摘要 :
This paper introduces how to use multi-valued PCNN (Pulse Coupled Neural Network) proposed in this paper to do classification. 2-dimensional data can be projected onto two-dimensional PCNN locally laterally linked. Different pulse...
展开
This paper introduces how to use multi-valued PCNN (Pulse Coupled Neural Network) proposed in this paper to do classification. 2-dimensional data can be projected onto two-dimensional PCNN locally laterally linked. Different pulse waves generated by training data label different regions corresponding to different classes. The same pulse wave labels the region corresponding to the same class. Meeting of different pulse waves obtains the separatrixes of different classes. In order to differentiate different pulse waves, outputs of neurons in PCNN should be multi-valued. We call networks composed of these neurons multi-valued PCNNs. The number of classes determines the number of output value of each neuron. N-valued PCNN can be used to classify N-1 different classes. Experimental results of the 2-dimensional salmon-weever classification show that the correct recognition rate of test set is 98.11% (3477/3544) when training samples are only 10% of all samples.
收起
摘要 :
This paper introduces how to use multi-valued PCNN (Pulse Coupled Neural Network) proposed in this paper to do classification. 2-dimensional data can be projected onto two-dimensional PCNN locally laterally linked. Different pulse...
展开
This paper introduces how to use multi-valued PCNN (Pulse Coupled Neural Network) proposed in this paper to do classification. 2-dimensional data can be projected onto two-dimensional PCNN locally laterally linked. Different pulse waves generated by training data label different regions corresponding to different classes. The same pulse wave labels the region corresponding to the same class. Meeting of different pulse waves obtains the separatrixes of different classes. In order to differentiate different pulse waves, outputs of neurons in PCNN should be multi-valued. We call networks composed of these neurons multi-valued PCNNs. The number of classes determines the number of output value of each neuron. N-valued PCNN can be used to classify N-1 different classes. Experimental results of the 2-dimensional salmon-weever classification show that the correct recognition rate of test set is 98.11% (3477/3544) when training samples are only 10% of all samples.
收起
摘要 :
This paper proposes a novel image segmentation algorithm based on Pulse Coupled Neural Network (PCNN).Unlike the traditional PCNN image segmentation methods, the presented algorithm can achieve the optimum parameters automatically...
展开
This paper proposes a novel image segmentation algorithm based on Pulse Coupled Neural Network (PCNN).Unlike the traditional PCNN image segmentation methods, the presented algorithm can achieve the optimum parameters automatically. Experimental results show its good performance and robustness. The research fruits have great importance both on the theory research and practical application of PCNN.
收起
摘要 :
This paper proposes a novel image segmentation algorithm based on Pulse Coupled Neural Network (PCNN). Unlike the traditional PCNN image segmentation methods, the presented algorithm can achieve the optimum parameters automaticall...
展开
This paper proposes a novel image segmentation algorithm based on Pulse Coupled Neural Network (PCNN). Unlike the traditional PCNN image segmentation methods, the presented algorithm can achieve the optimum parameters automatically. Experimental results show its good performance and robustness. The research fruits have great importance both on the theory research and practical application of PCNN.
收起
摘要 :
A novel method is proposed to detect and filter pepper and salt noise in an image based on Pulse Coupled Neural Network (PCNN) firing matrix, which contains the spatial information and time information of the original image. The P...
展开
A novel method is proposed to detect and filter pepper and salt noise in an image based on Pulse Coupled Neural Network (PCNN) firing matrix, which contains the spatial information and time information of the original image. The PCNN structure is simplified to avoid selecting too many parameters, which a unidirectional decaying threshold is proposed. The pixels polluted by noise are detected through analyzing and processing the PCNN firing matrix then the noisy pixels are filtered by median filter, which is proved to be effective in removing pepper and salt noise. The window size of the filter and the filtering time for noisy pixels are adaptively determined by calculating the noise intensity of the contaminated image. The experiment result demonstrates that the proposed method illustrates better performance in removing noise while conserving image edges and details than traditional filter does.
