基于均值漂移滤波及谱分类的海面舰船红外目标分割

提出了一种有效的海面舰船红外目标分割方法.利用均值漂移方法的不连续保持性滤波特性,滤除海面的强杂波干扰,同时又不损失舰船目标的信息.根据滤波得到的区域构建区域邻接图,采用基于最大最小SST图划分算法对区域邻接图的节点进行划分.划分结果最终将图像分为天空背景、海面背景以及舰船目标3个部分.由于采用区域节点来表征图像,较之采用原始图像象素节点表示,其节点个数大大减少,从而使算法的计算效率得到很大提高.实验结果也表明提出两步算法具有优越的性能,能够在海面强杂波干扰的情况下有效提取舰船红外目标.     

基于区域最大相似度的快速图像分割算法

针对基于区域最大相似度图像分割(MSRM)算法中利 用颜色直方图描述符计算相邻区域之间相似度存 在着计算量大和描述能力的不足,提出改用基于局部二值模式(LBP)纹理描述符计 算相邻区域相似度的改进MSRM(IMSRM)算法。LBP描述符通过对像素点之间局 部微结构进行编码实 现了对其空间关系的描述,有效提高了对区域特征的描述能力,并且所获得的特征矢量维数 远小于颜色直 方图,区域之间的相似度计算效率大幅度得到提高。与MSRM算法对比实验表明,IMSRM算法 可以从各种复杂背景中有效提取待分割对象的轮廓,所提取的轮廓边缘细节上更优,算法执 行效率能够提高50%左右。     

基于梯度矢量流理论的图像区域合并算法

为了减少过分割对图像后期处理的影响,提出基于梯度矢量流理论的过分割图像的区域合并算法。介绍了分水岭分割算法,梯度矢量流的产生、方向特征以及基于梯度矢量流理论的图像区域合并算法的方向查询及合并过分割区域的步骤。实验结果表明：在经典分水岭方法获得初始分割的基础上,可以获得待分割目标准确的边界和数目,对粘连、多目标及目标边界不封闭的生物图像具有较好的分割效果。     

An automatic algorithm for semantic object generation and temporal tracking

Automatic semantic video object extraction is an important step for providing content-based video coding, indexing and retrieval. However, it is very difficult to design a generic semantic video object extraction technique, which can provide variant semantic video objects by using the same function. Since the presence and absence of persons in an image sequence provide important clues about video content, automatic face detection and human being generation are very attractive for content-based video database applications. For this reason, we propose a novel face detection and semantic human object generation algorithm. The homogeneous image regions with accurate boundaries are first obtained by integrating the results of color edge detection and region growing procedures. The human faces are detected from these homogeneous image regions by using skin color segmentation and facial filters. These detected faces are then used as object seed for semantic human object generation. The correspondences of the detected faces and semantic human objects along time axis are further exploited by a contour-based temporal tracking procedure.     

Unsupervised image segmentation based on analysis of binary partition tree for salient object extraction

This paper proposes an unsupervised image segmentation approach aimed at salient object extraction. Starting from an over-segmentation result of a color image, region merging is performed using a novel dissimilarity measure considering the impact of color difference, area factor and adjacency degree, and a binary partition tree (BPT) is generated to record the whole merging sequence. Then based on a systematic analysis of the evaluated BPT, an appropriate subset of nodes is selected from the BPT to represent a meaningful segmentation result with a small number of segmented regions. Experimental results demonstrate that the proposed approach can obtain a better segmentation performance from the perspective of salient object extraction.     

Image segmentation via self-organising fusion

A method called self-organising fusion (SOF) for performing fast image segmentation is presented. The input image is divided into a set of small regions, each associated with a working feature. First, all regions are simultaneously updated and then a statistical process is applied to merge the qualified regions. The contours of objects are obtained by alternating the two processes of updating and merging until convergence. The concurrent updating creates a SOF behaviour that facilitates the identification of regions presumably comprising the same object. The method can save computation cost as both updating and merging are conducted in parallel fashion, and as parameter selection is done for local regions, it is able to deal with fairly complex images     

对基于图像分割与合并的相位展开算法的改进

为了提高基于图像分割与合并的相位展开算法的精度,对已有的一种算法进行多方面改进,采取区域不等分措施,使得区域信息完整、准确再现;针对不同区域的噪声及欠采样情况,分别采取不同的相位展开算法;对分块合并时重叠区域进行加权叠加处理。利用仿真和实测数据对算法进行了验证,结果表明,改进算法能更准确、快速地恢复出被测物体的相位信息。改进后的算法不但适合于超大规模图像的相位展开,也适合于部分区域条纹过密的包裹相位图的展开。     

Interactive video object segmentation: fast seeded region merging approach

An interactive video object segmentation tool is presented. The user interaction combines marker drawing and region selection. A fast seeded region merging approach is proposed to extract the video object from the regions of watershed segmentation. Experimental results show the effectiveness and convenience of the approach.     

Automatic image segmentation by integrating color-edge extractionand seeded region growing

We propose a new automatic image segmentation method. Color edges in an image are first obtained automatically by combining an improved isotropic edge detector and a fast entropic thresholding technique. After the obtained color edges have provided the major geometric structures in an image, the centroids between these adjacent edge regions are taken as the initial seeds for seeded region growing (SRG). These seeds are then replaced by the centroids of the generated homogeneous image regions by incorporating the required additional pixels step by step. Moreover, the results of color-edge extraction and SRG are integrated to provide homogeneous image regions with accurate and closed boundaries. We also discuss the application of our image segmentation method to automatic face detection. Furthermore, semantic human objects are generated by a seeded region aggregation procedure which takes the detected faces as object seeds.     

