Pub Date : 2012-07-07DOI: 10.1109/KST.2012.6287733
C. Panmungmee, M. Wongsarat, P. Tangamchit
We propose a mobile camera system that can be installed on a moving. The system will automatically evaluate traffic levels in the area that the car has been driven through. Our system consists of two parts, the mobile probe and a stationary server. The mobile probe is operated by Android OS smartphone installed in a vehicle, which is used collect GPS data and image sequence of traffic scene from the front of the vehicle. The GPS and image data is periodically transferred to the stationary server via EDGE/3G cellular network. The GPS data is used to find an average space speed, which is used as an indicator to traffic status. The image data is used to recognize and filter out data from parking events, which do not represent traffic status. The level of traffic congestion is displayed in the format of three colors: red, yellow, and green.
{"title":"Automatic traffic estimation system using mobile probe vehicles","authors":"C. Panmungmee, M. Wongsarat, P. Tangamchit","doi":"10.1109/KST.2012.6287733","DOIUrl":"https://doi.org/10.1109/KST.2012.6287733","url":null,"abstract":"We propose a mobile camera system that can be installed on a moving. The system will automatically evaluate traffic levels in the area that the car has been driven through. Our system consists of two parts, the mobile probe and a stationary server. The mobile probe is operated by Android OS smartphone installed in a vehicle, which is used collect GPS data and image sequence of traffic scene from the front of the vehicle. The GPS and image data is periodically transferred to the stationary server via EDGE/3G cellular network. The GPS data is used to find an average space speed, which is used as an indicator to traffic status. The image data is used to recognize and filter out data from parking events, which do not represent traffic status. The level of traffic congestion is displayed in the format of three colors: red, yellow, and green.","PeriodicalId":209504,"journal":{"name":"Knowledge and Smart Technology (KST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116087239","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 : 2012-07-07DOI: 10.1109/KST.2012.6287732
P. Boribalburephan, B. Sakboonyarat
The algorithm for online handwritten character recognition, PHIA algorithm, is introduced. The algorithm uses a likelihood score computed by a small neural network from every symbol pair for various decisions. Scores are used to generate a relationship map (Rivals/Non-rivals) between each symbol pairs. The training data is added to the database if and only if the relationship with the training data is `rival' for all existing database samples that identifies the same symbol. In the recognition phase, a nearest neighbor search is applied. During the search, if we traverse to a node whose relationship to the input is `non-rival', we later skip all processes that would operate on that node's rivals. This optimizes the decision path for each of the individual and enhances the ability to learn new symbols effectively.
{"title":"An algorithm development for handwritten character recognition by personal handwriting identity analysis [PHIA]","authors":"P. Boribalburephan, B. Sakboonyarat","doi":"10.1109/KST.2012.6287732","DOIUrl":"https://doi.org/10.1109/KST.2012.6287732","url":null,"abstract":"The algorithm for online handwritten character recognition, PHIA algorithm, is introduced. The algorithm uses a likelihood score computed by a small neural network from every symbol pair for various decisions. Scores are used to generate a relationship map (Rivals/Non-rivals) between each symbol pairs. The training data is added to the database if and only if the relationship with the training data is `rival' for all existing database samples that identifies the same symbol. In the recognition phase, a nearest neighbor search is applied. During the search, if we traverse to a node whose relationship to the input is `non-rival', we later skip all processes that would operate on that node's rivals. This optimizes the decision path for each of the individual and enhances the ability to learn new symbols effectively.","PeriodicalId":209504,"journal":{"name":"Knowledge and Smart Technology (KST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134132951","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 : 2012-07-07DOI: 10.1109/KST.2012.6287731
C. Worasucheep
Harmony Search is a relatively new meta-heuristic algorithm for continuous optimization, in which its concept imitates the process of music improvisation. This paper applied an improved harmony search algorithm called Harmony Search with Adaptive Pitch Adjustment (HSAPA) for prediction of stock market index. HSAPA is applied to optimize the weights and biases of Single Multiplicative Neuron for the prediction of daily S&P500 index. Its prediction performance has been extensively evaluated using various sizes of dataset, training proportions, and beginning dates spanning from 1990 to 2009, a totaling of 108 test sets. The prediction results are compared to those of standard Back Propagation learning method and Opposition-based Differential Evolution algorithm, a very efficient and widely-accepted evolutionary algorithm. The results demonstrate that HSAPA is very promising for the stock market index prediction, measured with the mean absolute percentage error of the prediction results.
