图像分块下的隧道裂缝识别方法

针对隧道衬砌表面不均匀光照、渗水和噪声等强视觉干扰,设计了基于图像分块的隧道衬砌裂缝检测算法;根据中国西部地区的地理特征和隧道衬砌的外观病害,研制开发出一种快速、自动化的非接触式智能隧道结构物外观检测系统; 以非均匀光照下隧道图像数据集为研究对象,在图像分块的基础上提出一种适用于隧道裂缝特征提取的图像识别算法;研究了电子元件产生的噪声,并分析和总结了隧道衬砌的灾害特征;根据裂缝特征和分辨率将图像矩阵划分为适当数量的区域块,根据区域块的灰度特征将原始图像划分为目标背景区、目标病害区、病害背景区和其他区域,通过最大类间方差法和局部阈值法分割得到了隧道裂缝的粗图像,在此基础上进行了粗图像裂缝特征提取;对原始图像的每个区域块进行了对比度受限的自适应直方图均衡操作和局部阈值分割,得到了细节图像;将细节图像和粗图像的重叠区域设为理想裂缝二值化图像;结合隧道结构物外观检测系统对不同方向的裂缝图像进行了二值化试验,并通过隧道裂缝定位和投影法得到了隧道衬砌图像中裂缝的位置信息和方向。研究结果表明:提出的算法对隧道裂缝识别的准确值、召回率和F值可分别达90.34%、98.78%和94.37%,既可以保证隧道裂缝的完整性,也可以在非均匀光照下最大程度地保留目标裂缝的细节,可用于处理一般灰度图像的二值化问题。      

隧道掌子面岩体裂隙快速识别方法

隧道掌子面上含有许多地质信息,若能充分提取和分析,将有助于对隧道工程地质状态作出评价,用于指导隧道设计和施工. 以隧道掌子面数码图像为基础,对掌子面上岩体裂隙检测、提取、分组算法进行研究. 首先,基于数字图像处理技术对掌子面岩体裂隙目标分割算法进行分析,根据分割结果,通过图像细化和边界线拟和、分离、合并、过滤,连接不连续边界,过滤短边界,形成较完整的岩体边界线识别结果;然后,计算岩体边界线视倾角,将视倾角相近的边界线合并为一组,实现对裂隙边界线的自动分组;最后,将本方法应用于实际掌子面岩体图像测试其有效性. 测试结果表明:该方法基本实现了对掌子面上岩体裂隙的自动提取和分组;对具有明显裂隙的掌子面岩体,本算法能较完整的提取出岩体裂隙,错误提取率不超过10%,并实现了自动分组,自动分组错误率不超过5%,提高了掌子面岩体分析的自动化程度,可用于地质素描,并为掌子面围岩分级提供参考依据.      

基于改进YCrCb颜色空间的肤色分割

人脸识别是计算机视觉、模式识别、生物特征识别、图像处理等多学科交叉的一门科学,肤色分割是人脸识别研究中一个重要的步骤。针对基于YCrCb颜色空间的肤色分割在强光下分割不准确的现状,提出了一种基于改进的YCrCb空间的肤色分割方法,本文利用改进YCrCb颜色空间提高了强光下肤色分割的准确性和适应性。实验证明该算法减弱了光线强弱对人脸肤色分割的影响,更加准确的找到人脸区域,误检率较低。     

Color image segmentation by edge linking and region grouping

A novel method toward color image segmentation is proposed based on edge linking and region grouping. Firstly, the edges extracted by the Canny detector are linked to form regions. Each of the end points of edges is connected by a direct line to the nearest pixel on another edge segment within a sub-window. A new distance is defined based on the feature that the edge tends to preserve its original direction. By sampling the lines to the image, the image is over-segmented to labeled regions. Secondly, the labeled regions are grouped both locally and globally. A decision tree is constructed to decide the importance of properties that affect the merging procedure. Finally, the result is refined by user’s selection of regions that compose the desired object. Experiments show that the method can effectively segment the object and is much faster than the state-of-the-art color image segmentation methods.     

