Pub Date : 2017-12-04DOI: 10.1109/ICACCI.2017.8126121
Balaji Raman Katta, Irfan Madani
Aircraft need to be separated from other aircraft by either a minimum vertical distance of 1000ft or by a minimum horizontal distance of 5NM to avoid mid-air collisions. Traffic Alert and Collision Avoidance System (TCAS) work well as a tactical safety backups to avoid collision, but cannot perform separation assurance. This paper presents the design aspects of system that would predict separation infringement and provide flight crew with necessary guidance for maintaining separation. This paper discusses formulation of system function based on ADS-B, mathematical models, simulation and results. A system model has been implemented in MATLAB and various encounters with different speed ratios at various conflict angles has been fed as input to system model with a goal of avoidance and recovery to original waypoint. Both Heading and Speed maneuvers are evaluated and results are presented. The required strength of resolution maneuver as a function of conflict geometry is studied and automatic maneuver selection function is implemented in system model and maneuver selection function is evaluated with discussion of results.
飞机需要与其他飞机保持至少1000英尺的垂直距离或至少5海里的水平距离，以避免空中碰撞。交通预警与避碰系统(Traffic Alert and Collision Avoidance System, TCAS)作为一种战术安全备份，可以很好地避免碰撞，但不能提供分离保障。本文介绍了隔离侵权预警系统的设计，为机组人员维护隔离提供必要的指导。本文讨论了基于ADS-B的系统功能的表述、数学模型、仿真和结果。在MATLAB中实现了系统模型，将不同碰撞角度下不同速比的各种碰撞作为系统模型的输入，以避免并恢复到原始航路点为目标。对航向机动和速度机动进行了评价，并给出了结果。研究了解决机动所需强度作为冲突几何的函数，在系统模型中实现了自动机动选择函数，并对机动选择函数进行了评价，讨论了结果。
{"title":"Traffic avoidance and separation system","authors":"Balaji Raman Katta, Irfan Madani","doi":"10.1109/ICACCI.2017.8126121","DOIUrl":"https://doi.org/10.1109/ICACCI.2017.8126121","url":null,"abstract":"Aircraft need to be separated from other aircraft by either a minimum vertical distance of 1000ft or by a minimum horizontal distance of 5NM to avoid mid-air collisions. Traffic Alert and Collision Avoidance System (TCAS) work well as a tactical safety backups to avoid collision, but cannot perform separation assurance. This paper presents the design aspects of system that would predict separation infringement and provide flight crew with necessary guidance for maintaining separation. This paper discusses formulation of system function based on ADS-B, mathematical models, simulation and results. A system model has been implemented in MATLAB and various encounters with different speed ratios at various conflict angles has been fed as input to system model with a goal of avoidance and recovery to original waypoint. Both Heading and Speed maneuvers are evaluated and results are presented. The required strength of resolution maneuver as a function of conflict geometry is studied and automatic maneuver selection function is implemented in system model and maneuver selection function is evaluated with discussion of results.","PeriodicalId":437297,"journal":{"name":"2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130456049","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 : 2017-09-01DOI: 10.1109/ICACCI.2017.8125973
Kamalesh Karmakar, Sunirmal Khatua, R. Das
Placement of Virtual Machines (VMs) on physical servers is a challenging area of research and has received considerable interest among researchers in the field of Cloud Computing. This paper focuses on the reduction of cost in placing a set of VMs considering the constraints of available cloud resources. We have proposed a polynomial time heuristic to place VMs satisfying the constraints with the objective of minimizing the number of active servers. When the number of VMs and servers are small, one restricted case of the problem can be solved optimally by forming an Integer Programming Problem (IPP). The performance of the proposed heuristics are evaluated considering different types of scenarios and it is observed that the maximum or average number of servers required by one of the proposed heuristics is nearly equal to that given by IPP based solution.
