Pub Date : 2014-12-01DOI: 10.1109/ICCIC.2014.7238303
K. Pradeepa, M. Sivitha
Text spotting in tantrum personas is an consequential obligatory for galore content-based persona psychoanalysis chores. In this nominate arrangement an surgical and husky technique for sleuthing textual matter in tantrum personas. A libertine and efficacious lopping algorithm is premeditated to educe poly-headed text from an persona. Opposed to some extra feelers which simulate that text is horizontally-oriented to handgrip text of impulsive predilection. The stimulation persona is first percolated with machine-accessible ingredient feeler. Connected component clumping is then used to discover prospect text realms based on the supreme deviation. The skeleton of apiece connected component avails to assort the divergent text strings from apiece other. Then anneal prospect parole realms and influence whether apiece realm moderates text or not. The exfoliation, skewed, and semblance of apiece prospect can be reckoned from CCs, to germinate a text/non text classifier for annealed personas. In this proficiencies not entirely reveal text, it also educes from the persona and recognizes the text in conditions of storing the recognized paroles into a disunite file cabinet by integrating galore key betterments over tralatitious surviving proficiencies to nominate a novel CC clumping based tantrum text sleuthing technique, which finally extends to substantial performance betterment over the other emulous proficiencies.
{"title":"Optical persona realization of tantrum text sensing, excavation and recognition","authors":"K. Pradeepa, M. Sivitha","doi":"10.1109/ICCIC.2014.7238303","DOIUrl":"https://doi.org/10.1109/ICCIC.2014.7238303","url":null,"abstract":"Text spotting in tantrum personas is an consequential obligatory for galore content-based persona psychoanalysis chores. In this nominate arrangement an surgical and husky technique for sleuthing textual matter in tantrum personas. A libertine and efficacious lopping algorithm is premeditated to educe poly-headed text from an persona. Opposed to some extra feelers which simulate that text is horizontally-oriented to handgrip text of impulsive predilection. The stimulation persona is first percolated with machine-accessible ingredient feeler. Connected component clumping is then used to discover prospect text realms based on the supreme deviation. The skeleton of apiece connected component avails to assort the divergent text strings from apiece other. Then anneal prospect parole realms and influence whether apiece realm moderates text or not. The exfoliation, skewed, and semblance of apiece prospect can be reckoned from CCs, to germinate a text/non text classifier for annealed personas. In this proficiencies not entirely reveal text, it also educes from the persona and recognizes the text in conditions of storing the recognized paroles into a disunite file cabinet by integrating galore key betterments over tralatitious surviving proficiencies to nominate a novel CC clumping based tantrum text sleuthing technique, which finally extends to substantial performance betterment over the other emulous proficiencies.","PeriodicalId":187874,"journal":{"name":"2014 IEEE International Conference on Computational Intelligence and Computing Research","volume":"14 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128825358","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 : 2014-12-01DOI: 10.1109/ICCIC.2014.7238490
B. Wilson, Babak Khazaei, Laurence Hirsch, S. Kannan
Cloud computing is currently the hot topic in Information Technology (IT) as it offers a nontraditional model for managing and implementing IT in enterprises. Due to its benefits such as low investment for hardware and dynamic scaling, migrating data and application to cloud environment is gaining popularity in recent years in India. The main aim of this paper is to investigate the aspects of cloud migration with particular importance to SMEs in India and present a literature review of the existing frameworks and models available for cloud adoption. We have identified a number of issues that SMEs in India face while migrating to a cloud infrastructure and have presented our findings as an initial step towards a Decision Support System for cloud migration in India, referred to as Cloud Migration Decision Support System for India (CMDSSI).