融合边缘检测与区域生长的交通图像分割方法

在交通监控中,如何从复杂的背景中分割运动物体是至关重要的一步,针对车辆的运动阴影对图像分割产生的不利影响,提出了一种新的融合边缘检测与区域生长的彩色图像分割算法,算法同时考虑了图像的彩色信息和空间信息.该算法首先对彩色图像边缘检测,并根据检测结果设置种子像素;再基于颜色相似性生长准则,结合边缘检测结果,对每个种子点进行区域生长;最后,利用区域合并算法对剩余的像素进行合并.实验结果表明该算法很大程度上克服了阴影给图像分割带来的不利影响.     

基于球面图像的三角网格模型分割

为了从局部形状的角度实现对三角网格模型的管理和重用,提出了一种基于球面图像的三角网格模型分割方法.通过球面参数化及球面划分,将三角网格模型的表面属性信息映射到球面图像中;利用成熟的区域生长、区域合并图像分割算法对球面图像进行分割;将球面图像的分割结果转换为三角网格模型的分割结果.实验结果表明:该分割方法可以对不均匀的低分辨率三角网格模型进行有效分割,降低了几何属性估算对分割结果的影响,不会发生过分割现象,不需要进行分割的后续处理.     

基于深度图像的机场道面裂缝自动检测算法

为了实现强噪声、弱光照、低对比度条件下的机场道面细小裂缝检测, 设计了基于深度图像的机场道面裂缝检测算法; 将采集到的深度图像划分成多个网格, 并对每个网格进行扩充, 获得了局部道面区域; 针对每个网格区域, 基于随机抽样一致算法进行局部三次曲面构建和优化估计; 在此基础上, 在全局尺度下融合全部网格区域的曲面模型, 生成整个图像采集区域道面的全局曲面模型; 利用全局曲面模型与原始深度图像之间的差值图像, 采用自适应阈值方法分割出候选裂缝像素, 并利用裂缝的像素总数、长度以及长宽比等多种形态学约束筛选候选裂缝像素, 去除错误的候选裂缝像素, 从而获得了最终的裂缝检测结果; 在机场道面深度图像数据集上进行了试验, 以人工标注结果作为真实值, 以准确率、召回率以及F值作为量化评估指标, 将提出的算法分别与4种有代表性的传统算法进行了对比。试验结果表明: 传统算法能够取得的最高准确率、召回率以及F值分别为77.05%、41.02%和50.02%, 提出的算法在准确率、召回率和F值3个指标上均有明显优势, 其均值分别为91.20%、97.99%和94.12%;提出的算法能够在分辨率为1 984像素×2 000像素的深度图像上检测出最小宽度为3 mm、最小长度为10 cm的裂缝, 实现了在复杂机场道面场景中识别细小裂缝的目标。      

基于主元分析和色调的彩色图像分割

提出一种基于主元分析和色调的彩色图像分割方法.首先应用主元分析法确定分类数,将彩色图像分成几个区域,然后基于色调特征将区域再划分为若干个子区域,最后根据CIE(L*α,b*)空间的颜色差异合并具有相似颜色的子区域,得到最终的精确分割结果.     

A Bintree Energy Approach for Colour Image Segmentation Using Adaptive Channel Selection

A new hierarchical approach called bintree energy segmentation was presented for color image seg-mentation. The image features are extracted by adaptive clustering on multi-channel data at each level and used as the criteria to dynamically select the best chromatic channel, where the segmentation is carried out. In this approach, an extended direct energy computation method based on the Chan-Vese model was proposed to segment the selected channel, and the segmentation outputs are then fused with other channels into new images,from which a new channel with better features is selected for the second round segmentation. This procedure is repeated until the preset condition is met. Finally, a binary segmentation tree is formed, in which each leaf represents a class of objects with a distinctive color. To facilitate the data organization, image background is employed in segmentation and channels fusion. The bintree energy segmentation exploits color information involved in all channels data and tries to optimize the global segmentation result by choosing the "best" chan-nel for segmentation at each level. The experiments show that the method is effective in speed, accuracy and flexibility.     