{"title":"Training a single multiplicative neuron with a harmony search algorithm for prediction of S&P500 index - An extensive performance evaluation","authors":"C. Worasucheep","doi":"10.1109/KST.2012.6287731","DOIUrl":"https://doi.org/10.1109/KST.2012.6287731","url":null,"abstract":"Harmony Search is a relatively new meta-heuristic algorithm for continuous optimization, in which its concept imitates the process of music improvisation. This paper applied an improved harmony search algorithm called Harmony Search with Adaptive Pitch Adjustment (HSAPA) for prediction of stock market index. HSAPA is applied to optimize the weights and biases of Single Multiplicative Neuron for the prediction of daily S&P500 index. Its prediction performance has been extensively evaluated using various sizes of dataset, training proportions, and beginning dates spanning from 1990 to 2009, a totaling of 108 test sets. The prediction results are compared to those of standard Back Propagation learning method and Opposition-based Differential Evolution algorithm, a very efficient and widely-accepted evolutionary algorithm. The results demonstrate that HSAPA is very promising for the stock market index prediction, measured with the mean absolute percentage error of the prediction results.","PeriodicalId":209504,"journal":{"name":"Knowledge and Smart Technology (KST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114105305","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 : 2012-07-07DOI: 10.1109/KST.2012.6287738
K. Thakulsukanant, W. Lee, V. Patanavijit
Recently, the images reconstruction approaches are very essential in digital image processing (DIP), especially in terms of removing the noise contaminations and recovering the content of images. Each image reconstruction approach has different mathematical models. Therefore a performance of individual reconstruction approach is varied depending on several factors such as image characteristic, reconstruction mathematical model, noise model and noise intensity. Thus, this paper presents comprehensive experiments based on the comparisons of various reconstruction approaches under Gaussian and non-Gaussian noise models. The employing reconstruction approaches in this experiment are Inverse Filter, Wiener Filter, Regularized approach, Lucy-Richardson (L-R) approach, and Bayesian approach applied on mean, median, myriad, meridian filters together with several regularization techniques (such as non-regularization, Laplacian regularized, Markov Random Field (MRF) regularization, and one-side Bi-Total Variation (OS-BTV) regularization). Three standard images of Lena, Resolution Chart, and Susie (40th) are used for testing in this experiment. Noise models of Additive White Gaussian Noise (AWGN), Poisson, Salt&Pepper, and Speckle of various intensities are used to contaminate all these images. The comparison is done by varying the parameters of each approach until the best peak-signal-to-noise ratio (PSNR) is obtained. Therefore, PSNR plays a vital parameter for comparisons all the results of individual approaches.
