Pub Date : 2014-07-12DOI: 10.1109/ICSPCT.2014.6884982
M. Narayanan, C. Arun
The Peer-to-Peer (P2P) computing is one of the rapidly growing technology, because day by day people needs and expectations are extending beyond boundaries. This P2P technology is started from file sharing, video streaming and P2P computing. Basically in this P2P computing, those who are in on-line all will act likes as a server or client. If they are having data segments then it will act as server otherwise clients. Generally the data segments are preserving at the peers in different levels such as hard cache and soft cache. Based on the popularity the video contents can be downloaded. Normally the most popular data segments are placed on the cache which is downloaded either from video server of from neighboring peers. There are so many of cache replacement algorithms have been introduced to replace the old data segments with newly arrived data segments. While arriving new data segments the old data segments removed from the queue i.e. cache, so the availability of the data content is presented very low. To overcome this problem multilevel cache is protecting the old segments in order to increase the speed. Generally P2P system the request will go at the neighbouring peer that particular neighbouring peer having is less connectivity then the client can receive the data segments slowly. Therefore overcoming this category of connectivity problem, we recommended bandwidth based cluster. After client registration, the video server build cluster based on bandwidth size. Once the request from client / server received immediately the video server finds highest bandwidth and LFU peer in their cluster and then service is redirected.
{"title":"An efficient technique for video content managing in peer-to-peer computing using multilevel cache and bandwidth based cluster","authors":"M. Narayanan, C. Arun","doi":"10.1109/ICSPCT.2014.6884982","DOIUrl":"https://doi.org/10.1109/ICSPCT.2014.6884982","url":null,"abstract":"The Peer-to-Peer (P2P) computing is one of the rapidly growing technology, because day by day people needs and expectations are extending beyond boundaries. This P2P technology is started from file sharing, video streaming and P2P computing. Basically in this P2P computing, those who are in on-line all will act likes as a server or client. If they are having data segments then it will act as server otherwise clients. Generally the data segments are preserving at the peers in different levels such as hard cache and soft cache. Based on the popularity the video contents can be downloaded. Normally the most popular data segments are placed on the cache which is downloaded either from video server of from neighboring peers. There are so many of cache replacement algorithms have been introduced to replace the old data segments with newly arrived data segments. While arriving new data segments the old data segments removed from the queue i.e. cache, so the availability of the data content is presented very low. To overcome this problem multilevel cache is protecting the old segments in order to increase the speed. Generally P2P system the request will go at the neighbouring peer that particular neighbouring peer having is less connectivity then the client can receive the data segments slowly. Therefore overcoming this category of connectivity problem, we recommended bandwidth based cluster. After client registration, the video server build cluster based on bandwidth size. Once the request from client / server received immediately the video server finds highest bandwidth and LFU peer in their cluster and then service is redirected.","PeriodicalId":419263,"journal":{"name":"2013 International Conference on Human Computer Interactions (ICHCI)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121692351","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 : 2013-08-01DOI: 10.1109/ICHCI-IEEE.2013.6887785
J. Manikandan, C. Niladri, S. Venugopal, V. Ktishnamurthy, V. K. Agrawal
Environment pollution has become a very big menace to human beings and awareness is required among the citizens to contribute for green environment. Polluted air is harmful for human beings and the biosphere, on the whole. Details about the effects of air pollutants on human beings for different concentrations are reported in this paper, which confirms that there is an urgent need to design a low-cost wired or wireless sensor node to monitor air pollution and the same can be employed for monitoring other sources of environment pollution too. The proposed module can be easily adapted in two-wheelers, four-wheelers and other automobiles enabling the drivers and passengers to get an idea of air pollutant content around them.