基于头脑风暴优化的PCNN路面裂缝分割算法

为提升裂缝检测的分割精度和鲁棒性,基于头脑风暴优化（brainstorming optimization,BSO）和脉冲耦合神经网络（pulse coupled neural network,PCNN）,提出了一种路面裂缝图像分割算法（BSO-PCNN）. 该算法采用最大熵准则作为BSO算法的适应度函数,并依据适应度值决定参与次轮迭代的个体;BSO具有强收敛性,可快速确定最优个体解;结合图像特征,获得PCNN模型的最优参数,将其代入PCNN模型实现对裂缝图像的分割. 试验结果表明:算法可在20次迭代内取得不同类型路面裂缝图像的最大适应值,从而确定最佳分割参数;与Sobel边缘检测算法、PCNN图像分割算法、基于最大熵的遗传算法（genetic algorithm based on the maximun entropy of the histogram,GA-KSW）、基于遗传算法参数优化的PCNN分割算法（genetic algorithm based on the pulse coupled neural network,GA-PCNN）相比,BSO-PCNN算法取得了0.9924的区域一致性与0.0900的区域对比度.      

IMAGE SEGMENTATION BASED ON MARKOV RANDOM FIELD AND WATERSHED TECHNIQUES

IntroductionThere are many methods to perform imagesegmentation and edge detection tasks that incor-porate region- growing and edge detection tech-niques,for example,it is applying edge detectiontechniques to obtain Difference In Strength( DIS)map then employ region growing techniques towork on the map as in Refs.[1 ,2 ]. In the others,combining both special and intensity information inimage segmentation approach based on multi- reso-lution edge detection,region selection and intensi-ty thre…     

多尺度特征增强的路面裂缝检测方法

针对路面裂缝检测不完整和分割出现断裂的问题，提出了一种多尺度特征增强的路面裂缝检测网络MFENet,实现端到端的路面裂缝图像检测、分类和分割处理；设计了多尺度注意力特征增强模块，建立了网络模型的上层多尺度特征通道与底层特征通道权重系数之间的映射关系，以提升有效通道的特征输出；基于路面裂缝的坐标信息和像素语义信息在物理位置上的相关性，设计了多语义特征关联模块，实现不同语义信息之间的特征融合增强，并通过特征维度转换实现对路面裂缝图像的前景特征过滤；提出了一种针对深度特征强度进行量化评估的方法，用于提升模型提取特征能力的可解释性。在自采集数据集上的研究结果表明：MFENet对路面裂缝图像检测的平均精准率和平均召回率相比Mask R-CNN分别提升了4.3%和5.4%,相比基线模型RDSNet分别提升了14.6%和14.3%;MFENet对路面裂缝图像分割的平均精准率和平均召回率相比Mask R-CNN分别提升了6.6%和8.8%,相比RDSNet分别提升了8.1%和9.7%;与Mask R-CNN等主流方法相比，MFENet对不同类型路面裂缝图像的检测、分割精度最高。在公开数据集(CFD、C...     

A bintree energy approach for colour image segmentation using adaptive channel selection

A new hierarchical approach called bintree energy segmentation was presented for color image segmentation. The image features are extracted by adaptive clustering on multi-channel data at each level and used as the criteria to dynamically select the best chromatic channel, where the segmentation is carried out. In this approach, an extended direct energy computation method based on the Chan-Vese model was proposed to segment the selected channel, and the segmentation outputs are then fused with other channels into new images, from which a new channel with better features is selected for the second round segmentation. This procedure is repeated until the preset condition is met. Finally, a binary segmentation tree is formed, in which each leaf represents a class of objects with a distinctive color. To facilitate the data organization, image background is employed in segmentation and channels fusion. The bintree energy segmentation exploits color information involved in all channels data and tries to optimize the global segmentation result by choosing the ＂best＂ channel for segmentation at each level. The experiments show that the method is effective in speed, accuracy and flexibility.     

基于自适应阈值和连通域的隧道裂缝提取

为了解决传统人工隧道裂缝检测存在诸如效率低、主观性大、安全性差等弊端,利用裂缝具有方向性和连续性等特征,提出了一种基于自适应阈值和连通域标记的隧道裂缝提取方法. 首先,根据裂缝的方向性特征,设计了一种阿拉伯数字算法（Algorithmic）对裂缝进行粗提取,其中对于该算法公式中的阈值选取进行了自适应阈值化,利用改进的阈值迭代法完成系统自动获取最佳阈值,无需人工干预;然后,根据裂缝的连续性特征,采用数学形态中的连通域标记法对裂缝进行细提取,其中通过控制连通域面积大小,实现裂缝粗提取后的去噪处理,通过膨胀和腐蚀操作实现裂缝粗提取后的修复处理;最后,选取了共计165张不同类型的裂缝图像作为实验样本,在MATLAB上进行仿真实验. 从实验数据可以看出,自适应阈值和连通域标记的提取方法其提取精度可高达94.2%,平均运行时间仅35.4 s,误识率和拒识率已控制在2.7%和1.1%,相较于传统的图像处理方法有着显著的提高,充分展现出良好的应用前景.      