{"title":"Efficient virtual machine placement in cloud environment","authors":"Kamalesh Karmakar, Sunirmal Khatua, R. Das","doi":"10.1109/ICACCI.2017.8125973","DOIUrl":"https://doi.org/10.1109/ICACCI.2017.8125973","url":null,"abstract":"Placement of Virtual Machines (VMs) on physical servers is a challenging area of research and has received considerable interest among researchers in the field of Cloud Computing. This paper focuses on the reduction of cost in placing a set of VMs considering the constraints of available cloud resources. We have proposed a polynomial time heuristic to place VMs satisfying the constraints with the objective of minimizing the number of active servers. When the number of VMs and servers are small, one restricted case of the problem can be solved optimally by forming an Integer Programming Problem (IPP). The performance of the proposed heuristics are evaluated considering different types of scenarios and it is observed that the maximum or average number of servers required by one of the proposed heuristics is nearly equal to that given by IPP based solution.","PeriodicalId":437297,"journal":{"name":"2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115168039","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 : 2017-09-01DOI: 10.1109/ICACCI.2017.8126130
Naba Krushna Sabat, B. Rao, B. Patnaik
This paper introduces a method of reducing the non-linear effect known as four waves mixing in fiber optic communication system. The four wave mixing effect has been studied in OPTISYSTEM 14.2 environment. We have proposed a method for reducing the FWM effect using dual port dual drive Mach-Zehnder modulator and circular polarization. The system is designed, simulated and analyzed for a single mode optical fiber of length 100 km, and bit rate of 10 Gbps with two channels having channel spacing of 0.5 nm. The performance of the system has been improved as compared with the existing system (which uses Mach-Zehnder modulator) in terms of reducing the FWM effect in fiber optic communication system.
{"title":"Reduction of fwm effect in fiber optic communication system by using dpddmz and circular polarization","authors":"Naba Krushna Sabat, B. Rao, B. Patnaik","doi":"10.1109/ICACCI.2017.8126130","DOIUrl":"https://doi.org/10.1109/ICACCI.2017.8126130","url":null,"abstract":"This paper introduces a method of reducing the non-linear effect known as four waves mixing in fiber optic communication system. The four wave mixing effect has been studied in OPTISYSTEM 14.2 environment. We have proposed a method for reducing the FWM effect using dual port dual drive Mach-Zehnder modulator and circular polarization. The system is designed, simulated and analyzed for a single mode optical fiber of length 100 km, and bit rate of 10 Gbps with two channels having channel spacing of 0.5 nm. The performance of the system has been improved as compared with the existing system (which uses Mach-Zehnder modulator) in terms of reducing the FWM effect in fiber optic communication system.","PeriodicalId":437297,"journal":{"name":"2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115705947","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 : 2017-09-01DOI: 10.1109/ICACCI.2017.8126030
S. Sushant, S. Anand, T. James, V. Aravind, Gayathri Narayanan
An Unmanned Aerial Vehicle (UAV) has several applications in the modern scenario. It can be used for capturing live video footages for sports like cricket or football or even commercial applications. It can even be used for procuring images at places where human intervention is difficult and so, can find wide application in disaster management. This paper mainly deals with the localization of a UAV and how it can be applied for detecting cracks in a railway track using the concepts of image processing. The algorithm used for localizing the UAV is called Monte Carlo or Particle filter localization algorithm. The video taken from the UAV is processed by further extracting image frames and analyzing each of these image frames for detection of cracks along railway line. A real-time implementation of our proposed method can significantly reduce physical labor involved in crack detection and also reduces the risk of accidents.
