The paper is dedicated to the restoration of impulse noise highly-corrupted images by exploiting the characteristics of the local similarity and connectivity existed in most real-world images. The basic strategy of the proposed method is firstly to detect a noisy pixel and then restores the corrupted pixel, by the local features of similarity and connectivity in an image. A decision rule based on the number of similar and connective pixels, followed by a line-judgement procedure, is used to determine if it is a noise. A simple local-connectivity (decision-based median) filter based on the noise density level is designed to restore the noisy pixel. Experimental results show that the proposed noise reduction method can remove impulse noise better than other methods in highly corrupted images of noise ratio more than 15%
{"title":"An Intelligent Restoration Method for Impulse Noise Highly-Corrupted Images","authors":"Thou-Ho Chen, Chao-Yu Chen, Tsong-Yi Chen, Ming-Kun Wu","doi":"10.1109/ICCIS.2006.252306","DOIUrl":"https://doi.org/10.1109/ICCIS.2006.252306","url":null,"abstract":"The paper is dedicated to the restoration of impulse noise highly-corrupted images by exploiting the characteristics of the local similarity and connectivity existed in most real-world images. The basic strategy of the proposed method is firstly to detect a noisy pixel and then restores the corrupted pixel, by the local features of similarity and connectivity in an image. A decision rule based on the number of similar and connective pixels, followed by a line-judgement procedure, is used to determine if it is a noise. A simple local-connectivity (decision-based median) filter based on the noise density level is designed to restore the noisy pixel. Experimental results show that the proposed noise reduction method can remove impulse noise better than other methods in highly corrupted images of noise ratio more than 15%","PeriodicalId":296028,"journal":{"name":"2006 IEEE Conference on Cybernetics and Intelligent Systems","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132516330","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 : 2006-06-07DOI: 10.1109/ICCIS.2006.252340
N. Sriwachirawat, S. Auwatanamongkol
This paper presents a new genetic algorithm that efficiently finds k-MPE of Bayesian networks. The algorithm is based on niching method and is designed to utilize multifractral characteristic and clustering property of Bayesian networks to improve a search toward solutions. Benchmark tests are performed to evaluate the effectiveness of the algorithm and compare its performance with other niching genetic algorithms. The results from the tests show that the new algorithm outperforms the others for both running time and accuracy
{"title":"On Approximating K-MPE of Bayesian Networks Using Genetic Algorithm","authors":"N. Sriwachirawat, S. Auwatanamongkol","doi":"10.1109/ICCIS.2006.252340","DOIUrl":"https://doi.org/10.1109/ICCIS.2006.252340","url":null,"abstract":"This paper presents a new genetic algorithm that efficiently finds k-MPE of Bayesian networks. The algorithm is based on niching method and is designed to utilize multifractral characteristic and clustering property of Bayesian networks to improve a search toward solutions. Benchmark tests are performed to evaluate the effectiveness of the algorithm and compare its performance with other niching genetic algorithms. The results from the tests show that the new algorithm outperforms the others for both running time and accuracy","PeriodicalId":296028,"journal":{"name":"2006 IEEE Conference on Cybernetics and Intelligent Systems","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132763071","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 : 2006-06-07DOI: 10.1109/ICCIS.2006.252348
G. Horn, B. Oommen
We consider the problem of partitioning a set of elements (or objects) into mutually exclusive classes (or groups), where elements which are "similar" to each other are, hopefully, located in the same class. This problem has been shown to be NP-hard, and the literature reports solutions in which the similarity constraint consists of a single index. For example, typical "similarity" conditions that have been used in the literature include those in which "similar" objects are accessed together, or when they communicate (as processes do) with each other. In this paper, we present the first reported solution to the case when the objects could be linked together in a multi-constraint manner, and indeed, visit the scenario when the constraints could, themselves, be contradictory. The solution we propose is based on the theory of estimator-based learning automata (LA), operating in non-stationary environments. Rather than use traditional estimates, we advocate the use of stochastic weak-estimates (B. J. Oommen and L. Rueda, 2006) and the specific digraph properties of the relations between the elements. Although the solutions proposed perform admirably when the number of elements is small, the simulated results demonstrate that the quality of the final solution decreases with the number of elements. Thus, although this is the first reported solution to the problem which incorporates specific digraph properties of the objects, the scalability of the solution remains open