{"title":"Wireless sensor node for green environment","authors":"J. Manikandan, C. Niladri, S. Venugopal, V. Ktishnamurthy, V. K. Agrawal","doi":"10.1109/ICHCI-IEEE.2013.6887785","DOIUrl":"https://doi.org/10.1109/ICHCI-IEEE.2013.6887785","url":null,"abstract":"Environment pollution has become a very big menace to human beings and awareness is required among the citizens to contribute for green environment. Polluted air is harmful for human beings and the biosphere, on the whole. Details about the effects of air pollutants on human beings for different concentrations are reported in this paper, which confirms that there is an urgent need to design a low-cost wired or wireless sensor node to monitor air pollution and the same can be employed for monitoring other sources of environment pollution too. The proposed module can be easily adapted in two-wheelers, four-wheelers and other automobiles enabling the drivers and passengers to get an idea of air pollutant content around them.","PeriodicalId":419263,"journal":{"name":"2013 International Conference on Human Computer Interactions (ICHCI)","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123418825","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 : 2013-08-01DOI: 10.1109/ICHCI-IEEE.2013.6887792
Bishnupriya Panda, A. P. Mishra, B. Majhi, M. Rout
Prediction of protein structural class has been a new area of research in the scientific community in the last decade. Various approaches has been adopted and analysed. However representing the raw amino acid sequence to preserve the property of proteins has posed a great challenge. Chou's pseudo amino acid composition feature representation method has fetched wide attention in this regard. In Chou's representation each protein molecule is represented as the combination of amino acid composition information, the amphiphillic correlation factors and the spectral characteristics of the protein. This method preserves both the sequence order and length information of the raw amino acid sequence and this plays a significant role in prediction. A set of exhaustive simulation studies with functional link artificial network(FLANN) demonstrates high success rate of classification. The self-consistency and jackknife test on the benchmark datasets has been performed and a comparison has been done with the results of radial basis function (RBF) neural network. It indicates that the FLANN model's accuracy is little less than RBF, but its complexity is very less whereas the accuracy of RBF is little higher, but it's complexity is high in comparison to FLANN.
{"title":"Performance evaluation of protein structural class prediction using artificial neural networks","authors":"Bishnupriya Panda, A. P. Mishra, B. Majhi, M. Rout","doi":"10.1109/ICHCI-IEEE.2013.6887792","DOIUrl":"https://doi.org/10.1109/ICHCI-IEEE.2013.6887792","url":null,"abstract":"Prediction of protein structural class has been a new area of research in the scientific community in the last decade. Various approaches has been adopted and analysed. However representing the raw amino acid sequence to preserve the property of proteins has posed a great challenge. Chou's pseudo amino acid composition feature representation method has fetched wide attention in this regard. In Chou's representation each protein molecule is represented as the combination of amino acid composition information, the amphiphillic correlation factors and the spectral characteristics of the protein. This method preserves both the sequence order and length information of the raw amino acid sequence and this plays a significant role in prediction. A set of exhaustive simulation studies with functional link artificial network(FLANN) demonstrates high success rate of classification. The self-consistency and jackknife test on the benchmark datasets has been performed and a comparison has been done with the results of radial basis function (RBF) neural network. It indicates that the FLANN model's accuracy is little less than RBF, but its complexity is very less whereas the accuracy of RBF is little higher, but it's complexity is high in comparison to FLANN.","PeriodicalId":419263,"journal":{"name":"2013 International Conference on Human Computer Interactions (ICHCI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129374620","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 : 2013-08-01DOI: 10.1109/ICHCI-IEEE.2013.6887803
Sukhpal Singh, Inderveer Chana, M. Singh
A common task in various machine learning (ML) application areas involves observing regularly gathered data for `interesting' events. This mission is predominant in reconnaissance, but also in responsibilities fluctuating from the investigation of scientific data to the observing of unsurprisingly happening events, and from controlling engineering procedures to noticing human behavior. We will refer to this observing procedure with the determination of classifying remarkable manifestations, as event detection, analysis and classification. With the appearance of personal computers (PCs) a lot of efforts have been made to substitute manual investigation by a computerized manner. Data, nevertheless, have become gradually difficult, and the sizes of gathered data have become enormously bulky in latest years. Text documents, JPEG images, MP3, videos and even relational data are now regularly gathered. In this paper, we propose an algorithm for event detection, analysis and classification in machine vision. Till proposed algorithm is deliberated a significant facility, required degree of event detection cannot be achieved. Finally, we use K-means algorithm for classification of incoming events and proposed algorithm has been validated by Z Formal specification language in general. The proposed algorithm has been implemented in Matlab and results have been gathered through a data mining tool. Using the proposed algorithm, the events are easily detected, analyzed and classified in machine vision.
