理获得的图像(消除不需要的工件)并导出到STL文件。在VolumeGraphics VGStudio MAX 2.2中对数据进行评估。在比较中，评估了所选尺寸、形状和方向的偏差，并将获得的扫描图像与CAD模型进行了比较。
{"title":"Comparison of optical and laser 3D scanners","authors":"T. Tóth, Viktória Rajťúková, J. Živčák","doi":"10.1109/CINTI.2013.6705168","DOIUrl":"https://doi.org/10.1109/CINTI.2013.6705168","url":null,"abstract":"Various types of 3D scanners are used for digitalization of objects. These are mostly different types of optical or laser 3D scanners. The presented article deals with the comparison of the Steinbichler Comet L3D optical scanner and the Creaform HandyScan EXAscan laser scanner. For scanners comparison, a specimen was designed that satisfies scanning criteria for both types of the 3D scanners; i.e. it does not contain complicated shapes or parts that are not possible to scan using the chosen technologies (deep apertures with a small diameter, corners, etc.). The designed specimen was scanned 3 times using both types of 3D scanners. The obtained images were then cleaned (elimination of unwanted artifacts) and exported to STL files. The data was evaluated in VolumeGraphics VGStudio MAX 2.2. In the comparison selected dimensions, shape and orientational deviations were evaluated and the scanned image obtained was compared to the CAD model.","PeriodicalId":439949,"journal":{"name":"2013 IEEE 14th International Symposium on Computational Intelligence and Informatics (CINTI)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126268097","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：