基于堆栈滤波器和Hopfield神经网络的边界检测法

提出了一种基于堆栈滤波器和Ｈｏｐｆｉｅｌｄ神经网络的边界检测法,采用较小滤波窗口的堆栈滤波器优化估计的图象象素点之间的灰度梯度,再根据这些灰度梯度的优化估计值计算及确定Ｈｏｐｆｉｅｌｄ神经网络的权重矢量,Ｈｏｐｆｉｅｌｄ神经网络收剑时输出图象的边界。相对于基于堆栈滤波器边界检测法,该方法对堆栈滤波器的优化训练速度大大提高,所需内存大为减少,而相对于基于Ｈｏｐｆｉｅｌｄ神经网络的边界检测法,该方法又     

一种新的基于统计向量和神经网络的边缘检测方法

通过构造不同的统计量定量描述了边缘点邻域灰度的分布特征,并将4个统计量组成统计向量.计算训练图像的统计向量作为样本对BP神经网络训练,然后将训练的BP网络直接用于边缘检测.新方法在统计向量的构造上充分考虑了边缘点和噪声点的区别,具有较好的抗噪性能;BP网络的结构和训练都比较简单;而且不需要设定阈值检测边缘.实验表明,新方法抗噪性能好,达到了令人满意的边缘检测效果.     

基于神经网络与模糊算法图像边缘检测方法*

针对传统图像边缘检测方法中出现毛边、噪边、边缘定位不精确等缺点,提出一种神经网络与模糊算法相结合的检测方法。根据图像特征,将图像分为高频和低频部分分别处理,高频部分适宜用双层网络结构,可以很好地减弱噪声;对于图像低频部分,将模糊理论引入到边缘检测中,能够检测出弱边。最后对检测出的两个图像边缘进行融合,实验结果证明得出的检测效果较好,比传统边缘检测算子所获结果有很大改善。     

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。     

A high performance edge detector based on fuzzy inference rules

Edge detection is an important topic in computer vision and image processing. In this paper, a novel edge detector based on fuzzy If-Then inference rules and edge continuity is proposed. The fuzzy If-Then rule system is designed to model edge continuity criteria. The maximum entropy principle is used in the parameter adjusting process. We also discuss the related issues in designing fuzzy edge detectors. We compare it with the popular edge detectors: Sobel and Canny edge detectors. The proposed fuzzy edge detector does not need parameter setting as Canny edge detector does, and it can preserve an appropriate detection in details. It is very robust to noise and can work well under high level noise situations, while other edge detectors cannot. The detector efficiently extracts edges in images corrupted by noise without requiring the filtering process. The experimental results demonstrate the superiority of the proposed method to existing ones.     

基于图像特征与面向对象BP算法的边缘检测

提出了一种基于图像特征与面向对象BP神经网络的边缘检测方法。首先，在图像特征的选取上，充分考虑边缘和噪声的本质区别，构造具有较强抗噪能力的特征向量；然后用经人工处理的样本对BP网络进行训练，将训练后的网络用于图像的边缘检测。     

模糊Hopfield网络的收敛性与鲁棒性分析

收敛性与鲁棒性是模糊神经网络的两个重要性质。对带阈值的Max-T模糊Hopfield神经网络（记为Max-T-C FHNN）的收敛性及在训练模式小幅摄动情况下的鲁棒性进行了分析,从理论上给出了严格的证明。发现了采用最大权值矩阵学习算法时,Max-T-C FHNN具有良好的收敛性,同时当T模及其蕴含算子满足Lipschitz条件时,Max-T-C FHNN对训练模式摄动全局拥有好的鲁棒性,用自联想实验验证了理论的有效性。     

基于GPN径向基神经网络的边缘检测方法

在基于神经网络的边缘检测模型中,大部分模型的检测效率不高,检测效果也有待提升.本文受人眼视觉系统特性的启发,提出了一种新的基于GPN （Gaussian Positive-Negative）径向基神经网络的边缘检测方法.首先,本文构造了一种新型的基于GPN径向基神经网络,将图像中经高斯滤波预处理后的每个像素点作为GPN径向基神经网络的中心点,并将其输入神经网络;然后,在每层之间使用卷积神经网络的部分特性进行处理,经过扩展层和隐层计算后输出结果;最后根据输出结果利用轮廓跟踪的方法将边缘提取出来.本文在检测效果以及效率这2个方面进行了相应的数值实验.针对合成图像以及部分灰度不均匀图像,相较于脉冲耦合神经网络模型、遗传神经网络模型以及卷积神经网络模型,本文模型在效率上得到了提升,且边缘的连通性更好.实验结果表明,本文提出的基于GPN径向基神经网络的边缘检测方法是一种新的、有效的边缘检测方法,比传统的神经网络边缘检测方法效率更高,且在检测效果上也有所提升.     