{"title":"Z language based an algorithm for event detection, analysis and classification in machine vision","authors":"Sukhpal Singh, Inderveer Chana, M. Singh","doi":"10.1109/ICHCI-IEEE.2013.6887803","DOIUrl":"https://doi.org/10.1109/ICHCI-IEEE.2013.6887803","url":null,"abstract":"A common task in various machine learning (ML) application areas involves observing regularly gathered data for `interesting' events. This mission is predominant in reconnaissance, but also in responsibilities fluctuating from the investigation of scientific data to the observing of unsurprisingly happening events, and from controlling engineering procedures to noticing human behavior. We will refer to this observing procedure with the determination of classifying remarkable manifestations, as event detection, analysis and classification. With the appearance of personal computers (PCs) a lot of efforts have been made to substitute manual investigation by a computerized manner. Data, nevertheless, have become gradually difficult, and the sizes of gathered data have become enormously bulky in latest years. Text documents, JPEG images, MP3, videos and even relational data are now regularly gathered. In this paper, we propose an algorithm for event detection, analysis and classification in machine vision. Till proposed algorithm is deliberated a significant facility, required degree of event detection cannot be achieved. Finally, we use K-means algorithm for classification of incoming events and proposed algorithm has been validated by Z Formal specification language in general. The proposed algorithm has been implemented in Matlab and results have been gathered through a data mining tool. Using the proposed algorithm, the events are easily detected, analyzed and classified in machine vision.","PeriodicalId":419263,"journal":{"name":"2013 International Conference on Human Computer Interactions (ICHCI)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125034894","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 : 2013-08-01DOI: 10.1109/ICHCI-IEEE.2013.6887816
K. Rangasamy, L. Sivakumar
This work aims to retune the controller parameters of decentralised PI controller of Alstom gasifier using Firefly algorithm. Coal gasifier is a highly nonlinear, multivariable process involving many complex reactions, and it seems to be difficult to control. The performance of the existing decentralised PI controller of Alstom gasifier does not able to satisfy the requirements at 0% load condition for sinusoidal pressure disturbance except which it seems to be good enough to meet the constraints at 50% and 100% load conditions. This is due to improper tuning of decentralised PI controllers and here we attempt to retune the PI controller responsible for pressure loop, using Firefly Algorithm (FA). Existing parameters of PI controller for pressure loop is replaced by the retuned parameters and pressure disturbance test (both sinusoidal and step), load change test and coal quality test are conducted and compared with the existing results. Results shows that the process satisfies the performance requirements at 0%, 50% and 100% load conditions without violating the constraints.
{"title":"Partial-retuning of decentralised PI controller of nonlinear multivariable process using firefly algorithm","authors":"K. Rangasamy, L. Sivakumar","doi":"10.1109/ICHCI-IEEE.2013.6887816","DOIUrl":"https://doi.org/10.1109/ICHCI-IEEE.2013.6887816","url":null,"abstract":"This work aims to retune the controller parameters of decentralised PI controller of Alstom gasifier using Firefly algorithm. Coal gasifier is a highly nonlinear, multivariable process involving many complex reactions, and it seems to be difficult to control. The performance of the existing decentralised PI controller of Alstom gasifier does not able to satisfy the requirements at 0% load condition for sinusoidal pressure disturbance except which it seems to be good enough to meet the constraints at 50% and 100% load conditions. This is due to improper tuning of decentralised PI controllers and here we attempt to retune the PI controller responsible for pressure loop, using Firefly Algorithm (FA). Existing parameters of PI controller for pressure loop is replaced by the retuned parameters and pressure disturbance test (both sinusoidal and step), load change test and coal quality test are conducted and compared with the existing results. Results shows that the process satisfies the performance requirements at 0%, 50% and 100% load conditions without violating the constraints.","PeriodicalId":419263,"journal":{"name":"2013 International Conference on Human Computer Interactions (ICHCI)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114255925","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 : 2013-08-01DOI: 10.1109/ICHCI-IEEE.2013.6887796
J. Archana, Senthil Raja Chermapandan, S. Palanivel
For a widespread usage of the software product, the product should be available and usable in different local languages of different countries. Many companies are planning to or have already invested time and money to internationalize their products and websites and localize them into other languages. When making a product to support multiple languages, there are chances for assumed conventions for a specific language. To ensure that the product is usable anywhere in the world while adapting to the cultural identity of the user we provide an automation framework to check the internationalization functionality of the product. The implementation of our proposed automation framework shows that it can identify the hardcoded content of a specific language, the text that has been over translated for a specific language and the character handling issues for various languages. The framework is flexible as it can be used for any web-based software product. The proposed framework will reduce the time involved in regression testing and with minimal effort the future enhancements of the product can be easily tested.