{"title":"An experimental performance analysis of image reconstruction techniques under both Gaussian and non-Gaussian noise models","authors":"K. Thakulsukanant, W. Lee, V. Patanavijit","doi":"10.1109/KST.2012.6287738","DOIUrl":"https://doi.org/10.1109/KST.2012.6287738","url":null,"abstract":"Recently, the images reconstruction approaches are very essential in digital image processing (DIP), especially in terms of removing the noise contaminations and recovering the content of images. Each image reconstruction approach has different mathematical models. Therefore a performance of individual reconstruction approach is varied depending on several factors such as image characteristic, reconstruction mathematical model, noise model and noise intensity. Thus, this paper presents comprehensive experiments based on the comparisons of various reconstruction approaches under Gaussian and non-Gaussian noise models. The employing reconstruction approaches in this experiment are Inverse Filter, Wiener Filter, Regularized approach, Lucy-Richardson (L-R) approach, and Bayesian approach applied on mean, median, myriad, meridian filters together with several regularization techniques (such as non-regularization, Laplacian regularized, Markov Random Field (MRF) regularization, and one-side Bi-Total Variation (OS-BTV) regularization). Three standard images of Lena, Resolution Chart, and Susie (40th) are used for testing in this experiment. Noise models of Additive White Gaussian Noise (AWGN), Poisson, Salt&Pepper, and Speckle of various intensities are used to contaminate all these images. The comparison is done by varying the parameters of each approach until the best peak-signal-to-noise ratio (PSNR) is obtained. Therefore, PSNR plays a vital parameter for comparisons all the results of individual approaches.","PeriodicalId":209504,"journal":{"name":"Knowledge and Smart Technology (KST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128351460","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 : 2012-07-07DOI: 10.1109/KST.2012.6287735
T. Charoenpong, S. Thewsuwan, Theerasak Chanwimalueang, V. Mahasithiwat
As vertigo is a type of dizziness, it causes by problem with nystagmus. Doctors can diagnosis this disease from observing the motion of inner eye. For Nystagmus diagnosis system, efficient and precise pupil extraction system is needed. This paper proposed a method of pupil extraction by using K-mean clustering and Mahalanobis distance. Image sequence is captured via infrared camera mounted on the binocular. Eye tracking algorithm is consisted of K-mean clustering and Mahalanobis Distance. Based on the darkness of pupil, K-means clustering algorithm is used to segment black pixels. Extracted region is pupil, however noise is occurred. The noisy data is eliminated by means of Mahalanobis distance technique. Then the pupil is extracted. For experimental result, 1869 frames from 9 image sequences are use to test the performance of the proposed method. Accuracy is 73.68%, precision is 3.18 pixels error.
{"title":"Pupil extraction system for Nystagmus diagnosis by using K-mean clustering and Mahalanobis distance technique","authors":"T. Charoenpong, S. Thewsuwan, Theerasak Chanwimalueang, V. Mahasithiwat","doi":"10.1109/KST.2012.6287735","DOIUrl":"https://doi.org/10.1109/KST.2012.6287735","url":null,"abstract":"As vertigo is a type of dizziness, it causes by problem with nystagmus. Doctors can diagnosis this disease from observing the motion of inner eye. For Nystagmus diagnosis system, efficient and precise pupil extraction system is needed. This paper proposed a method of pupil extraction by using K-mean clustering and Mahalanobis distance. Image sequence is captured via infrared camera mounted on the binocular. Eye tracking algorithm is consisted of K-mean clustering and Mahalanobis Distance. Based on the darkness of pupil, K-means clustering algorithm is used to segment black pixels. Extracted region is pupil, however noise is occurred. The noisy data is eliminated by means of Mahalanobis distance technique. Then the pupil is extracted. For experimental result, 1869 frames from 9 image sequences are use to test the performance of the proposed method. Accuracy is 73.68%, precision is 3.18 pixels error.","PeriodicalId":209504,"journal":{"name":"Knowledge and Smart Technology (KST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120930822","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 : 2012-07-07DOI: 10.1109/KST.2012.6287740
Supawadee Srikamdee, S. Rimcharoen, K. Chinnasarn
Although an artificial neural network and evolutionary algorithms have been proved that they are efficient in many problems, the algorithms, generally, may produce good results with some problems and yield inferior solution in others. These cause risk of selecting an appropriate algorithm to solve a particular problem. This paper proposes a method to reduce risk of selecting an algorithm for solving classification problems by forming NeuroEAs-based algorithm portfolios to diversify risk. This method combines an artificial neural network and many different evolutionary algorithms to work together. It allocates existing computation time to the constituent algorithms, and encourages interaction among these algorithms consistently so that the algorithms can help improve performance of each other. The experiment results with 5 classification problems from UCI machine learning repository have shown that the algorithm portfolio outperforms its constituent algorithms given the same computation time.