Multiprocessor Task Assignment with Fuzzy Hopfield Neural Network Clustering Technique

Most scheduling applications have been demonstrated as NP-complete problems. A variety of schemes are introduced in solving those scheduling applications, such as linear programming, neural networks, and fuzzy logic. In this paper, a new approach of first analogising a scheduling problem to a clustering problem and then using a fuzzy Hopfield neural network clustering technique to solve the scheduling problem is proposed. This fuzzy Hopfield neural network algorithm integrates fuzzy c-means clustering strategies into a Hopfield neural network. This investigation utilises this new approach to demonstrate the feasibility of resolving a multiprocessor scheduling problem with no process migration and constrained times (execution time and deadline). Each process is regarded as a data sample, and every processor is taken as a cluster. Simulation results illustrate that imposing the fuzzy Hopfield neural network onto the proposed energy function provides an appropriate approach to solving this class of scheduling problem.       

基于区域一致性测度的彩色图像边缘检测

针对在RGB空间很难有效区分颜色相似性的问题,选择HSI颜色空间进行图像处理和分析。首先计算饱和度、色度、亮度等色差分量,通过引入模糊熵,构造出一组基于模糊熵的信息测度分量来定量描述图像的边缘特征。利用训练样本获取该组分量,并组成一特征向量对BP神经网络进行训练,然后将训练的BP网络直接用于边缘检测。BP网络的结构和训练比较简单,而且不需要设定阈值检测边缘。实验表明,该方法具有较强的细节保持能力,达到了令人满意的边缘检测效果。     

A rank ordered filter for medical image edge enhancement and detection using intuitionistic fuzzy set

This paper gives a novel scheme using intuitionistic fuzzy set theory to enhance the edges of medical images. Medical images contain lots of uncertainties, as they are poorly illuminated and fuzzy/vague in nature. So, direct segmentation techniques will not produce better results. There are lots of researches on edge enhancement starting from non-fuzzy to fuzzy set, but proper enhancement (highlighting important structures) is not obtained. Enhancement of edges helps in recovering the important structures that are not visible properly. Even minute pathological blood vessels/cells are not visible properly and in that case edge enhancement will enhance these blood vessels/cells. Intuitionistic fuzzy set theory is found suitable in medical image processing as it considers more (two) uncertainties as compared to fuzzy set theory. In the processing phase, image is initially converted to intuitionistic fuzzy image and intuitionistic fuzzy entropy is used to obtain the optimum value of the parameter in the membership and non-membership functions. Then it computes the total variation of the pixels with respect to the median value of the image window (rank order filtering). This enhances the borders or the edges of the image. The resulting image is then segmented (edge detected) using standard Canny's edge detector, when simply using Canny's edge detector does not give better result. From the result it is observed that on comparing with non-fuzzy and fuzzy methods, the proposed method gives better information about the images, which is helpful to the pathologists in accurate diagnosing of diseases.     

基于模糊推理的噪声图像边缘检测

对于噪声感染的图像,提出一种基于模糊推理的图像边缘检测方法。该方法将像素点的基本梯度与关联梯度作为模糊推理系统的输入变量,根据确定的模糊规则,运用模糊推理方法得到该点属于噪声的程度,从而去除由噪声引起的伪边缘,实现边缘检测。实验结果表明,与其他边缘检测方法相比,该方法可以获得较好的边缘特性,具有较强的抗噪性能。     

基于模糊神经网络火灾探测信号处理方法

针对火灾探测信号的特点,建立了火灾探测系统模型及用于处理火灾信号的模糊神经网络计算模型.利用神经网络构造模糊系统,用神经网络的自学习和自适应能力自动调整模糊系统参数,用改进的BP算法对网络进行学习和训练.根据国家标准试验火数据进行网络的学习和测试,系统误差小于试验火标准误差要求,表明了算法的有效性和可行性.     

一种对Gamma分布的SAR图像相干斑去噪方法

鉴于Gamma分布的SAR图像相干斑经对数变换后可近似为高斯分布,提出一种基于粒子群优化的BP神经网络复原去噪算法。首先用高斯噪声对无噪图像进行模糊处理,然后将结果和原图像组成训练对,用于训练优化后的神经网络,最后利用训练好的神经网络对SAR图像进行复原,从而达到去除相干斑的目的。实验表明,该算法能有效解决传统去噪算法在图像失真、边缘模糊方面的问题,收敛速度快,迭代次数少,归一化均方误差(NMSE)和峰值噪比(PSNR)效果更好。     

An Improved Method for Edge Detection and Image Segmentation Using Fuzzy Cellular Automata