{"title":"CMDSSI: A decision support system for cloud migration for SMEs in India","authors":"B. Wilson, Babak Khazaei, Laurence Hirsch, S. Kannan","doi":"10.1109/ICCIC.2014.7238490","DOIUrl":"https://doi.org/10.1109/ICCIC.2014.7238490","url":null,"abstract":"Cloud computing is currently the hot topic in Information Technology (IT) as it offers a nontraditional model for managing and implementing IT in enterprises. Due to its benefits such as low investment for hardware and dynamic scaling, migrating data and application to cloud environment is gaining popularity in recent years in India. The main aim of this paper is to investigate the aspects of cloud migration with particular importance to SMEs in India and present a literature review of the existing frameworks and models available for cloud adoption. We have identified a number of issues that SMEs in India face while migrating to a cloud infrastructure and have presented our findings as an initial step towards a Decision Support System for cloud migration in India, referred to as Cloud Migration Decision Support System for India (CMDSSI).","PeriodicalId":187874,"journal":{"name":"2014 IEEE International Conference on Computational Intelligence and Computing Research","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128408969","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 : 2014-12-01DOI: 10.1109/ICCIC.2014.7238454
G. Matharu, Anju Mishra, Pallavi Chhikara
In India, Information and Communication technologies (ICT) are being increasingly deployed in almost each sector of economy including media, health, agriculture, transportation, and education. Upon an analysis of the existing Indian Election Voting System, it is felt that the ICT remains to be exploited to its fullest potential. Although, the Election Commission of India (ECI) has recently taken up several ICT-enabled initiatives, but the application of advanced ICTs still needs to be promoted in Indian Election Voting System. In this paper, we propose an I-Voting System to provide for an additional channel of voting to the Indian electorate. This paper evaluates the utility of cloud computing technology in I-Voting and specifies ancillary benefits arising out of its deployment in I-Voting. Further, this paper proposes a cloud deployment model “Cloud-based Integrated Election Voting System (CIEVS)” that leverages advanced Information and Communication technologies including cloud computing, web services and mobile phone services to integrate the existing Electronic Voting Machine (EVM) System with the I-Voting System to provide a solution to the problem of prevailing low voting percentages in the Indian elections. Additionally, the paper elaborates on the components of the proposed model besides discussing the advantages offered by the proposed model.
{"title":"CIEVS: A cloud-based framework to modernize the Indian election voting system","authors":"G. Matharu, Anju Mishra, Pallavi Chhikara","doi":"10.1109/ICCIC.2014.7238454","DOIUrl":"https://doi.org/10.1109/ICCIC.2014.7238454","url":null,"abstract":"In India, Information and Communication technologies (ICT) are being increasingly deployed in almost each sector of economy including media, health, agriculture, transportation, and education. Upon an analysis of the existing Indian Election Voting System, it is felt that the ICT remains to be exploited to its fullest potential. Although, the Election Commission of India (ECI) has recently taken up several ICT-enabled initiatives, but the application of advanced ICTs still needs to be promoted in Indian Election Voting System. In this paper, we propose an I-Voting System to provide for an additional channel of voting to the Indian electorate. This paper evaluates the utility of cloud computing technology in I-Voting and specifies ancillary benefits arising out of its deployment in I-Voting. Further, this paper proposes a cloud deployment model “Cloud-based Integrated Election Voting System (CIEVS)” that leverages advanced Information and Communication technologies including cloud computing, web services and mobile phone services to integrate the existing Electronic Voting Machine (EVM) System with the I-Voting System to provide a solution to the problem of prevailing low voting percentages in the Indian elections. Additionally, the paper elaborates on the components of the proposed model besides discussing the advantages offered by the proposed model.","PeriodicalId":187874,"journal":{"name":"2014 IEEE International Conference on Computational Intelligence and Computing Research","volume":"160 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117346620","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 : 2014-12-01DOI: 10.1109/ICCIC.2014.7238357
Silki Baghla, S. Bansal
Beyond 3G or 4G or Fourth generation wireless networks is an era of heterogeneous networks where a large number of wireless networks having different quality of service and features are present simultaneously. To provide ubiquitous access to end users in such environment, vertical handoff mechanism is deployed where an active call or session is transferred from one access point to another depending on the services required by the end user. This optimal network selection among large number of networks available requires consideration of multiple criteria like cost, delay, jitter, available bandwidth etc. To incorporate maximum number of quality of service (Qos) parameters MADM methods provide a promising solution. But MADM methods suffer from two major problems; number of handovers and ranking abnormality. In this paper VIKOR MADM method has been analyzed with various normalization techniques to mitigate the effect of large number of handovers and ranking abnormality.
{"title":"Effect of normalization techniques in VIKOR method for network selection in heterogeneous networks","authors":"Silki Baghla, S. Bansal","doi":"10.1109/ICCIC.2014.7238357","DOIUrl":"https://doi.org/10.1109/ICCIC.2014.7238357","url":null,"abstract":"Beyond 3G or 4G or Fourth generation wireless networks is an era of heterogeneous networks where a large number of wireless networks having different quality of service and features are present simultaneously. To provide ubiquitous access to end users in such environment, vertical handoff mechanism is deployed where an active call or session is transferred from one access point to another depending on the services required by the end user. This optimal network selection among large number of networks available requires consideration of multiple criteria like cost, delay, jitter, available bandwidth etc. To incorporate maximum number of quality of service (Qos) parameters MADM methods provide a promising solution. But MADM methods suffer from two major problems; number of handovers and ranking abnormality. In this paper VIKOR MADM method has been analyzed with various normalization techniques to mitigate the effect of large number of handovers and ranking abnormality.","PeriodicalId":187874,"journal":{"name":"2014 IEEE International Conference on Computational Intelligence and Computing Research","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116081771","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 : 2014-12-01DOI: 10.1109/ICCIC.2014.7238325
P. Suganya, M. Sivitha
In the network data sharing is an important functionality. In many organizations data owners store their data into the storage server which can certainly share data with other followers (users). Earlier approaches either unreasonably expose the uniqueness of a data owner to the untrusted server or any unexclusive vouchers, or innovate substantial expenses on confirmation metadata to preserve concealment. In the proposed system, group manager is introduced and takes charge of user registration, and enlightening the real uniqueness of a dispute data proprietor. Group manager will generate a key and provide to the user, who want to access the data from the storage server. Consequently proposed method reduces the computation overhead and provides high performance due to revoke verification procedure.