{"title":"Localization of an unmanned aerial vehicle for crack detection in railway tracks","authors":"S. Sushant, S. Anand, T. James, V. Aravind, Gayathri Narayanan","doi":"10.1109/ICACCI.2017.8126030","DOIUrl":"https://doi.org/10.1109/ICACCI.2017.8126030","url":null,"abstract":"An Unmanned Aerial Vehicle (UAV) has several applications in the modern scenario. It can be used for capturing live video footages for sports like cricket or football or even commercial applications. It can even be used for procuring images at places where human intervention is difficult and so, can find wide application in disaster management. This paper mainly deals with the localization of a UAV and how it can be applied for detecting cracks in a railway track using the concepts of image processing. The algorithm used for localizing the UAV is called Monte Carlo or Particle filter localization algorithm. The video taken from the UAV is processed by further extracting image frames and analyzing each of these image frames for detection of cracks along railway line. A real-time implementation of our proposed method can significantly reduce physical labor involved in crack detection and also reduces the risk of accidents.","PeriodicalId":437297,"journal":{"name":"2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI)","volume":"144 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127302775","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 : 2017-09-01DOI: 10.1109/ICACCI.2017.8125866
P. Sudev, J. P. Anita, P. Sudheesh
In wind turbine, the third power of the wind speed is directly proportional to the power produced due to the wind. Hence the power produced increases with respect to the wind speed. By using an appropriate generator torque, the system can optimize the conversion of wind energy. During high wind speeds, wind turbine power has to be constrained. Approximating the system states by processing the input data is called as state estimation. We are using this state estimation for the estimation of wind turbine parameters. The wind speeds are the most mandatory among them all to be estimated. For a set of conditions, state estimation techniques can be used to track the wind turbine parameters. A nonlinear state estimator, particle filter, is introduced and explained. The particle filter is implemented for estimating the wind turbine parameters: tower top displacement, tower Stop velocity and the rotor speed. The resultant performance is tested and verified with the simulation results. Particle filter is the most popular approach. The main reason why particle filters are so accepted is that it is very flexible and adaptive.
{"title":"Nonlinear state estimation of wind turbine","authors":"P. Sudev, J. P. Anita, P. Sudheesh","doi":"10.1109/ICACCI.2017.8125866","DOIUrl":"https://doi.org/10.1109/ICACCI.2017.8125866","url":null,"abstract":"In wind turbine, the third power of the wind speed is directly proportional to the power produced due to the wind. Hence the power produced increases with respect to the wind speed. By using an appropriate generator torque, the system can optimize the conversion of wind energy. During high wind speeds, wind turbine power has to be constrained. Approximating the system states by processing the input data is called as state estimation. We are using this state estimation for the estimation of wind turbine parameters. The wind speeds are the most mandatory among them all to be estimated. For a set of conditions, state estimation techniques can be used to track the wind turbine parameters. A nonlinear state estimator, particle filter, is introduced and explained. The particle filter is implemented for estimating the wind turbine parameters: tower top displacement, tower Stop velocity and the rotor speed. The resultant performance is tested and verified with the simulation results. Particle filter is the most popular approach. The main reason why particle filters are so accepted is that it is very flexible and adaptive.","PeriodicalId":437297,"journal":{"name":"2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127320043","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 : 2017-09-01DOI: 10.1109/ICACCI.2017.8126208
G. Rajendran, P. Poornachandran, Bhadrachalam Chitturi
The process of identifying and assigning the relationship between two bodies of text is referred to as stance classification. Given a headline and the corresponding body they are compared and their relationship is classified into one of the following two classes — unrelated or related where related is further divided into agree, disagree and discuss. In this article, data is collected from news articles which contains headlines and bodies. We call a headline and the corresponding body as a pair. Deep learning models are applied to these pairs. We applied bidirectional Long Short-Term Memory (LSTM) model and multi-layered perceptron (MLP) model and obtained accuracies of 83.5% and 78% respectively. The accuracy calculation is based on a weighted scheme. The correctly classified unrelated pair has a score of 0.25. A pair correctly classified as related yields a score of one only if the the sub-relationships of agree, disagree and discuss are correctly identified; otherwise, the score is 0.25.
