基于调和模型神经网络的彩色图像复原研究

针对彩色图像复原提出了基于网络能量递减收敛的调和模型神经网络图像复原方法,研究了该方法在运动模糊图像复原上的应用。利用待复原图像重构出多幅模糊图像用于算法的实现,并首次提出基于图像局部方差的自适应正则化算子的实现方法。实验结果表明,该方法是有效的,复原效果优于有约束的最小二乘复原法和已有的传统神经网络图像复原法,对复原图像的信噪比有一定的提高。     

模糊细胞神经网络在书法碑帖汉字重构中的应用

模糊细胞神经网络作为一种模拟逻辑可编程并行网络,可以用来实时实现数学形态学的全部基本算子。文中基于加性模糊细胞神经网络结构,应用数学形态学的重构算法,研究中国书法碑帖在自然腐蚀噪声环境下的去噪和汉字提取问题,并给出了算法的伪代码描述和数字计算信息结果。该方法可应用于书法碑帖的汉字处理和实时重构。     

基于模糊聚类分析的模糊神经网络结构的优化

该文讨论了模糊聚类分析在模糊神经网络结构的确定中的应用。通过将模糊C－均值算法、有效性函数和模糊指数相结合,给出了模糊神经网络结构确定的方法,并且给出了应用该算法具体的模糊神经网络模型。     

基于改进T-S模糊神经网络的交通流量预测

在萤火虫优化算法和T-S模糊神经网络的基础上,提出了一种采用萤火虫算法优化的T-s模糊神经网络预测交通流量的算法。该算法利用萤火虫算法得到T_s模糊神经网络的最优参数配置,从而能发挥T-s模糊神经网络泛化的映射能力。将该算法应用到实测交通流中进行算法的有效性验证,并与传统的T-s模糊神经网络和遗传算法优化的T-S模糊神经网络进行比较,仿真结果表明该算法具有更高的预测准确性,从而证明了该算法在交通流量预测领域的可行性和有效性。     

神经网络在彩色图像压缩中的应用

文中旨在提出一种基于神经网络的图像压缩算法对彩色图像信息进行处理,从而减少大规模彩色图像的冗余度,方便其传输、存储及加密等。该算法通过将BP（Back Propagation）神经网络用于彩色图像压缩,利用其多层前馈网络的模式变化能力,实现了对由RGB编码得到的彩色图像数字矩阵进行的压缩编码。经Matlab仿真实验表明,该算法具有良好的压缩效果,且与灰度编码下的图像压缩结果对比,具有更好的压缩效率及保真效果,并能有效地保留原彩色图像的色彩信息,能够满足彩色图像压缩处理的要求。     

多方向模糊形态学彩色图像边缘检测算法*

提出了一种多方向模糊形态学彩色图像边缘检测算法,并将灰度模糊形态学推广到彩色图像。首先采用隶属度函数将彩色图像映射到模糊域;然后采用多方向模糊形态学在R、G、B三个分量上进行边缘检测;最后合成各分量的边缘,得到最终彩色图像边缘。仿真实验证明,该算法能够较好地检测彩色图像边缘,检测结果优于传统的边缘检测算子,并能够检测出彩色图像中的模糊边缘。     

模糊C-均值聚类引导的Kinect深度图像修复算法

针对Kinect传感器所采集的深度图像中存在大面积空洞的问题,提出了一种模糊C-均值聚类引导的深度图像修复算法。该算法将同步获取的彩色图像和深度图像作为输入;利用模糊C-均值聚类算法对彩色图像进行聚类,聚类结果作为引导图像;然后对每个深度图像中的大面积空洞区域,利用改进的快速行进算法,从空洞边缘向空洞内部逐层修复空洞区域;最后,利用改进的双边滤波算法去除图像中的散粒噪声。实验表明该算法能有效修复Kinect深度图像中的空洞,修复后的图像在平滑度和边缘强度上优于传统算法。     