Unsupervised color-texture image segmentation

The measure J in J value segmentation （JSEG） fails to represent the discontinuity of color, which degrades the robustness and discrimination of JSEG. An improved approach for JSEG algorithm was proposed for unsupervised color-texture image segmentation. The texture and photometric invariant edge information were combined, which results in a discriminative measure for color-texture homogeneity. Based on the image whose pixel values are values of the new measure, region growing-merging algorithm used in JSEG was then employed to segment the image. Finally, experiments on a variety of real color images demonstrate performance improvement due to the proposed method.     

IMAGE ANALYSIS BASED ON EDGE DETECTION TECHNIQUES

IntroductionEdges are pixels where brightness changesabruptly and often used in image analysis for find-ing region boundaries.It locates sharp changes inthe intensity function.Edges detection is basic im-age features.They carry useful information aboutobject boundaries.Edges can be used for object i-dentification,image analysis and image filteringapplications as well.We shall consider as an edgethe border between two homogeneous image re-gions having different illumination.This definitionimp…     

Lesion segmentation and identification of breast tumor on dynamic contrast-enhanced magnetic resonance imaging

Dynamic contrast-enhanced magnetic resonance imaging （DCE-MRI） can show subtle lesion morphol- ogy, improve the display of lesion definitions, and objectively reflect the blood supply of breast tumors; it can also reflect different strengthening patterns of normal tissues and lesion areas after medical tracer injection. DCE-MRI has become an important basis for the clinical diagnosis of breast cancer. To DCE-MRI data acquired from several hospitals across multiple provinces, a series of in-silico computational methods were applied for lesion segmentation and identification of breast tumor in this paper. The image segmentation methods include Otsu segmentation of subtraction images, signal-interference-ratio segmentation method and an improved variational level set method, each has its own application scope. After that, the distribution of benign and malignant in lesion region is iden- tified based on three-time-point theory. From the experiment, the analysis of DCE-MRI data of breast tumor can show the distribution of benign and malignant in lesion region, provide a great help for clinicians to diagnose breast cancer more expediently and lay a basis for medical diagnosis and treatment planning.     

基于视觉注意机制 PCNN 模型的车牌 图像分割方法

车辆图像中车牌具有所占比例小、位置不固定、大小不一,以及分割易受光照影 响的特点.因此,车牌图像的分割始终是车辆跟踪、车辆识别等领域中的难点问题.针对以 上问题,本文提出了基于视觉注意机制脉冲耦合神经网络模型的车牌图像分割方法.该方 法将视觉注意机制中的数据驱动模式和任务驱动模式相结合. 数据驱动模式中,通过对 PCNN 模型细胞感受野功能的完善,使优化 PCNN 模型具有了尺度性和方向性.任务驱 动模式中,针对不同尺度的分割,利用组合不变矩和局部灰度熵,自适应地确定目标的特 征尺度和最佳尺度,并确定该目标最终的分割结果.经实验验证,该方法对车牌图像具有 较好的分割效果.     

Active Contours and Mumford-Shah Segmentation Based on Level Sets

IntroductionThe basic idea in active contour models orsnakes is to evolve a curve,subject to constraintsfrom a given image,in order to detect objects inthat image.For instance,starting with a curvearound the object to be detected,the curve movestoward its interior normal and has to stop on theboundary of the object.LetΩ be a bounded open subset of R2 ,with Ω its boundary. Let u0 ∶Ω→ R be a given image,and C( s)∶ [0 ,1 ]→ R2 be a parameterized curve. Inthe classical snakes and active…     

基于多层前馈神经网络的车牌提取方法

文中提出一种采用三层前馈神经网络提取车牌的方法。该方法是一种基于纹理分析的图像分割算法,适合于彩色及灰度图像。实验表明,该方法能准确地提取图像中的车牌。