{"title":"NeuroEAs-based algorithm portfolios for classification problems","authors":"Supawadee Srikamdee, S. Rimcharoen, K. Chinnasarn","doi":"10.1109/KST.2012.6287740","DOIUrl":"https://doi.org/10.1109/KST.2012.6287740","url":null,"abstract":"Although an artificial neural network and evolutionary algorithms have been proved that they are efficient in many problems, the algorithms, generally, may produce good results with some problems and yield inferior solution in others. These cause risk of selecting an appropriate algorithm to solve a particular problem. This paper proposes a method to reduce risk of selecting an algorithm for solving classification problems by forming NeuroEAs-based algorithm portfolios to diversify risk. This method combines an artificial neural network and many different evolutionary algorithms to work together. It allocates existing computation time to the constituent algorithms, and encourages interaction among these algorithms consistently so that the algorithms can help improve performance of each other. The experiment results with 5 classification problems from UCI machine learning repository have shown that the algorithm portfolio outperforms its constituent algorithms given the same computation time.","PeriodicalId":209504,"journal":{"name":"Knowledge and Smart Technology (KST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132516056","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 : 2012-07-07DOI: 10.1109/KST.2012.6287734
P. Chainapaporn, P. Netisopakul
Thai herbs have increasingly gained public attention. Recently, there are a number of Thai herb websites. Each website has similar information but quite different details. For example, some webpages do not provide information indicating which part of Thai herb can treat the specified symptom. In order to collect more complete Thai herb information, we have developed information extraction process to extract Thai herb information from multiple websites. The process employed a HTML parser and file templates to recognize useful information in various webpage formats. Preliminary experiments gave satisfactory precision and recall over 85 percent.
{"title":"Thai herb information extraction from multiple websites","authors":"P. Chainapaporn, P. Netisopakul","doi":"10.1109/KST.2012.6287734","DOIUrl":"https://doi.org/10.1109/KST.2012.6287734","url":null,"abstract":"Thai herbs have increasingly gained public attention. Recently, there are a number of Thai herb websites. Each website has similar information but quite different details. For example, some webpages do not provide information indicating which part of Thai herb can treat the specified symptom. In order to collect more complete Thai herb information, we have developed information extraction process to extract Thai herb information from multiple websites. The process employed a HTML parser and file templates to recognize useful information in various webpage formats. Preliminary experiments gave satisfactory precision and recall over 85 percent.","PeriodicalId":209504,"journal":{"name":"Knowledge and Smart Technology (KST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121651201","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 : 2012-07-07DOI: 10.1109/KST.2012.6287736
Nichakorn Pankong, Somchai Prakancharoen, M. Buranarach
The technology of web 2.0 especially social networking has changed people's behavior, attitudes, interactions, and relationships. User activities on social networking sites have created both explicit and implicit relationship. The relations can be distinguished for the sites with symmetric and asymmetric relationship types. In this paper, we propose a framework for semantic social network analysis for recommending user member groups on social media sites that combines explicit and implicit relationship. The framework utilizes semantic technology, i.e. ontology and RDF, to integrate the resulted data from different sites. Moreover, a presentation of a ontology design for user and activities referring to social network sites. An example of the integrated user profile is demonstrated using FOAF vocabulary.
web 2.0技术,尤其是社交网络已经改变了人们的行为、态度、互动和关系。用户在社交网站上的活动产生了显性和隐性的关系。对于具有对称和非对称关系类型的站点,可以区分这些关系。在本文中,我们提出了一个结合显式和隐式关系的语义社交网络分析框架,用于推荐社交媒体网站上的用户成员组。该框架利用语义技术,即本体和RDF来集成来自不同站点的结果数据。在此基础上,提出了一种基于社交网站的用户与活动本体设计。使用FOAF词汇表演示了一个集成用户概要文件的示例。
{"title":"A combined semantic social network analysis framework to integrate social media data","authors":"Nichakorn Pankong, Somchai Prakancharoen, M. Buranarach","doi":"10.1109/KST.2012.6287736","DOIUrl":"https://doi.org/10.1109/KST.2012.6287736","url":null,"abstract":"The technology of web 2.0 especially social networking has changed people's behavior, attitudes, interactions, and relationships. User activities on social networking sites have created both explicit and implicit relationship. The relations can be distinguished for the sites with symmetric and asymmetric relationship types. In this paper, we propose a framework for semantic social network analysis for recommending user member groups on social media sites that combines explicit and implicit relationship. The framework utilizes semantic technology, i.e. ontology and RDF, to integrate the resulted data from different sites. Moreover, a presentation of a ontology design for user and activities referring to social network sites. An example of the integrated user profile is demonstrated using FOAF vocabulary.","PeriodicalId":209504,"journal":{"name":"Knowledge and Smart Technology (KST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114471553","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 : 2012-07-07DOI: 10.1109/KST.2012.6287739
S. Nootyaskool
Genetic algorithm (GA) has an advantage in exploration search. Particle swarm optimization (PSO) has an advantage in sharing movement information between particles. The combining between GA and PSO is proposed in this research. We design hybrid-GA with PSO, and compare the performance with simple GA and simple PSO, which their models will find the solution of five-difference complexity of numerical functions. The experiment result showed that hybrid GA with PSO can find the solution of a multimodal problem and unimodal with noise signal quickly.