{"title":"Dynamic group key authentication mechanism for data sharing in network","authors":"P. Suganya, M. Sivitha","doi":"10.1109/ICCIC.2014.7238325","DOIUrl":"https://doi.org/10.1109/ICCIC.2014.7238325","url":null,"abstract":"In the network data sharing is an important functionality. In many organizations data owners store their data into the storage server which can certainly share data with other followers (users). Earlier approaches either unreasonably expose the uniqueness of a data owner to the untrusted server or any unexclusive vouchers, or innovate substantial expenses on confirmation metadata to preserve concealment. In the proposed system, group manager is introduced and takes charge of user registration, and enlightening the real uniqueness of a dispute data proprietor. Group manager will generate a key and provide to the user, who want to access the data from the storage server. Consequently proposed method reduces the computation overhead and provides high performance due to revoke verification procedure.","PeriodicalId":187874,"journal":{"name":"2014 IEEE International Conference on Computational Intelligence and Computing Research","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127172627","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 : 2014-12-01DOI: 10.1109/ICCIC.2014.7238360
A. Karthikeyan, V. Jagadeep, A. Rakesh
Recent achievements in wireless sensor networks have enabled the use of tiny and inexpensive sensors with the ability of sensing large information and propagating over large distances. But the most important concern with wireless sensor network is, the node sensing range is very small, Low storage and limited energy resources. So to overcome this type of problem efficient energy planning should be made. Clustering is one of the technologies that can utilize the node energy effectively. So that the network life time can be extended. The proposed method which uses the advantage of SNR for multi hopping and power efficient gathering in sensor information systems (PEGASIS) routing protocol in order to increase the life time of the network. The analysis shows that the proposed method has extended the network life time and were compared with the previously introduced methods based on different parameters.
{"title":"Energy efficient multihop selection with PEGASIS routing protocol for wireless sensor networks","authors":"A. Karthikeyan, V. Jagadeep, A. Rakesh","doi":"10.1109/ICCIC.2014.7238360","DOIUrl":"https://doi.org/10.1109/ICCIC.2014.7238360","url":null,"abstract":"Recent achievements in wireless sensor networks have enabled the use of tiny and inexpensive sensors with the ability of sensing large information and propagating over large distances. But the most important concern with wireless sensor network is, the node sensing range is very small, Low storage and limited energy resources. So to overcome this type of problem efficient energy planning should be made. Clustering is one of the technologies that can utilize the node energy effectively. So that the network life time can be extended. The proposed method which uses the advantage of SNR for multi hopping and power efficient gathering in sensor information systems (PEGASIS) routing protocol in order to increase the life time of the network. The analysis shows that the proposed method has extended the network life time and were compared with the previously introduced methods based on different parameters.","PeriodicalId":187874,"journal":{"name":"2014 IEEE International Conference on Computational Intelligence and Computing Research","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126802506","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 : 2014-12-01DOI: 10.1109/ICCIC.2014.7238393
Fernaz Jasdanwala, N. Dutta, D. K. Bhattacharyya
Wireless communication adapters in mobile nodes form an ad hoc network without the need for any fundamental network infrastructure. Nodes in MANETs use radio signals with a finite range to communicate making it possible for any intermediate node to intercept the communication. Also the frequently changing topology, with high susceptibility to physical compromise along with the node's limitations in terms of energy resource, storage device and CPU form a tremendous challenge in providing security to MANETs. Unlike wired networks, there is no central infrastructure, which paves way for new challenges as services provided by central entities is now to be ensured by the mobile nodes in the network itself. As a result, there is no definitive form of defense and a comprehensive security solution should encompass avoidance, detection and reaction along with sought-after network performances. This paper focuses on the prevention/proactive approach of securing MANETs using NTRU (Nth degree truncated polynomial ring), to secure end-to-end communication through data encryption during data transmission. NTRU is Lattice-based cryptography, which is known to be resistant to quantum attacks. We assume a clustered MANET environment i.e. the mobile nodes have an efficient cluster-based routing algorithm deployed which gives us the list of clusters available in the environment along with its cluster heads and competent routing between them. The proposed technique provides data encryption using NTRU between cluster heads.