收起
摘要 :
The pulse-coupled neural network (PCNN) algorithm is an efficient method widely used in image segmentation. Parameters adjusting is usually difficult in a classic model of PCNN. In this study the pulse-coupled neural network model...
展开
The pulse-coupled neural network (PCNN) algorithm is an efficient method widely used in image segmentation. Parameters adjusting is usually difficult in a classic model of PCNN. In this study the pulse-coupled neural network model was simplified for optimal segmentation by reducing the number of parameters of PCNN. In addition, the local standard deviation was utilized for adjusting the connection strength coefficient adaptively. The simplified PCNN was used for separating the cucumber from complex background in a cucumber image effectively. To evaluate the performance of this algorithm, a simple evaluation method was designed for evaluating the segmentation image. The experimental results show that the average rate of correct segmentation reaches up to 82.4%.
收起
摘要 :
The pulse-coupled neural network (PCNN) algorithm is an efficient method widely used in image segmentation. Parameters adjusting is usually difficult in a classic model of PCNN. In this study the pulse-coupled neural network model...
展开
The pulse-coupled neural network (PCNN) algorithm is an efficient method widely used in image segmentation. Parameters adjusting is usually difficult in a classic model of PCNN. In this study the pulse-coupled neural network model was simplified for optimal segmentation by reducing the number of parameters of PCNN. In addition, the local standard deviation was utilized for adjusting the connection strength coefficient adaptively. The simplified PCNN was used for separating the cucumber from complex background in a cucumber image effectively. To evaluate the performance of this algorithm, a simple evaluation method was designed for evaluating the segmentation image. The experimental results show that the average rate of correct segmentation reaches up to 82.4%.
收起
摘要 :
The pulse-coupled neural network (PCNN) algorithm is an efficient method widely used in image segmentation. Parameters adjusting is usually difficult in a classic model of PCNN. In this study the pulse-coupled neural network model...
展开
The pulse-coupled neural network (PCNN) algorithm is an efficient method widely used in image segmentation. Parameters adjusting is usually difficult in a classic model of PCNN. In this study the pulse-coupled neural network model was simplified for optimal segmentation by reducing the number of parameters of PCNN. In addition, the local standard deviation was utilized for adjusting the connection strength coefficient adaptively. The simplified PCNN was used for separating the cucumber from complex background in a cucumber image effectively. To evaluate the performance of this algorithm, a simple evaluation method was designed for evaluating the segmentation image. The experimental results show that the average rate of correct segmentation reaches up to 82.4%.
收起
摘要 :
Autowave travelling of Discrete Pulse Coupled Neural Networks(PCNNs) is of much importance in dealing with image processing and combinatorial optimization with PCNNs. This paper presents the condition for the autowave to spread in...
展开
Autowave travelling of Discrete Pulse Coupled Neural Networks(PCNNs) is of much importance in dealing with image processing and combinatorial optimization with PCNNs. This paper presents the condition for the autowave to spread in the PCNN on the stimulus of neurons in it. The condition is that whenever the intensity of stimulus to the neurons is in the range of an exponentially decreasing band along the neurons that are from the autowave source neuron, the autowave could spread out along the neurons in the net. The spreading ability respect to the parameters of the PCNN is studied. Finally, a large number of experiments show a concrete consistency with our theoretical results.
收起
摘要 :
Autowave travelling of Discrete Pulse Coupled Neural Networks(PCNNs) is of much importance in dealing with image processing and combinatorial optimization with PCNNs. This paper presents the condition for the autowave to spread in...
展开
Autowave travelling of Discrete Pulse Coupled Neural Networks(PCNNs) is of much importance in dealing with image processing and combinatorial optimization with PCNNs. This paper presents the condition for the autowave to spread in the PCNN on the stimulus of neurons in it. The condition is that whenever the intensity of stimulus to the neurons is in the range of an exponentially decreasing band along the neurons that are from the autowave source neuron, the autowave could spread out along the neurons in the net. The spreading ability respect to the parameters of the PCNN is studied. Finally, a large number of experiments show a concrete consistency with our theoretical results.
收起
原文获取