{"title":"The hybrid implementation genetic algorithm with particle swarm optimization to solve the unconstrained optimization problems","authors":"S. Nootyaskool","doi":"10.1109/KST.2012.6287739","DOIUrl":"https://doi.org/10.1109/KST.2012.6287739","url":null,"abstract":"Genetic algorithm (GA) has an advantage in exploration search. Particle swarm optimization (PSO) has an advantage in sharing movement information between particles. The combining between GA and PSO is proposed in this research. We design hybrid-GA with PSO, and compare the performance with simple GA and simple PSO, which their models will find the solution of five-difference complexity of numerical functions. The experiment result showed that hybrid GA with PSO can find the solution of a multimodal problem and unimodal with noise signal quickly.","PeriodicalId":209504,"journal":{"name":"Knowledge and Smart Technology (KST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125960173","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 : 2012-07-07DOI: 10.1109/KST.2012.6287737
D. Kesrarat, V. Patanavijit
This paper presents experimental efficiency study of noise tolerance model of spatial optical flow based on Lucas-Kanade (LK) algorithms such as original LK with kernel of Barron, Fleet, and Beauchemin (BFB), confidence based optical flow algorithm for high reliability (CHR), robust motion estimation methods using gradient orientation information (RGOI), and a novel robust and high reliability for Lucas-Kanade optical flow algorithm using median filter and confidence based technique (NRLK) under several Non-Gaussian Noise. These experiment results are comprehensively tested on several standard sequences (such as AKIYO, COASTGUARD, CONTAINER, and FOREMAN) that have differences speed, foreground and background movement characteristics in a level of 0.5 sub-pixel displacements. Each standard sequence has 6 sets of sequence included an original (no noise), Poisson Noise (PN), Salt&Pepper Noise (SPN) at density (d) = 0.005 and d = 0.025, Speckle Noise (SN) at variance (v) = 0.01 and v = 0.05 respectively which Peak Signal to Noise Ratio (PSNR) is concentrated as the performance indicator.
{"title":"Experimental study efficiency of robust models of Lucas-Kanade optical flow algorithms in the present of Non-Gaussian Noise","authors":"D. Kesrarat, V. Patanavijit","doi":"10.1109/KST.2012.6287737","DOIUrl":"https://doi.org/10.1109/KST.2012.6287737","url":null,"abstract":"This paper presents experimental efficiency study of noise tolerance model of spatial optical flow based on Lucas-Kanade (LK) algorithms such as original LK with kernel of Barron, Fleet, and Beauchemin (BFB), confidence based optical flow algorithm for high reliability (CHR), robust motion estimation methods using gradient orientation information (RGOI), and a novel robust and high reliability for Lucas-Kanade optical flow algorithm using median filter and confidence based technique (NRLK) under several Non-Gaussian Noise. These experiment results are comprehensively tested on several standard sequences (such as AKIYO, COASTGUARD, CONTAINER, and FOREMAN) that have differences speed, foreground and background movement characteristics in a level of 0.5 sub-pixel displacements. Each standard sequence has 6 sets of sequence included an original (no noise), Poisson Noise (PN), Salt&Pepper Noise (SPN) at density (d) = 0.005 and d = 0.025, Speckle Noise (SN) at variance (v) = 0.01 and v = 0.05 respectively which Peak Signal to Noise Ratio (PSNR) is concentrated as the performance indicator.","PeriodicalId":209504,"journal":{"name":"Knowledge and Smart Technology (KST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114004111","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}