模糊聚类的侧扫声纳图像分割算法

来源 :华中科技大学学报(自然科学版) | 被引量 : 7次 | 上传用户:f40042
下载到本地 , 更方便阅读
声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架
论文部分内容阅读
针对侧扫声纳图像的特点,利用二维经验模态分解(BEMD)将图像分解成若干固有模态函数(IMF)和1个余量.分析了侧扫声纳图像背景区的图像频率特征,通过增强目标和阴影的特征信息降低噪声的影响.提取图像的高斯马尔可夫纹理(GMRF),用来表达图像像素点间的空间关系,以减少图像的误分割.利用BEMD和GMRF改进模糊C均值聚类算法,提出了新的聚类准则和距离函数,形成一种新的模糊聚类算法.利用该算法对不同的侧扫声纳图像进行分割,并将分割结果与其他典型的聚类算法的分割结果进行比较,验证了该算法的抗噪性和准确性.
其他文献
The node-link diagram is an intuitive way to depict a graph and present relationships between entities.Addressing the visual clutter induced by edge crossing and node-edge overlapping is a challenging
期刊
Recently,sequential document visualization has attracted much attention for its superior capability in depicting the sequential semantic progression in a single document.However,existing methods commo
期刊
Ultra-scale data analysis has created many new challenges for visualization.For example,in climate research with two-dimensional time-varying data,scientists find it crucial to study the hidden tempor
期刊
Visualizing 2-D vector fields using streamlines is one popular ?ow visualization technique.Standard streamline generation algorithms compute the density of streamlines across the domain,detect feature
期刊
The effects of soil and water conservation (SWC) on soil properties are well documented. However, definitive and quantitative information of SWC and its interactions with soil properties on soil produ
期刊
Sensitivity analysis is a powerful method for discovering the significant factors that contribute to understanding the interaction between variables in multivariate datasets.A number of sensitivity an
期刊
噪声元素在光子量有限的最大似然期望最大化(MLEM)方法重建PET/CT(positron emission tomography/computed tomography)图像研究的过程中影响甚至加重图像特征明暗度变化。为减小这类影响,该文提出了一种包含解剖端信息的中值非局部平均算法(AMNLM)。该算法是对适用低信噪比图像去噪的非局部平均算法(NLM)的改进。将该算法应用于临床肺部病变患者PET
期刊
自动泊位引导系统的关键是飞机定位是否准确,而特殊天气下飞机特征选择和提取是定位准确与否的关键因素。提出了基于自适应加权形态学的高阶神经网络识别算法。首先利用自适应加权形态学提取边缘从中选择特征同时进行预处理,然后利用高阶反馈神经网络进行机型和子型识别。实验证明:该方法具有特征简单、识别率高的特点,能准确识别出飞机型号,得到比较精确的飞机外形描述,可有效对抗噪声、遮挡、阴影等干扰,具有很好的稳健性。
期刊
A SIMO(single input and multiple output) system of a step-frequency(SF) radar is used.It works in downward-looking spotlight mode and moves within a 2D synthetic plane array.A 3D(three-dimensional) ma
期刊
Combined with the printing application,an image registration method based on the multi-resolution morphology contour detection was proposed.First,a direction based multi-resolution gray morphology in
期刊