我们考虑将一组元素(或对象)划分为互斥类(或组)的问题，其中彼此“相似”的元素希望位于同一类中。这个问题已经被证明是np困难的，并且文献报道了相似约束由单个索引组成的解决方案。例如，文献中使用的典型“相似”条件包括一起访问“相似”对象，或者当它们彼此通信时(如进程所做的那样)。在本文中，我们首次报道了当对象可以以多约束方式连接在一起时的解决方案，并且确实访问了约束本身可能是矛盾的场景。我们提出的解决方案是基于基于估计器的学习自动机(LA)理论，在非平稳环境中运行。而不是使用传统的估计，我们主张使用随机弱估计(B. J. Oommen和L. Rueda, 2006)和元素之间关系的特定有向图属性。虽然所提出的解在单元数较少时表现良好，但模拟结果表明，最终解的质量随着单元数的增加而降低。因此，尽管这是第一个报道的包含对象的特定有向图属性的问题的解决方案，但解决方案的可伸缩性仍然是开放的
{"title":"Towards a Learning Automata Solution to the Multi-Constraint Partitioning Problem","authors":"G. Horn, B. Oommen","doi":"10.1109/ICCIS.2006.252348","DOIUrl":"https://doi.org/10.1109/ICCIS.2006.252348","url":null,"abstract":"We consider the problem of partitioning a set of elements (or objects) into mutually exclusive classes (or groups), where elements which are \"similar\" to each other are, hopefully, located in the same class. This problem has been shown to be NP-hard, and the literature reports solutions in which the similarity constraint consists of a single index. For example, typical \"similarity\" conditions that have been used in the literature include those in which \"similar\" objects are accessed together, or when they communicate (as processes do) with each other. In this paper, we present the first reported solution to the case when the objects could be linked together in a multi-constraint manner, and indeed, visit the scenario when the constraints could, themselves, be contradictory. The solution we propose is based on the theory of estimator-based learning automata (LA), operating in non-stationary environments. Rather than use traditional estimates, we advocate the use of stochastic weak-estimates (B. J. Oommen and L. Rueda, 2006) and the specific digraph properties of the relations between the elements. Although the solutions proposed perform admirably when the number of elements is small, the simulated results demonstrate that the quality of the final solution decreases with the number of elements. Thus, although this is the first reported solution to the problem which incorporates specific digraph properties of the objects, the scalability of the solution remains open","PeriodicalId":296028,"journal":{"name":"2006 IEEE Conference on Cybernetics and Intelligent Systems","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132310917","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}
The purpose of this paper is to design and implement a grey prediction controller (GPC) via LabVIEW as a test platform. Grey prediction model GM(1,1) is used with the aid of first-order, digital low-pass alpha filter to refine the estimation of the system response in advance. The prediction is then utilized to modify the parameters of PID controller. Hence, an auto-tuning PID controller according to the forecasting of system response is achieved. LabVIEW software programming with a data acquisition card (model DAQPad-6015) from National Instruments Co. is chosen to provide a high-resolution, however, time-saving solution for developing this auto-tuning control system. One temperature regulation example is arranged and tested to confirm this auto-tuning controller scheme. Test results of this novel grey prediction controller are derived and compared with traditional PID controller. The Grey prediction controller is far better than PID controller in the prospect of both the transient response and steady state response. Best of all, this auto-tuning regulator eliminates the hassle of human interference
{"title":"LabVIEW Implementation of an Auto-tuning PID Regulator via Grey-predictor","authors":"Chien-Ming Lee, Yao-Lun Liu, Hong-Wei Shieh, Chia-Chang Tong","doi":"10.1109/ICCIS.2006.252318","DOIUrl":"https://doi.org/10.1109/ICCIS.2006.252318","url":null,"abstract":"The purpose of this paper is to design and implement a grey prediction controller (GPC) via LabVIEW as a test platform. Grey prediction model GM(1,1) is used with the aid of first-order, digital low-pass alpha filter to refine the estimation of the system response in advance. The prediction is then utilized to modify the parameters of PID controller. Hence, an auto-tuning PID controller according to the forecasting of system response is achieved. LabVIEW software programming with a data acquisition card (model DAQPad-6015) from National Instruments Co. is chosen to provide a high-resolution, however, time-saving solution for developing this auto-tuning control system. One temperature regulation example is arranged and tested to confirm this auto-tuning controller scheme. Test results of this novel grey prediction controller are derived and compared with traditional PID controller. The Grey prediction controller is far better than PID controller in the prospect of both the transient response and steady state response. Best of all, this auto-tuning regulator eliminates the hassle of human interference","PeriodicalId":296028,"journal":{"name":"2006 IEEE Conference on Cybernetics and Intelligent Systems","volume":"30 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124204126","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 : 2006-06-07DOI: 10.1109/ICCIS.2006.252235