基于双模式联合三边滤波器的深度图像超分辨率方法

彩色图像引导的深度图像超分辨率方法通过利用高分辨率彩色图像的高频信息来重建深度图像,取得了不错的重建效果,但当深度图像和彩色图像边缘不(完全)一致或彩色区域纹理丰富时,重建图像普遍存在边缘模糊和纹理拷贝问题.针对这一问题,提出一种边缘图像引导的双模式联合三边滤波器(DMJTF)方法.该方法利用单幅低分辨率深度图像构建了一个边缘图像金字塔字典,然后利用MRF模型构建了一个高分辨率边缘图像,该图像确定了滤波器的两种模式,分别用于重构深度图像的边缘和平滑区域.实验结果表明DMJTF算法有效地避免了纹理拷贝异常,降低了边缘模糊现象,在定性和定量两个方面都优于其他算法,取得了较好的超分效果.     

DE优化T-S模糊神经网络的交通流量预测

提出了一种差分进化算法优化T-S模糊神经网络预测交通流量的算法方法.该算法利用差分进化来弥补T-S模糊神经网络连接权值和阂值选择上的随机性缺陷,从而能发挥T-S模糊神经网络泛化的映射能力,而且能使T-S模糊神经网络具有较快的收敛性以及较强的学习能力.将该算法应用到实测交通流进行算法的有效性验证,并与传统的T-S模糊神经网络进行比较,仿真结果表明,该算法具有更好的非线性拟合能力和更高的预测准确性,在交通流量预测领域具备可行性和有效性.     

模糊小波神经网络的研究及其应用

针对小波神经网络训练时间较长且易陷入局部极小值的缺点,文章提出了将小波神经网络融合模糊算法的方法,并建立了模糊小波神经网络模型及其训练算法,给出了该模型在变频调速系统故障预测中的应用实例。应用结果表明,模糊小波神经网络提高了网络训练速度,达到了优良的函数逼近效果。     

Color image segmentation: advances and prospects

Image segmentation is very essential and critical to image processing and pattern recognition. This survey provides a summary of color image segmentation techniques available now. Basically, color segmentation approaches are based on monochrome segmentation approaches operating in different color spaces. Therefore, we first discuss the major segmentation approaches for segmenting monochrome images: histogram thresholding, characteristic feature clustering, edge detection, region-based methods, fuzzy techniques, neural networks, etc.; then review some major color representation methods and their advantages/disadvantages; finally summarize the color image segmentation techniques using different color representations. The usage of color models for image segmentation is also discussed. Some novel approaches such as fuzzy method and physics-based method are investigated as well.     

Color image associative memory on a class of Cohen-Grossberg networks

In this paper, neural associative memories for storing gray-scale and true color images are presented based on a class of reduced Cohen-Grossberg neural networks. Some fundamental conditions for endowing the networks with retrieval properties are proposed. Moreover, a system designing procedure is developed by using matrix decomposition. Numerical simulations show that the constructed networks can act as reliable noise-reducing systems for storing and retrieving color images.     

Comparison of crisp and fuzzy character neural networks inhandwritten word recognition

Experiments comparing neural networks trained with crisp and fuzzy desired outputs are described. A handwritten word recognition algorithm using the neural networks for character level confidence assignment was tested on images of words taken from the United States Postal Service mailstream. The fuzzy outputs were defined using a fuzzy k-nearest neighbor algorithm. The crisp networks slightly outperformed the fuzzy networks at the character level but the fuzzy networks outperformed the crisp networks at the word level. This empirical result is interpreted as an example of the principle of least commitment     

