结合爬山法的模糊C均值彩色图像分割方法

采用传统的模糊C均值聚类(FCM)算法进行彩色图像分割存在聚类数的选取、初始聚类中心的确定、迭代过程中的大计算量及后处理等问题。在对上述问题进行研究的基础上,针对传统FCM聚类分割时初始值选取方法的盲目性和随机性,为了更准确地自动获取待分割图像聚类的初始参数,提出了一种结合爬山法的模糊C均值彩色图像分割方法(HFCM),该方法可根据待分割图像的三维颜色直方图自适应地获取FCM算法的初始聚类中心及聚类数目,同时提出一种最频滤波与区域合并相结合的新的后处理策略,有效消除了小的空间区域。实验表明,相对于传统FCM,该图像分割方法的速度较快,并且分割结果更接近人类分割效果。     

融合Tamura纹理特征的改进FCM脑MRI图像分割算法

针对FCM算法在分割脑MRI图像时存在噪声敏感性和初始聚类中心随机性的问题,提出一种融合图像Tamura纹理特征的改进FCM图像分割算法.首先提取图像的Tamura纹理特征,将其与灰度特征线性加权构成融合特征.然后使用模糊邻域关系计算像素点的密度,将其与距离关系结合自适应选取初始聚类中心.最后使用融合特征作为更新隶属度和聚类中心的特征约束.实验利用该方法与FCM,D-FCM,WKFCM方法对Brain Web脑MRI数据集中的图像进行分割,并在抗噪性、准确性和运行效率方面进行了比较.实验结果表明,所提算法能获取更优的初始聚类中心,在处理噪声和灰度不均匀图像上表现出更好的鲁棒性,能够快速有效地分割脑MRI图像.     

基于蚁群和自适应滤波的模糊聚类图像分割

为了改进模糊C均值聚类(FCM)算法对初始聚类中心敏感、抗噪性能较差、运算量大的问题,提出一种新的基于蚁群和自适应滤波的模糊聚类图像分割方法(ACOAFCM).首先,该方法利用改进的蚁群算法确定初始聚类中心,作为FCM初始参数,克服FCM算法对初始聚类中心的敏感;其次,采用自适应中值滤波抑制图像噪声干扰,增强算法的鲁棒性;最后,用直方图特征空间优化FCM目标函数,对图像进行分割,减少运算量.实验结果表明,该方法克服了FCM算法对初始聚类中心的依赖,抗噪能力强,收敛速度快,分割精度高.     

基于改进的FCM算法提取彩色图像有意义区域

针对传统的FCM算法随机获取初始聚类中心与分类类别数的缺陷问题,提出了一种获取初始聚类中心与分类类别数的方法,并采用交叉熵测度准则进行FCM聚类,对彩色图像进行分割,提取有意义区域.实验结果表明,该方法不仅能够提高算法的聚类速度与算法的普适度,而且可以改善图像的聚类效果.与传统的FCM算法相比,该算法更易于实现彩色图像有意义区与背景的分离,分割效果令人满意.     

基于分水岭和改进的模糊聚类图像分割*

针对模糊C-均值聚类算法需预先给出初始聚类中心、未考虑邻城信息、计算复杂度高等缺点,提出了一种基于分水岭和改进的模糊聚类图像分割方法.该方法首先利用分水岭分割方法对原图像进行预分割,然后利用粒子群的全局寻优能力从预分割的小区域中搜索出较为准确的初始聚类中心;最后,在对小区域进行模糊聚类时,建立了包含邻域信息的聚类目标函...     