{"title":"Lattice based secure data transmission in MANETs","authors":"Fernaz Jasdanwala, N. Dutta, D. K. Bhattacharyya","doi":"10.1109/ICCIC.2014.7238393","DOIUrl":"https://doi.org/10.1109/ICCIC.2014.7238393","url":null,"abstract":"Wireless communication adapters in mobile nodes form an ad hoc network without the need for any fundamental network infrastructure. Nodes in MANETs use radio signals with a finite range to communicate making it possible for any intermediate node to intercept the communication. Also the frequently changing topology, with high susceptibility to physical compromise along with the node's limitations in terms of energy resource, storage device and CPU form a tremendous challenge in providing security to MANETs. Unlike wired networks, there is no central infrastructure, which paves way for new challenges as services provided by central entities is now to be ensured by the mobile nodes in the network itself. As a result, there is no definitive form of defense and a comprehensive security solution should encompass avoidance, detection and reaction along with sought-after network performances. This paper focuses on the prevention/proactive approach of securing MANETs using NTRU (Nth degree truncated polynomial ring), to secure end-to-end communication through data encryption during data transmission. NTRU is Lattice-based cryptography, which is known to be resistant to quantum attacks. We assume a clustered MANET environment i.e. the mobile nodes have an efficient cluster-based routing algorithm deployed which gives us the list of clusters available in the environment along with its cluster heads and competent routing between them. The proposed technique provides data encryption using NTRU between cluster heads.","PeriodicalId":187874,"journal":{"name":"2014 IEEE International Conference on Computational Intelligence and Computing Research","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125825739","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 : 2014-12-01DOI: 10.1109/ICCIC.2014.7238403
A. Anitha, E. Kannan
Immense databases may contain critical instances or chunks-a small heap of records or instances which has domain specific information. These chunks of information are useful in future decision making for improving classification accuracy for labeling of critical, unlabeled instances by reducing false positives and false negatives. Classification process may be assessed based on efficiency and effectiveness. Efficiency is concerned with the time to process the records by reducing attributes in the data set and effectiveness is the improvement in classification accuracy using crucial information. This work focuses on reducing the attributes in the large databases, put forwards an innovative procedure for computing criticality which isolates critical instances from the boundary region and are validated using real-world data set. This work also uses different attribute reduction technique used for fetching the critical instances to reduce the computational time. Results of the experiments show that only subsets of instances are isolated as critical nuggets. It is found that use of attribute reduction technique decreases the computational time. The data set with reduced attributes does not affect the classification accuracy and produces the same result as with the original data set. It also reveals that these critical records helps in improving classification accuracy substantially along with reduced computational time and are validated using real-life data sets.
{"title":"Isolating critical data points from boundary region with feature selection","authors":"A. Anitha, E. Kannan","doi":"10.1109/ICCIC.2014.7238403","DOIUrl":"https://doi.org/10.1109/ICCIC.2014.7238403","url":null,"abstract":"Immense databases may contain critical instances or chunks-a small heap of records or instances which has domain specific information. These chunks of information are useful in future decision making for improving classification accuracy for labeling of critical, unlabeled instances by reducing false positives and false negatives. Classification process may be assessed based on efficiency and effectiveness. Efficiency is concerned with the time to process the records by reducing attributes in the data set and effectiveness is the improvement in classification accuracy using crucial information. This work focuses on reducing the attributes in the large databases, put forwards an innovative procedure for computing criticality which isolates critical instances from the boundary region and are validated using real-world data set. This work also uses different attribute reduction technique used for fetching the critical instances to reduce the computational time. Results of the experiments show that only subsets of instances are isolated as critical nuggets. It is found that use of attribute reduction technique decreases the computational time. The data set with reduced attributes does not affect the classification accuracy and produces the same result as with the original data set. It also reveals that these critical records helps in improving classification accuracy substantially along with reduced computational time and are validated using real-life data sets.","PeriodicalId":187874,"journal":{"name":"2014 IEEE International Conference on Computational Intelligence and Computing Research","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125825781","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 : 2014-12-01DOI: 10.1109/ICCIC.2014.7238369
Pranay Yadav, Parool Singh
In this reserch article presents a novel method for the enhancement of color images, when images are corrupted by color impulse noise. According to planned algorithm the color noisy pixels are substituted by novel trimmed mean median value color images. Firstly, the color image (RGB) is sub-split up into three sections, i.e. Red (R), Green (G) and Blue (B) color pixel matrices, then all three matrices are checked for noisy pixels. In our proposed work divided in two parts. In first part is detection of noisy pixels and the second part is removal of noisy with details preservation like edges. When pixels values, are present in between 0's and 255's, it implies that they pixel are noise free pixels. Apply this scenario in whole color image pixels for the detection of color impulse noise. Second stage is the removal of noise. In this stage whole image is divided into a small 3×3 particular window and apply Unsymmetric condition in a small 3×3 window with the combination of mean median filter. Different color images are tested via proposed method. The experimental result shows better Peak Signal to Noise Ratio (PSNR) value, Mean Square Error (MSE), Root Mean Square Error (RMSE) and with better visual and human sensing. This method yields a better output for color impulse noise as compare to the other filters.