{"title":"Deep learning model on stance classification","authors":"G. Rajendran, P. Poornachandran, Bhadrachalam Chitturi","doi":"10.1109/ICACCI.2017.8126208","DOIUrl":"https://doi.org/10.1109/ICACCI.2017.8126208","url":null,"abstract":"The process of identifying and assigning the relationship between two bodies of text is referred to as stance classification. Given a headline and the corresponding body they are compared and their relationship is classified into one of the following two classes — unrelated or related where related is further divided into agree, disagree and discuss. In this article, data is collected from news articles which contains headlines and bodies. We call a headline and the corresponding body as a pair. Deep learning models are applied to these pairs. We applied bidirectional Long Short-Term Memory (LSTM) model and multi-layered perceptron (MLP) model and obtained accuracies of 83.5% and 78% respectively. The accuracy calculation is based on a weighted scheme. The correctly classified unrelated pair has a score of 0.25. A pair correctly classified as related yields a score of one only if the the sub-relationships of agree, disagree and discuss are correctly identified; otherwise, the score is 0.25.","PeriodicalId":437297,"journal":{"name":"2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126006345","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 : 2017-09-01DOI: 10.1109/ICACCI.2017.8126158
N. Anilkumar, Deepa Gupta, S. Khare, D. Gopalkrishna, Amalendu Jyotishi
Good nutrition is an essential component of life. Undernutrition is the root cause of death of over 3.5 million children under the age of five in India. To address this issue of malnutrition, though overarching national policy is desirable, it may not be effective if the root cause of malnutrition varies across regions of the country. In this context, the attempt made in this paper is two-fold. First, weather the Indian States can be clustered on four anthropometric parameters of malnutrition. Second, whether the clusters formed thus, exhibit different explaining factors for malnutrition. The Indian-DHS (Demographic Health Survey) Data is used for the analysis. The results thus arrived would help policy-makers to have a targeted approach to malnutrition in different clusters of states.
{"title":"Characteristics and causes of malnutrition across Indian states: A cluster analysis based on Indian demographic and health survey data","authors":"N. Anilkumar, Deepa Gupta, S. Khare, D. Gopalkrishna, Amalendu Jyotishi","doi":"10.1109/ICACCI.2017.8126158","DOIUrl":"https://doi.org/10.1109/ICACCI.2017.8126158","url":null,"abstract":"Good nutrition is an essential component of life. Undernutrition is the root cause of death of over 3.5 million children under the age of five in India. To address this issue of malnutrition, though overarching national policy is desirable, it may not be effective if the root cause of malnutrition varies across regions of the country. In this context, the attempt made in this paper is two-fold. First, weather the Indian States can be clustered on four anthropometric parameters of malnutrition. Second, whether the clusters formed thus, exhibit different explaining factors for malnutrition. The Indian-DHS (Demographic Health Survey) Data is used for the analysis. The results thus arrived would help policy-makers to have a targeted approach to malnutrition in different clusters of states.","PeriodicalId":437297,"journal":{"name":"2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI)","volume":"7 12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123416871","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 : 2017-09-01DOI: 10.1109/ICACCI.2017.8125862
Namita Arya, A. Singh
The integration level in today's word is continuously increasing in VLSI chips. So that complexity of testing is a major challenge. That is because the internal chip modules have become increasingly midcult to access. There is a significant amount of the testing cost as compared to the total manufacturing cost. Hence there is a necessity to reduce the testing cost. The main factor is the time required to test the circuitry that has the biggest impact on testing cost of a chip. This time can be decreased by reducing the number of tests required to test the chip. So, we simply need to devise a test set that should be small in size. There is one way to generate a small test set is to compact a large test set parameters. The main drawback of the compaction results on the quality of the original test set. This aspect of compaction has motivated the work presented here with some methods of fault detection and avoidance techniques to test the circuit for a fault-free environment.