Guisheng Yin, Dongmei Yang, Qi Wen, Churong Lai, Jie Shen
Based the theory of binocular vision, user avatar is constructed dynamically by many pictures with different angles, regulating the view point position adaptively according to the purpose of user interactive operation to receive the accurate sense of distance and direction. Based on the video's modeling of user avatar sincerity and long-distance reappearance in real-time, it is important for the virtual user avatar with the help of interactive museum presence of robot avatar. The realization of real-time visual feedback among users interaction in distributed virtual environment is help to realize the sincere merge between virtual scenes and true scenes and the realization of the interaction between human and computer based on virtual avatar
{"title":"Sincerity and User Avatar Research Based on Binocular Vision in Virtual Reality","authors":"Guisheng Yin, Dongmei Yang, Qi Wen, Churong Lai, Jie Shen","doi":"10.1109/ICCIS.2006.252235","DOIUrl":"https://doi.org/10.1109/ICCIS.2006.252235","url":null,"abstract":"Based the theory of binocular vision, user avatar is constructed dynamically by many pictures with different angles, regulating the view point position adaptively according to the purpose of user interactive operation to receive the accurate sense of distance and direction. Based on the video's modeling of user avatar sincerity and long-distance reappearance in real-time, it is important for the virtual user avatar with the help of interactive museum presence of robot avatar. The realization of real-time visual feedback among users interaction in distributed virtual environment is help to realize the sincere merge between virtual scenes and true scenes and the realization of the interaction between human and computer based on virtual avatar","PeriodicalId":296028,"journal":{"name":"2006 IEEE Conference on Cybernetics and Intelligent Systems","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124902772","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 : 2006-06-07DOI: 10.1109/ICCIS.2006.252298
Kun-Chieh Wang
The thermal effect on machine tools has become a well-recognized problem in response to the increasing requirement of product quality. The performance of a thermal error compensation system strongly depends on the accuracy of the thermal error model. This paper presents a novel thermal error modeling technique including two mathematic schemes: GM(1,N) model of the grey system theory and the hierarchy-genetic-algorithm (HGA) trained neural network in order to map the temperature ascent against thermal drift of the machine tool. Fist, the GM(1,N) scheme of the grey system theory was applied to minimize the numbers of the temperature sensors on machine. Then, the HGA method is incorporated into the neural network training to optimize its layer numbers and neurons in each layer. These two schemes provide an efficient and accurate thermal error compensation for CNC machine tools. The thermal error compensation technique built in this study can be applied to any type of CNC machine tool because the error model parameters are only calculated mathematically
{"title":"Thermal Error Modeling of a Machining Center using Grey System Theory and HGA-Trained Neural Network","authors":"Kun-Chieh Wang","doi":"10.1109/ICCIS.2006.252298","DOIUrl":"https://doi.org/10.1109/ICCIS.2006.252298","url":null,"abstract":"The thermal effect on machine tools has become a well-recognized problem in response to the increasing requirement of product quality. The performance of a thermal error compensation system strongly depends on the accuracy of the thermal error model. This paper presents a novel thermal error modeling technique including two mathematic schemes: GM(1,N) model of the grey system theory and the hierarchy-genetic-algorithm (HGA) trained neural network in order to map the temperature ascent against thermal drift of the machine tool. Fist, the GM(1,N) scheme of the grey system theory was applied to minimize the numbers of the temperature sensors on machine. Then, the HGA method is incorporated into the neural network training to optimize its layer numbers and neurons in each layer. These two schemes provide an efficient and accurate thermal error compensation for CNC machine tools. The thermal error compensation technique built in this study can be applied to any type of CNC machine tool because the error model parameters are only calculated mathematically","PeriodicalId":296028,"journal":{"name":"2006 IEEE Conference on Cybernetics and Intelligent Systems","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114905735","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}