{"title":"Color impulse noise removal by modified alpha trimmed median mean filter for FVIN","authors":"Pranay Yadav, Parool Singh","doi":"10.1109/ICCIC.2014.7238369","DOIUrl":"https://doi.org/10.1109/ICCIC.2014.7238369","url":null,"abstract":"In this reserch article presents a novel method for the enhancement of color images, when images are corrupted by color impulse noise. According to planned algorithm the color noisy pixels are substituted by novel trimmed mean median value color images. Firstly, the color image (RGB) is sub-split up into three sections, i.e. Red (R), Green (G) and Blue (B) color pixel matrices, then all three matrices are checked for noisy pixels. In our proposed work divided in two parts. In first part is detection of noisy pixels and the second part is removal of noisy with details preservation like edges. When pixels values, are present in between 0's and 255's, it implies that they pixel are noise free pixels. Apply this scenario in whole color image pixels for the detection of color impulse noise. Second stage is the removal of noise. In this stage whole image is divided into a small 3×3 particular window and apply Unsymmetric condition in a small 3×3 window with the combination of mean median filter. Different color images are tested via proposed method. The experimental result shows better Peak Signal to Noise Ratio (PSNR) value, Mean Square Error (MSE), Root Mean Square Error (RMSE) and with better visual and human sensing. This method yields a better output for color impulse noise as compare to the other filters.","PeriodicalId":187874,"journal":{"name":"2014 IEEE International Conference on Computational Intelligence and Computing Research","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126684854","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 : 2014-12-01DOI: 10.1109/ICCIC.2014.7238451
B. Thakur, Kushagra Kulshrestha
An assistive mechanism for implementing comfortable wheelchair locomotion for severely disabled people is presented. The main feature of the prototype is that the estimation of the direction of movement is decided solely by the patient without stressing him physically. This is successfully achieved by investigating the user's natural gaze behavior using eyeball tracking in NI LabView. The prototype consists of a camera, image processing software and a motor controller to drive the wheelchair. Besides being a reliable, convenient and extremely useful, this prototype promises a cheap solution to the latest technology access. Tracking algorithm utilized is shape adapted mean shift algorithm in NI Vision assistant. The eyeball tracking outcomes are then used to produce suitable wheelchair motion taking the user to the intended location. The prototype encompasses a critical blend of knowledge and skills and should find high acceptance within the target group of severely disabled, especially whose communications are limited only to eye movements.
{"title":"Eye controlled electric wheelchair","authors":"B. Thakur, Kushagra Kulshrestha","doi":"10.1109/ICCIC.2014.7238451","DOIUrl":"https://doi.org/10.1109/ICCIC.2014.7238451","url":null,"abstract":"An assistive mechanism for implementing comfortable wheelchair locomotion for severely disabled people is presented. The main feature of the prototype is that the estimation of the direction of movement is decided solely by the patient without stressing him physically. This is successfully achieved by investigating the user's natural gaze behavior using eyeball tracking in NI LabView. The prototype consists of a camera, image processing software and a motor controller to drive the wheelchair. Besides being a reliable, convenient and extremely useful, this prototype promises a cheap solution to the latest technology access. Tracking algorithm utilized is shape adapted mean shift algorithm in NI Vision assistant. The eyeball tracking outcomes are then used to produce suitable wheelchair motion taking the user to the intended location. The prototype encompasses a critical blend of knowledge and skills and should find high acceptance within the target group of severely disabled, especially whose communications are limited only to eye movements.","PeriodicalId":187874,"journal":{"name":"2014 IEEE International Conference on Computational Intelligence and Computing Research","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121646267","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}