Image segmentation is one of the most important and challenging problems in image processing. The main purpose of image segmentation is to partition an image into a set of disjoint regions with uniform attributes. In this study, we propose an improved method for edge detection and image segmentation using fuzzy cellular automata. In the first stage, we introduce a new edge detection method based on fuzzy cellular automata, called the texture histogram, and empirically demonstrate the efficiency of the proposed method and its robustness in denoising images. In the second stage, we propose an edge detection algorithm by considering the mean values of the edges matrix. In this algorithm, we use four fuzzy rules instead of 32 fuzzy rules reported earlier in the literature. In the third and final stage, we use the local edge in the edge detection stage to more accurately accomplish image segmentation. We demonstrate that the proposed method produces better output images in comparison with the separate segmentation and edge detection methods studied in the literature. In addition, we show that the method proposed in this study is more flexible and efficient when noise is added to an image.     

模糊PID和Hopfield神经网络在矿井通风系统中的应用

针对传统的PID控制或者单一的模糊控制无法准确控制矿井通风系统风量的问题,提出了一种采用模糊PID调节器和Hopfield神经网络调节器对矿井通风机的转速、风门、风量进行控制的方法。该方法利用模糊控制器对PID参数进行实时修正,并结合Hopfield神经网络的联想记忆功能和反馈调节特性,实现矿井通风机风量的快速、稳定输出。仿真与实验结果表明,模糊PID调节器和Hopfield神经网络调节器可以准确控制矿井通风机的转速和风量,实现通风系统的稳定输出。     

基于Hopfield神经网络的盲检测数字水印

提出了一种基于Hopfield神经网络的盲检测数字水印算法。基于噪声可见函数实现了水印的自适应嵌入,利用Hopfield神经网络记忆宿主图像以及原始水印信息。在水印检测时,通过神经网络从嵌入水印的图像中联想出宿主图像和水印嵌入信息,再利用嵌水印图像和联想出的宿主图像提取出水印,实现了水印的盲检测。     

量子Hopfield神经网络及图像识别

传统的Hopfield网络的存储容量是神经元个数的0·14倍(P=0·14N)。由于它在识别大量的图像或模式时遇到了巨大的困难,所以研究人员一直在寻找新的方法。由量子计算和神经网络结合而产生的量子神经网络是新兴和前沿的学科之一。为了提高图像识别的速度和增加图像识别量,在分析了量子线性叠加特性的基础上,提出了一种用于存储矩阵元素的基于概率分布的量子Hopfield神经网络,它在存储容量或记忆容量上提高到了神经元个数的2N倍,比传统的Hopfield神经网络有了指数级的提高。通过图像识别的实例分析和仿真试验的结果表明,该量子Hopfield神经网络能有效地识别图像或模式,并且工作过程符合量子演化过程。     

Neural edge enhancer for supervised edge enhancement from noisy images

We propose a new edge enhancer based on a modified multilayer neural network, which is called a neural edge enhancer (NEE), for enhancing the desired edges clearly from noisy images. The NEE is a supervised edge enhancer: Through training with a set of input noisy images and teaching edges, the NEE acquires the function of a desired edge enhancer. The input images are synthesized from noiseless images by addition of noise. The teaching edges are made from the noiseless images by performing the desired edge enhancer. To investigate the performance, we carried out experiments to enhance edges from noisy artificial and natural images. By comparison with conventional edge enhancers, the following was demonstrated: The NEE was robust against noise, was able to enhance continuous edges from noisy images, and was superior to the conventional edge enhancers in similarity to the desired edges. To gain insight into the nonlinear kernel of the NEE, we performed analyses on the trained NEE. The results suggested that the trained NEE acquired directional gradient operators with smoothing. Furthermore, we propose a method for edge localization for the NEE. We compared the NEE, together with the proposed edge localization method, with a leading edge detector. The NEE was proven to be useful for enhancing edges from noisy images.     

基于共生矩阵分析的自适应神经网络图像复原算法

为了保护图像中的细节信息,提出了一种基于共生矩阵聚类分析的自适应Hopfield神经网络图像复原算法．通过计算图像局部区域的共生矩阵提取其纹理特征,对共生矩阵非零元素进行聚类分析．根据聚类数量和各聚类之间的距离,提出了图像局部区域细节强度的定义及其计算方法．细节强度在准确地区分图像的平坦区域和细节区域基础上,通过非线性函数自适应地调整Hopfield网络的权系数矩阵,以使权系数适合图像的纹理特征,而且权系数的生成过程符合人的视觉特性．图像复原的迭代求解过程和神经网络权系数矩阵的更新过程交替进行．该算法能够在图像的平坦区域有效地抑制噪声,在包含细节的区域突出细节．对比实验结果显示,该算法获得的复原图像的信噪比明显提高,视觉效果明显改善．