{"title":"Automation framework for localizability testing of internationalized software","authors":"J. Archana, Senthil Raja Chermapandan, S. Palanivel","doi":"10.1109/ICHCI-IEEE.2013.6887796","DOIUrl":"https://doi.org/10.1109/ICHCI-IEEE.2013.6887796","url":null,"abstract":"For a widespread usage of the software product, the product should be available and usable in different local languages of different countries. Many companies are planning to or have already invested time and money to internationalize their products and websites and localize them into other languages. When making a product to support multiple languages, there are chances for assumed conventions for a specific language. To ensure that the product is usable anywhere in the world while adapting to the cultural identity of the user we provide an automation framework to check the internationalization functionality of the product. The implementation of our proposed automation framework shows that it can identify the hardcoded content of a specific language, the text that has been over translated for a specific language and the character handling issues for various languages. The framework is flexible as it can be used for any web-based software product. The proposed framework will reduce the time involved in regression testing and with minimal effort the future enhancements of the product can be easily tested.","PeriodicalId":419263,"journal":{"name":"2013 International Conference on Human Computer Interactions (ICHCI)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114309297","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 : 2013-08-01DOI: 10.1109/ICHCI-IEEE.2013.6887767
K. P. Rao, C. Rupa
Cryptography is used to provide the security to the information. At present various security algorithms are used by the users to protect their data from intruders. Even though, attacks are being done by the assailants on the data due to rapid growth of the technology as well as its diffidence also. Hence in this paper we proposed a security approach using unit fractions of the Linear Algebra i.e Hilbert Matrix. The main important properties of the Hilbert matrix are symmetric and positive definitive, which makes determinant of every sub matrix, is positive and useful to generate different cipher texts to the same plain text. It improves the security to the data by confusing the intruders. We show that the various properties that just differ by the standard security algorithms such as RSA. Cryptanalysis of the proposed algorithm shows that it is resistant to various attacks and stronger than existed encryption algorithms.
{"title":"A novel security approach in the information and communication with cryptanalysis","authors":"K. P. Rao, C. Rupa","doi":"10.1109/ICHCI-IEEE.2013.6887767","DOIUrl":"https://doi.org/10.1109/ICHCI-IEEE.2013.6887767","url":null,"abstract":"Cryptography is used to provide the security to the information. At present various security algorithms are used by the users to protect their data from intruders. Even though, attacks are being done by the assailants on the data due to rapid growth of the technology as well as its diffidence also. Hence in this paper we proposed a security approach using unit fractions of the Linear Algebra i.e Hilbert Matrix. The main important properties of the Hilbert matrix are symmetric and positive definitive, which makes determinant of every sub matrix, is positive and useful to generate different cipher texts to the same plain text. It improves the security to the data by confusing the intruders. We show that the various properties that just differ by the standard security algorithms such as RSA. Cryptanalysis of the proposed algorithm shows that it is resistant to various attacks and stronger than existed encryption algorithms.","PeriodicalId":419263,"journal":{"name":"2013 International Conference on Human Computer Interactions (ICHCI)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117138910","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 : 2013-08-01DOI: 10.1109/ICHCI-IEEE.2013.6887799
J. Grover, Shivangi Katiyar
Cloud Computing is one of the latest computing paradigms in IT sector today where applications, platforms, software and some other IT services are provided over the internet. It is also known as On Demand Computing. Cloud Computing considers shared pool of configurable computing resources which requires proper resource distribution among the tasks, otherwise in some situations resources may over-utilized or under-utilized. For the sake of efficient resource utilization, Load Balancing System problem needs more attention in cloud computing. In This paper, we have used Agent Based Dynamic Load Balancing (ABDLB) approach in which mobile agent plays very important role, which is a software entity and usually defined as an independent software program that runs on behalf of a network administrator. It has ability to learn. After comparing the proposed method with traditional load balancing scheme we concluded that Agent Base load balancing scheme greatly reduces the communication cost of servers, accelerates the rate of load balancing which indirectly improves the Throughput and Response Time of the cloud.