结合[k]-means的自动FCM图像分割方法

针对图像分割中模糊C均值算法（FCM）无法自动确定聚类中心,不考虑像素邻域信息的问题,提出一种结合[k]-means的自动FCM图像分割方法。该方法先由图像的灰度直方图确定聚类数目,使用一种改进的快速FCM方法产生初始聚类中心。即通过一步[k]-means算法对大隶属度灰度更新模糊聚类中心,同时仅对小隶属度灰度使用快速FCM?方法进行隶属度更新,迭代后得到初始聚类中心。利用改进隶属度的FCM算法进行最终聚类。实验表明,该方法获取初始聚类中心接近最终值,加速图像分割,并对噪声具有一定的鲁棒性。     

基于改进粒子群和自适应滤波的快速模糊聚类图像分割

为改进传统模糊C均值聚类(FCM)算法对初始聚类中心敏感、易陷入局部收敛、抗噪性差、计算量大的问题,提出一种新的基于改进粒子群算法的快速模糊聚类图像分割方法(PSOFFCM);方法首先利用自适应中值滤波对图像进行滤波处理,增强算法的鲁棒性;然后,将图像像素灰度值映射到二维直方图特征空间,作为聚类样本,优化FCM的目标函数,减少图像分割的计算量;最后,利用PSO算法代替FCM的梯度迭代过程,减弱了算法对初始聚类中心的依赖,同时增强全局搜索能力;实验结果表明,该方法不仅克服了FCM算法对初始聚类中心的依赖,而且抗噪能力强,收敛速度快,分割精度明显优于传统FCM。     

基于自适应蚁群的FCM聚类优化算法研究

模糊C均值聚类算法在算法初始化时需要人为设定聚类类别数、随机初始化聚类中心,致使该算法容易陷入局部最优值.为解决此类问题,在蚁群算法中引入信息素更新机制,使其输出的聚类中心更具全局优化的特征和较强鲁棒性的特点;用蚁群算法得到的聚类中心来初始化FCM算法的聚类中心,解决了FCM算法对初始聚类中心敏感的问题;使用结合熵信息与数据几何结构的聚类有效性评价方法对FCM算法和优化FCM算法进行评价,评价结果表明优化的FCM算法性能更优.在仿真实验中,利用提出的优化算法和FCM算法对自然图像、纹理图像和SAR图像进行分割实验,从图像分割的准确性和算法的实时性做对比实验,验证了优化算法的有效性.     

结合非局部均值的快速FCM算法分割MR图像研究

针对FCM算法分割医学MR图像存在的运算速度慢、对初始值敏感以及难以处理MR图像中固有Rician噪声等缺陷,提出了一种结合非局部均值的快速FCM算法。该算法的核心是首先针对MR图像中存在的Rician噪声,利用非局部均值算法对图像进行去噪处理,消除噪声对分割结果的影响;然后根据所提出的新的自动获取聚类中心的规则得到初始聚类中心;最后将得到的聚类中心作为快速FCM算法的初始聚类中心用于去噪后的图像分割,解决了随机选择初始聚类中心造成的搜索速度慢和容易陷入局部极值的问题。实验表明,该算法能够快速有效地分割图像,并且具有较好的抗噪能力。     

基于蚁群优化的直觉模糊聚类脑MR图像分割

针对现有模糊C均值(FCM)聚类算法存在的对初始参数敏感、迭代速度慢,以及对噪声鲁棒性差等问题,提出将蚁群优化算法(ACO)与直觉模糊聚类相结合的方法用于分割脑部MR图像.该算法采用自适应蚁群优化算法获取初始聚类中心与聚类个数作为直觉模糊聚类的初始值,将融入了局部空间信息和犹豫度的直觉模糊聚类算法应用于含噪声脑部图像及脑肿瘤图像进行分割.实验结果表明该算法能够有效抑制噪声干扰且保存图像细节,相较于FCM及相关改进算法具有更高的分割精度和分割效率.     

Evidence-based recommendations for building better bras for women treated for breast cancer

Participating in exercise is beneficial for women who have been treated for breast cancer. However, not being able to find a comfortable exercise bra can be a barrier to exercise participation. This study aimed to systematically investigate what breast support women treated for breast cancer want when they exercise in order to provide evidence-based recommendations to improve exercise bra designs for these women. Based on 432 responses from a national online survey, frequency and relationship data were analysed (binary logistic regression) to understand exercise bra issues pertinent to this population. These issues included being able to control for asymmetrical cup sizes, managing heightened skin sensitivity, managing fluid (size) fluctuations, managing a prosthesis and restoring body image by restoring shape. This study provides evidence-based recommendations to inform an exercise bra design that will meet the unique needs of women treated for breast cancer. Rigorous, evidence-based evaluations of exercise bras for women treated for breast cancer may contribute to their well-being and quality of life through enhanced designs.     