It is the purpose of this paper to introduce the advantages of grey predictor controllers. We adopt grey prediction to obtain simple and effective estimated values, and, with the aid of first-order low-pass alpha filter, greatly improve the accuracy subsequently used in the prediction for system response. The result will be in turn used to predict error and furthermore automatically adjust the parametrical values of PID controller, and accordingly will be able to deal with the possible variation of system responses at the very first stage. It can not only actively promote the responses efficiency of transient response, but also passively prevent disturbance. As a matter of fact, the highest demand of "plug in and play" can be met without any need to adjust the parameter. This paper will give a detailed specification of the system structure, the design, and the concept, as well as prove the modulation function of grey predictor controllers in unit step response by means of Matlab program simulation and mathematical argumentation. In transient response, it will effectively fasten rising time, shorten settling time, and oppress overshoot; meanwhile, in steady state response, it is able to reduce steady state error to zero and achieve what traditional PID cannot perform
{"title":"An Auto-tuning PID Regulator Using Grey Predictor","authors":"Ching-Yi Hsu, Shuen-Jeng Lin, Wei-Liang Chien, Chia-Chang Tong","doi":"10.1109/ICCIS.2006.252317","DOIUrl":"https://doi.org/10.1109/ICCIS.2006.252317","url":null,"abstract":"It is the purpose of this paper to introduce the advantages of grey predictor controllers. We adopt grey prediction to obtain simple and effective estimated values, and, with the aid of first-order low-pass alpha filter, greatly improve the accuracy subsequently used in the prediction for system response. The result will be in turn used to predict error and furthermore automatically adjust the parametrical values of PID controller, and accordingly will be able to deal with the possible variation of system responses at the very first stage. It can not only actively promote the responses efficiency of transient response, but also passively prevent disturbance. As a matter of fact, the highest demand of \"plug in and play\" can be met without any need to adjust the parameter. This paper will give a detailed specification of the system structure, the design, and the concept, as well as prove the modulation function of grey predictor controllers in unit step response by means of Matlab program simulation and mathematical argumentation. In transient response, it will effectively fasten rising time, shorten settling time, and oppress overshoot; meanwhile, in steady state response, it is able to reduce steady state error to zero and achieve what traditional PID cannot perform","PeriodicalId":296028,"journal":{"name":"2006 IEEE Conference on Cybernetics and Intelligent Systems","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117116865","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 : 2006-06-07DOI: 10.1109/ICCIS.2006.252305
A.S. Jamab, Babak Nadjar Araabi
A self-constructing version of locally linear model tree (LOLIMOT) algorithm for structure identification in neuro-fuzzy models is proposed in this paper. LOLIMOT is an incremental tree-construction learning algorithm that partitions the input space by axis-orthogonal splits. In each iteration, LOLIMOT splits a local model into two models in a way that a local classification error is minimized. As a result, during the training procedure some of the formerly made divisions may become suboptimal or even superfluous. In this paper, the LOLIMOT is improved in two ways: (1) the ability to merge previously divided local linear models is added, and (2) a simulated annealing stochastic decision process is responsible to select a local model for splitting. Comparing to the LOLIMOT, our proposed improved learning algorithm shows the ability to construct models with fewer number of rules at comparable modeling errors. Algorithms are compared through a case study of nonlinear function approximation. Obtained results demonstrate the better performance of modified method as compared to that of original form of the LOLIMOT algorithm
{"title":"A Learning Algorithm for Local Linear Neuro-fuzzy Models with Self-construction through Merge & Split","authors":"A.S. Jamab, Babak Nadjar Araabi","doi":"10.1109/ICCIS.2006.252305","DOIUrl":"https://doi.org/10.1109/ICCIS.2006.252305","url":null,"abstract":"A self-constructing version of locally linear model tree (LOLIMOT) algorithm for structure identification in neuro-fuzzy models is proposed in this paper. LOLIMOT is an incremental tree-construction learning algorithm that partitions the input space by axis-orthogonal splits. In each iteration, LOLIMOT splits a local model into two models in a way that a local classification error is minimized. As a result, during the training procedure some of the formerly made divisions may become suboptimal or even superfluous. In this paper, the LOLIMOT is improved in two ways: (1) the ability to merge previously divided local linear models is added, and (2) a simulated annealing stochastic decision process is responsible to select a local model for splitting. Comparing to the LOLIMOT, our proposed improved learning algorithm shows the ability to construct models with fewer number of rules at comparable modeling errors. Algorithms are compared through a case study of nonlinear function approximation. Obtained results demonstrate the better performance of modified method as compared to that of original form of the LOLIMOT algorithm","PeriodicalId":296028,"journal":{"name":"2006 IEEE Conference on Cybernetics and Intelligent Systems","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124079208","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 : 2006-06-07DOI: 10.1109/ICCIS.2006.252248