{"title":"Agent based dynamic load balancing in Cloud Computing","authors":"J. Grover, Shivangi Katiyar","doi":"10.1109/ICHCI-IEEE.2013.6887799","DOIUrl":"https://doi.org/10.1109/ICHCI-IEEE.2013.6887799","url":null,"abstract":"Cloud Computing is one of the latest computing paradigms in IT sector today where applications, platforms, software and some other IT services are provided over the internet. It is also known as On Demand Computing. Cloud Computing considers shared pool of configurable computing resources which requires proper resource distribution among the tasks, otherwise in some situations resources may over-utilized or under-utilized. For the sake of efficient resource utilization, Load Balancing System problem needs more attention in cloud computing. In This paper, we have used Agent Based Dynamic Load Balancing (ABDLB) approach in which mobile agent plays very important role, which is a software entity and usually defined as an independent software program that runs on behalf of a network administrator. It has ability to learn. After comparing the proposed method with traditional load balancing scheme we concluded that Agent Base load balancing scheme greatly reduces the communication cost of servers, accelerates the rate of load balancing which indirectly improves the Throughput and Response Time of the cloud.","PeriodicalId":419263,"journal":{"name":"2013 International Conference on Human Computer Interactions (ICHCI)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124656519","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 : 2013-08-01DOI: 10.1109/ICHCI-IEEE.2013.6887768
Chandranath Adak
This paper introduces an efficient edge detection method based on Gabor filter and rough clustering. The input image is smoothed by Gabor function, and the concept of rough clustering is used to focus on edge detection with soft computational approach. Hysteresis thresholding is used to get the actual output, i.e. edges of the input image. To show the effectiveness, the proposed technique is compared with some other edge detection methods.
{"title":"Gabor filter and rough clustering based edge detection","authors":"Chandranath Adak","doi":"10.1109/ICHCI-IEEE.2013.6887768","DOIUrl":"https://doi.org/10.1109/ICHCI-IEEE.2013.6887768","url":null,"abstract":"This paper introduces an efficient edge detection method based on Gabor filter and rough clustering. The input image is smoothed by Gabor function, and the concept of rough clustering is used to focus on edge detection with soft computational approach. Hysteresis thresholding is used to get the actual output, i.e. edges of the input image. To show the effectiveness, the proposed technique is compared with some other edge detection methods.","PeriodicalId":419263,"journal":{"name":"2013 International Conference on Human Computer Interactions (ICHCI)","volume":"160 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122310417","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}
This paper aims to present a new transformation model estimation frame work for feature based image registration techniques. In general Feature based image registration techniques involves Feature detection, matching, transformation model estimation, image resampling and transformation. Very little work has been done in the area of transformation model estimation compared to wide range of techniques available in Feature Detection and matching. While RANSAC (Random Sample Consensus) and LMS (Least Median of Squares) are the most commonly used methods for robust global transformation estimation in affine and perspective transformations, research is going on for the methods that would do well in the presence of a very high number of outlier data and overcome the disadvantages of these state of art techniques. This motivated us to develop a new algorithm which not only uses the spatial relations between the feature points but also make use of the image intensity profiles for robust model estimation even in presence of outliers. In current approach, first the Euclidean distances created by the matched feature points is clustered and matching error for each cluster is computed using intensity information. The feature point pairs of the cluster having minimum error are retained. Now by applying mean filtering followed by recursive least square approximation, the transformation model is estimated. The efficiency of the proposed methodology is demonstrated on different datasets under different transformations & for different areas of application. The method has shown significant improvements in accuracy compared to other existing techniques even in the presence of large number of outliers.
{"title":"RLSAK: A recursive least square approximation with k-means for transformation model estimation in image registration techniques","authors":"Sistu Ganesh, Nivedita Tripathi, Gineesh Sukumaran","doi":"10.1109/ICHCI-IEEE.2013.6887775","DOIUrl":"https://doi.org/10.1109/ICHCI-IEEE.2013.6887775","url":null,"abstract":"This paper aims to present a new transformation model estimation frame work for feature based image registration techniques. In general Feature based image registration techniques involves Feature detection, matching, transformation model estimation, image resampling and transformation. Very little work has been done in the area of transformation model estimation compared to wide range of techniques available in Feature Detection and matching. While RANSAC (Random Sample Consensus) and LMS (Least Median of Squares) are the most commonly used methods for robust global transformation estimation in affine and perspective transformations, research is going on for the methods that would do well in the presence of a very high number of outlier data and overcome the disadvantages of these state of art techniques. This motivated us to develop a new algorithm which not only uses the spatial relations between the feature points but also make use of the image intensity profiles for robust model estimation even in presence of outliers. In current approach, first the Euclidean distances created by the matched feature points is clustered and matching error for each cluster is computed using intensity information. The feature point pairs of the cluster having minimum error are retained. Now by applying mean filtering followed by recursive least square approximation, the transformation model is estimated. The efficiency of the proposed methodology is demonstrated on different datasets under different transformations & for different areas of application. The method has shown significant improvements in accuracy compared to other existing techniques even in the presence of large number of outliers.","PeriodicalId":419263,"journal":{"name":"2013 International Conference on Human Computer Interactions (ICHCI)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2013-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124014741","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：