一种SIP穿越NAT的解决方案

NAT使得SIP端到端的应用变得非常困难,文章分析了几种SIP穿越NAT方法及其不足,提出了一种基于STUN和TURN方法的穿越方案.其基本思想是根据NAT的不同采用不同的方式实现SIP信令的穿越,而媒体流的穿越则通过对所有可用媒体地址进行连接检查来实现.方案不改动现有NAT,在应用层上实现了对所有NAT的有效穿越,避免单独使用其它方法带来的缺陷.     

Grammar engineering for multiple front-ends for Python

In this paper, we describe our experience in grammar engineering to construct multiple parsers and front ends for the Python language. We present a metrics-based study of the evolution of the Python grammars through the multiple versions of the language in an effort to distinguish and measure grammar evolution and to provide a basis of comparison with related research in grammar engineering. To conduct this research, we have built a toolkit, pygrat , which builds on tools developed in other research. We use pygrat to build a system that automates much of the process needed to translate the Python grammars from EBNF to a formalism acceptable to the bison parser generator. We exploit the suite of Python test cases, used by the Python developers, to validate our parser generation. Finally, we describe our use of the menhir parser generator to facilitate the parser and front-end construction, eliminating some of the transformations and providing practical support for grammar modularisation.     

Regional Process Modeling for Design for Environment

This research is an effort towards providing higher level Design for Environment (DFE) tools for a broad industrial region. Issues ranging from the levels immediately above existing design tools, to the envisioned highest level for a broad geographical region are discussed. A tool for the regional planning of the DFE activities is proposed, considering a model construction based on material flows across the industry. The Multi-Lifecycle approach is supported by organizing the input/output flows for industries, potentially utilizing waste material, side products and recycling. Capitalizing on the conceptual integration of the design and process activities, an Abstract Design Environment is used for the design of the basically process oriented material flow tool. Within the context, the relations among design, process and flow-modeling concepts are discussed.     

医院多功能情报监控系统的研究

介绍了基于AT89S52单片机设计的医院多功能情报监控系统,该系统分为监测端和控制端2个部分.监测端位于病房内,和控制端通过CAN总线进行通讯,传递病房内的环境参数以及室内环境调节装置的控制信息.控制端位于控制室内,通过RS232与上位机通信,可以使用计算机上的C语言编译的人机对话界面,对各个病房的环境进行实时监测调节.     

Louvers design for LED displays for sunny days

The use of louvers attached to variable information display needs to be optimized taking into account different intrinsic and extrinsic parameters. The analysis of the performance of the display–louvers system takes into account the location, orientation, and daily and seasonal variations. The observation of the system is divided depending on the distance of observation. The far distance vision performance use the background luminance. The medium distance performance needs the use of the Contrast Sensitivity Function of the eye.     

Conceptual tools for planning for the wireless classroom

Abstract  Wireless and mobile devices are beginning to offer stunning new technical capabilities for collaborative learning. Yet, researchers in this field must recognise the importance of complementing these technical advances with improved understanding of the patterns of classroom activity that most need support. The approach taken in the work reported in this paper has been to create conceptual tools that help thinking and talking about technology-supported collaborative learning. A particularly powerful tool is Collaborative Design Patterns, which captures common learning situations and benefits in written form. This paper uses four classroom scenarios to describe eight patterns. These patterns fall into two categories: whole-activity patterns, which suggest ways to organise one or more class periods, and smaller-grained support patterns.     

Requirements for Maintaining Web Access for Hearing-Impaired Individuals

The current textual and graphical interfaces to computing, including the Web, is a dream come true for the hearing impaired. However, improved technology for voice and audio interface threaten to end this dream. Requirements are identified for continued access to computing for the hearing impaired. Consideration is given also to improving access to the sight impaired.