T. Takahama, S. Sakai
The epsiv constrained method is an algorithm transformation method, which can convert algorithms for unconstrained problems to algorithms for constrained problems using the epsiv level comparison that compares the search points based on the constraint violation of them. We proposed the epsiv constrained particle swarm optimizer epsivPSO, which is the combination of the epsiv constrained method and particle swarm optimization. In the epsivPSO, the agents who satisfy the constraints move to optimize the objective function and the agents who don't satisfy the constraints move to satisfy the constraints. But sometimes the velocity of agents becomes too big and they fly away from feasible region. In this study, to solve this problem, we propose to divide agents into some groups and control the maximum velocity of agents adaptively by comparing the movement of agents in each group. The effectiveness of the improved epsivPSO is shown by comparing it with various methods on well known nonlinear constrained problems
{"title":"Solving Constrained Optimization Problems by the ε Constrained Particle Swarm Optimizer with Adaptive Velocity Limit Control","authors":"T. Takahama, S. Sakai","doi":"10.1109/ICCIS.2006.252248","DOIUrl":"https://doi.org/10.1109/ICCIS.2006.252248","url":null,"abstract":"The epsiv constrained method is an algorithm transformation method, which can convert algorithms for unconstrained problems to algorithms for constrained problems using the epsiv level comparison that compares the search points based on the constraint violation of them. We proposed the epsiv constrained particle swarm optimizer epsivPSO, which is the combination of the epsiv constrained method and particle swarm optimization. In the epsivPSO, the agents who satisfy the constraints move to optimize the objective function and the agents who don't satisfy the constraints move to satisfy the constraints. But sometimes the velocity of agents becomes too big and they fly away from feasible region. In this study, to solve this problem, we propose to divide agents into some groups and control the maximum velocity of agents adaptively by comparing the movement of agents in each group. The effectiveness of the improved epsivPSO is shown by comparing it with various methods on well known nonlinear constrained problems","PeriodicalId":296028,"journal":{"name":"2006 IEEE Conference on Cybernetics and Intelligent Systems","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114629907","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 : 2006-06-07DOI: 10.1109/ICCIS.2006.252289
Y. Nguwi, A. Kouzani
An automatic road sign recognition system identifies road signs from within images captured by an imaging sensor on-board of a vehicle, and assists the driver to properly operate the vehicle. Most existing systems include a detection phase and a classification phase. This paper classifies the methods applied to road sign recognition into three groups: colour-based, shape-based, and others. In this paper, the issues associated with automatic road sign recognition are addressed, the popular existing methods developed to tackle the road sign recognition problem are reviewed, and a comparison of the features of these methods is given
{"title":"A Study on Automatic Recognition of Road Signs","authors":"Y. Nguwi, A. Kouzani","doi":"10.1109/ICCIS.2006.252289","DOIUrl":"https://doi.org/10.1109/ICCIS.2006.252289","url":null,"abstract":"An automatic road sign recognition system identifies road signs from within images captured by an imaging sensor on-board of a vehicle, and assists the driver to properly operate the vehicle. Most existing systems include a detection phase and a classification phase. This paper classifies the methods applied to road sign recognition into three groups: colour-based, shape-based, and others. In this paper, the issues associated with automatic road sign recognition are addressed, the popular existing methods developed to tackle the road sign recognition problem are reviewed, and a comparison of the features of these methods is given","PeriodicalId":296028,"journal":{"name":"2006 IEEE Conference on Cybernetics and Intelligent Systems","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132771869","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：