{"title":"Defect and fault detection in combinational circuits: Techniques and analysis","authors":"Namita Arya, A. Singh","doi":"10.1109/ICACCI.2017.8125862","DOIUrl":"https://doi.org/10.1109/ICACCI.2017.8125862","url":null,"abstract":"The integration level in today's word is continuously increasing in VLSI chips. So that complexity of testing is a major challenge. That is because the internal chip modules have become increasingly midcult to access. There is a significant amount of the testing cost as compared to the total manufacturing cost. Hence there is a necessity to reduce the testing cost. The main factor is the time required to test the circuitry that has the biggest impact on testing cost of a chip. This time can be decreased by reducing the number of tests required to test the chip. So, we simply need to devise a test set that should be small in size. There is one way to generate a small test set is to compact a large test set parameters. The main drawback of the compaction results on the quality of the original test set. This aspect of compaction has motivated the work presented here with some methods of fault detection and avoidance techniques to test the circuit for a fault-free environment.","PeriodicalId":437297,"journal":{"name":"2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123660622","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 : 2017-09-01DOI: 10.1109/ICACCI.2017.8125813
Gulshakh Kaur, P. Saini
In the Linked Data context, identity link is one of the most important semantic links that can be established between the datasets. It specifies that different identifiers refer to the same real world object and therefore must be linked. The process of detecting these identical instances across different data repositories is referred as instance matching. This is used to connect existing data sources and provides effective data integration from multiple data sources, therefore, maintains consistency and integrity of resultant data. To establish links, an instance matching system follows a link configuration which specifies the properties, similarity measures and other parameters required for data linking. When the data is huge detecting the configuration manually is not feasible. The paper proposes the supervised learning based instance matching system that relies on the learning of link configuration to establish identity links. The output of the learning algorithm is the optimal link configuration which returns the best possible combination of linking parameters.
{"title":"Supervised learning based instance matching system for data linking","authors":"Gulshakh Kaur, P. Saini","doi":"10.1109/ICACCI.2017.8125813","DOIUrl":"https://doi.org/10.1109/ICACCI.2017.8125813","url":null,"abstract":"In the Linked Data context, identity link is one of the most important semantic links that can be established between the datasets. It specifies that different identifiers refer to the same real world object and therefore must be linked. The process of detecting these identical instances across different data repositories is referred as instance matching. This is used to connect existing data sources and provides effective data integration from multiple data sources, therefore, maintains consistency and integrity of resultant data. To establish links, an instance matching system follows a link configuration which specifies the properties, similarity measures and other parameters required for data linking. When the data is huge detecting the configuration manually is not feasible. The paper proposes the supervised learning based instance matching system that relies on the learning of link configuration to establish identity links. The output of the learning algorithm is the optimal link configuration which returns the best possible combination of linking parameters.","PeriodicalId":437297,"journal":{"name":"2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125499056","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 : 2017-09-01DOI: 10.1109/ICACCI.2017.8125968
Poonam Salunkhe, Sreebha Bhaskaran, Joseph Amudha, Deepa Gupta
This paper presents a text detection approach based on Stroke Width Transform (SWT) and methodology to extract letter candidates. Major application focus here is tourism industry and local transport, to help people to deal with different Indian languages which involve text associated with natural scenes in the local public places. Multilingual text system supports curvy letters with different scale, size, direction, font and language. This method can significantly perform for different Indian Languages and results are tested based on ICDAR 2015 dataset and different user Test dataset.
{"title":"Recognition of multilingual text from signage boards","authors":"Poonam Salunkhe, Sreebha Bhaskaran, Joseph Amudha, Deepa Gupta","doi":"10.1109/ICACCI.2017.8125968","DOIUrl":"https://doi.org/10.1109/ICACCI.2017.8125968","url":null,"abstract":"This paper presents a text detection approach based on Stroke Width Transform (SWT) and methodology to extract letter candidates. Major application focus here is tourism industry and local transport, to help people to deal with different Indian languages which involve text associated with natural scenes in the local public places. Multilingual text system supports curvy letters with different scale, size, direction, font and language. This method can significantly perform for different Indian Languages and results are tested based on ICDAR 2015 dataset and different user Test dataset.","PeriodicalId":437297,"journal":{"name":"2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125672615","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：