水下光学图像重建方法研究进展

水下光学图像可以提供直观丰富的海洋信息,近年来在海洋资源开发、环境保护和海洋工程等诸多领域发挥越来越重要的作用。但是受恶劣复杂的水下成像环境影响,水下光学图像普遍存在对比度低、图像模糊以及颜色失真等质量退化问题,严重制约水下智能处理系统的性能和应用。如何清晰地重建水下光学图像是国内外广泛关注的、具有挑战性的难点问题。随着深度学习技术的蓬勃发展,利用深度学习来提升水下图像质量成为当前的研究热点。鉴于目前国内在水下光学图像重建方面的研究综述较少,本文全面综述其研究进展。分析了水下图像退化机理,总结了现有水下成像模型以及水下图像重建的挑战;梳理了水下光学图像重建方法的发展历程,根据是否采用深度学习以及是否基于成像模型,将现有方法分为4大类,并按照研究发展顺序,依次介绍4类方法的基本思想,分析其优缺点;归纳了目前公开的水下图像数据集以及常用的水下图像质量评价方法,并对8种典型的水下图像重建方法进行了性能评测和对比分析;总结了该领域目前仍存在的问题,展望了后续研究方向,以便于相关研究人员了解该领域的研究现状,促进该领域的技术发展。     

模糊神经网络在图像目标检测中的应用

红外图像中的微弱目标检测与跟踪是数字图像处理领域中的研究热点。针对红外图像中微弱目标灰度的统计特点以及模糊神经网络在自适应噪声消除的应用,提出一种基于增强型动态模糊神经网络算法用于红外图像噪声消除。经过自适应噪声消除后,可有效的有自动阈值门限分割法进行微弱目标检测。     

基于模糊熵和BP神经网络的彩色图像边缘检测

在RGB颜色空间中,分别提取R、G、B三个分量并计算R、G、B三个分量的组合V,通过引入模糊熵,构造出4个基于模糊熵的信息测度分量来定量描述彩色图像的边缘特征,并将4个测度分量组成一个整体的特征向量,计算训练图像的特征向量作为样本对BP网络进行训练,然后将训练的BP网络直接用于边缘检测。该方法充分考虑了颜色空间中各颜色分量以及它们之间的相关性;BP网络的结构和训练都比较简单;实验表明,改进方法具有较强的细节保持能力,对弱边缘具有较强的检测能力。     

Exponential Synchronization of Stochastic Fuzzy Cellular Neural Networks with Reaction-Diffusion Terms via Periodically Intermittent Control

This paper considers the exponential synchronization of stochastic fuzzy cellular neural networks with time-varying delays and reaction-diffusion terms based on p-norm. Motivated by the achievements from both the stability of fuzzy cellular neural networks with stochastic perturbation and reaction-diffusion effects and the synchronization issue of coupled chaotic delayed neural networks by using periodically intermittent control approach, a periodically intermittent controller is proposed to guarantee the exponential synchronization of the coupled chaotic neural networks by using Lyapunov stability theory and stochastic analysis approaches. The synchronization results presented in this paper generalize and improve many known results. This paper also presents an illustrative example and uses simulated results of this example to show the feasibility and effectiveness of the proposed scheme.     

Reconstruction problem and information granularity

The paper elaborates on the representation and reconstruction of numerical and nonnumerical data in fuzzy modeling. Proposed are general criteria leading to the distortion-free interfacing mechanisms that help transform information between the systems (or modeling environments) operating at different levels of information granularity. Distinguished are three basic categories of information: numerical, interval-valued, and linguistic (fuzzy). Since all of them are dealt with here, the paper subsumes the current studies concentrated exclusively on representing fuzzy sets through their numerical representatives (prototypes). The algorithmic framework in which the distortion-free interfacing is completed is realized through neural networks. Each category of information is treated separately and gives rise to its own specialized architecture of the neural network. Similarly, these networks require carefully designed training sets that fully capture the specificity of the reconstruction problem. Several carefully selected numerical examples are aimed at the illustration of the key ideas     

Neural network-based text location in color images

This paper proposes neural network-based text locations in complex color images. Texture information extracted on several color bands using neural networks is combined and corresponding text location algorithms are then developed. Text extraction filters can be automatically constructed using neural networks. Comparisons with other text location methods are presented; indicating that the proposed system has a better accuracy.