课程文献中心 更多>>

关键词： 医学图像融合   双通道   脉冲耦合神经网络   链接强度   空间频域  

摘要： 通过对双通道脉冲神经网络模型的改进,提出了一种邻域SEML激励的自适应双通道脉冲耦合神经网络医学图像融合的新方法。即通过提高模型的性能和脉冲神经网络进行自动化图像处理的能力。首先介绍了双通道脉冲耦合神经网络模型及其原理,然后阐述了基于这一模型的一种新融合算法,最后对本文融合算法以及各传统融合算法得到的实验仿真结果进行了分析。

关键词： 交通标志   脉冲耦合神经网络   自动波扩散   类Euclidean距离   特征提取  

摘要： 脉冲耦合神经网络(PCNN)提取的特征序列的旋转不变性降低了道路交通标志类内匹配识别的准确性,为了提取更有利于形状分类的特征向量,本文利用PCNN的自动波扩散特性,简化了PCNN模型。采用简化PCNN模型产生的类Euclidean距离图像作为分类特征,利用最小方差值进行匹配分析,并通过实验选取了最佳PCNN参数。针对道路交通标志图像库GB5768-1999的实验结果表明,采用获得的类Euclidean距离图像作为特征向量进行分类匹配,在选定边缘图像的迭代次数N为16,反馈输入固有电势VF为0.65,动态门限固有电势VT为100,卷积核矩阵为5×5时,最小方差值均出现在对应的标准图像位置。结果表明,简化PCNN的类Euclidean距离变换能够有效提取二值边缘图像的形状信息。该方法优于传统PCNN熵序列的特征向量方法,类内区分效果更加明显。

关键词： 图像融合   脉冲耦合神经网络   多聚焦图像  

摘要： 脉冲耦合神经网络模型PCNN(Pulse Coupled Neural Network)运行时间长、效率低等特点,现提出了一种改进的脉冲耦合神经网络模型用于图像融合。通过对多聚焦距图像和医学图像进行了实验,同时与小波变换、拉普拉斯变换等图像融合算法进行了比较。研究结果表明:方法简化了PCNN模型,减少了PCNN运行的时间。在主观视觉和客观评价上均具有良好的效果。

关键词： 图像插值   脉冲耦合神经网络   图像插值   集群   视觉效果  

摘要： 为解决数字图像插值过程中边缘锯齿和图像模糊问题,提出一种基于脉冲耦合神经网络(PCNN)的图像插值算法。利用PCNN同步脉冲发放特性,获取图像的各个集群及点火路径,对集群内和集群间隙的像素采用不同插值方法完成整幅图像的插值。实验结果表明,与双线性插值和三次B样条插值方法相比,该算法在主观视觉效果方面有所改善,峰值信噪比均获得0.2 dB以上的提高。

关键词： Time-to-First-Spike编码   Sigmoid函数   脉冲神经网络   图像分割   感受野   最大香农熵  

摘要： 针对脉冲神经网络图像分割中的脉冲编码问题,基于Time-to-First-Spike编码策略提出2种编码方式:线性编码和非线性编码。线性编码方法采用从图像像素值到神经元脉冲发放时间的线性函数对应关系,而非线性编码方法采用Sigmoid函数的对应关系。应用2种方法对图像进行分割,实验结果表明,非线性编码方法的分割结果优于线性编码方法,分割图像具有更大的香农熵值,并且非线性编码方法在图像分割时具有更大的取值区间,更容易对参数进行选择,取得最佳的图像分割结果。

关键词： methods: data analysis   stars: neutron   pulsars: general  

摘要： We present 75 pulsars discovered in the mid-latitude portion of the High Time Resolution Universe survey, 54 of which have full timing solutions. All the pulsars have spin periods greater than 100 ms, and none of those with timing solutions is in binaries. Two display particularly interesting behaviour;PSR J1054-5944 is found to be an intermittent pulsar, and PSR J1809-0119 has glitched twice since its discovery. In the second half of the paper we discuss the development and application of an artificial neural network in the data-processing pipeline for the survey. We discuss the tests that were used to generate scores and find that our neural network was able to reject over 99 per cent of the candidates produced in the data processing, and able to blindly detect 85 per cent of pulsars. We suggest that improvements to the accuracy should be possible if further care is taken when training an artificial neural network;for example, ensuring that a representative sample of the pulsar population is used during the training process, or the use of different artificial neural networks for the detection of different types of pulsars.

关键词： Lyapunov functions  

摘要： In this paper, a new concept called average impulsive occurring interval is introduced to describe the impulsive sequences by referring to the concept of average dwell time. Based on the average impulsive occurring interval concept and Lyapunov stability theory, the globally exponential stability of a genetic network under mixed impulsive control is investigated and some stable criterions are obtained. Different from the existing results, both destabilizing and stabilizing impulsive control are considered in the neural networks simultaneously. The destabilizing and stabilizing impulses are assumed to be time-varying and take values from two finite sets {μ1, μ2, , μN1} and {γ1, γ2, , γN2}, respectively. Finally, an illustrative example is provided to show the validity of the theoretical results. Copyright © 2012 Binary Information Press.

关键词： 点云曲面   点云曲面去噪   脉冲耦合神经网络   双边滤波  

摘要： 提出一种基于脉冲耦合神经网络(PCNN)的点云曲面去噪算法.该算法主要分为两步:噪声点定位和噪声点滤波.首先针对点云曲面构建一个PCNN神经网络,各个神经元的外部刺激值由邻近点的几何位置差异和法向差异构成,利用神经元输出的自适应点火捕获特性,实现了噪声点的定位;而后针对点云曲面中的噪声点,基于网格光顺中双边滤波的思想,实现噪声点的滤波,对于非噪声点,则保持原有的几何位置不变.实验结果表明,由于区分了噪声点和非噪声点,该算法较传统的点云曲面去噪算法能更加有效的去除噪声的同时并保持模型的几何特征.

关键词： PCNN   图像分割   同步脉冲   调制耦合  

摘要： 脉冲耦合神经网络PCNN是一种新的模拟生物视觉的连接模型,更接近于人类大脑视觉皮层的视觉机理。在图像分割、图像融合、图像增强、目标识别等方面都广泛的应用。根据其改进方程,验证了PCNN在图像分割中的效果,结果证明在复杂图像中还需要增加像素空间信息。

关键词： Image segmentation  

摘要： Pulse coupled neural network (PCNN), as a well-known efficient method for image processing, has its original advantage because of its biological background. However, when it is used to image processing, its performance strongly depends on the appropriate values of PCNN's parameters. Moreover, the values of the parameters are not self-adapting according to different images. Considering that, the paper proposed a new method based on modified differential evolution algorithm (MDE) to determine the suitable parameters of PCNN automatically. In this method, the MDE algorithm searches automatically the space of solution until finding the optimal solutions. Simulation results illustrate that the proposed method is accuracy and efficiency.