基于区域相似性与相异性的数字图像分割方法

针对数字图像数据量大、内容复杂、特征度量困难的特点,提出了一种综合区域相似性和相异性的基于图模型的分割方法.使用颜色方差作为距离度量,依靠区域邻接图和最近邻区域图来完成数字图像的快速区域合并分割.在合并过程中,通过合并区域的最小合并代价和最大合并代价变化,调整合并顺序,从策略上保证了分割区域的同质性和区域间的相异性.实验结果表明,该方法可以较好地解决图像的误分割现象.     

基于区域与深度残差网络的图像语义分割

该文提出了一种结合区域和深度残差网络的语义分割模型。基于区域的语义分割方法使用多尺度提取相互重叠的区域,可识别多种尺度的目标并得到精细的物体分割边界。基于全卷积网络的方法使用卷积神经网络(CNN)自主学习特征,可以针对逐像素分类任务进行端到端训练,但是这种方法通常会产生粗糙的分割边界。该文将两种方法的优点结合起来:首先使用区域生成网络在图像中生成候选区域,然后将图像通过带扩张卷积的深度残差网络进行特征提取得到特征图,结合候选区域以及特征图得到区域的特征,并将其映射到区域中每个像素上;最后使用全局平均池化层进行逐像素分类。该文还使用了多模型融合的方法,在相同的网络模型中设置不同的输入进行训练得到多个模型,然后在分类层进行特征融合,得到最终的分割结果。在SIFT FLOW和PASCAL Context数据集上的实验结果表明该文方法具有较高的平均准确率。     

一种适合于目标检测的图像分割方法

在航空图像的目标检测过程中，首先需要把图像中的每个目标都单独地分离开。一般的图像分割方法是把图像分成几大类，同一类目标组成一个个区域。这种分割结果给目标检测造成了很大的困难。本文首先采用最小值滤波对图像进行预处理，尽量地扩大目标之间的间隙。然后用降低分辨率的方法得到初始的分割图像，并用分裂合并法修正分割结果。计算结果显示，分割结果中不同的目标尽管距离很近，也能较好地分离。这个结果对于目标检测有着重要的意义。     

边缘惩罚层次区域合并SAR图像分割算法

该文利用方向边缘强度信息,建立一种新的边缘惩罚SAR图像分割模型,提出一种最小化该模型的层次区域合并算法。利用多方向比例边缘检测算子(MDRED)提取边缘强度信息,并结合分水岭变换获得高质量的初始过分割结果。利用多边形近似区域边缘,提取边缘的方向,将方向边缘强度映射(OESM)融入边缘惩罚中,获得惩罚强度与边缘强度呈反比的惩罚项。逐渐增大边缘惩罚项的强度,获得由图像特征驱动的层次区域合并算法。利用区域邻接图(RAG)表示图像分割,提高区域合并的速度。实验表明:该文方法与其它方法相比在性能和效率上都有优势,获得更好的分割结果。     

一种边界引导的多尺度高分辨率遥感图像分割方法

针对高分辨率遥感图像分割过程中区域合并复杂性问题,提出了一种基于边界引导的多尺度遥感图像分割算法.一方面应用SUSAN算子提取高分辨率遥感图像中地物的边界用于限制区域增长过程;另一方面进行两阶段增长,首先应用基于图的分割算法进行基于像素的区域生长,然后进行考虑对象特征信息的区域合并.对宜昌城区某处融合后的QuickBird彩色图像进行了实验,并分别与无边界引导分割以及eCognition平台下图像分割效果进行了对比.结果表明,该方法可以有效抑制传统图像分割算法在低对比度区的区域融合问题,突破了分割尺度参数不能在全图取得合理分割的局限性.     

Saliency-directed color image segmentation using modified particle swarm optimization

Color image segmentation, an ill-posed problem, can be treated as a process of dividing a color image into some constituent regions and each region is homogeneous. In this study, a saliency-directed color image segmentation approach using “simple” modified particle swarm optimization (PSO) is proposed, in which both low-level features and high-level image semantics extracted from each color image are employed. To extract high-level image semantics from each color image, the visual attention saliency map for each color image is generated by three (color, intensity, and orientation) feature maps, which is used to guide region merging using “simple” modified PSO and a hybrid fitness function for color image segmentation. The proposed approach contains four stages, namely, color quantization, feature extraction, small region elimination, and region merging using “simple” modified PSO. Based on the experimental results obtained in this study, as compared with four comparison approaches, the proposed approach usually provides the better color image segmentation results.     

基于时空信息融合的视频对象分割系统

提出了一种有效的时空融合视频分割系统.首先利用基于梯度的分水岭算法对图像进行分割,并利用基于时空联合的区域合并方法克服过分割现象,然后结合改进的帧差掩模对目标进行提取.试验结果表明,由于该系统充分利用了图像的颜色信息,能较完整地分割出对象,并且对象边缘更加准确.     

基于分水岭变换和区域融合的建筑物彩色图像分割

提出了一种彩色建筑物图像分割方法,该算法采用区域面积控制预处理技术和分水岭算法生成初始分割,结合区域对称性等多种属性作为区域相似性的度量,由区域融合得到最终分割结果.同时又提出了一种基于融合代价函数值直方图分布的终止阈值自动设定法.实验证明,本文提出的算法可生成有意义的建筑物各区域,并能有效地降低噪声对分割的影响,对三维重建等研究领域的建筑物图像分割有着十分重要的意义.     

Segmenting object with ambiguous boundary using information theoretic rough sets

In image segmentation, image is divided into regions of similar pixels that satisfy a defined notion of similarity. The complexity of image segmentation is further increased when the separation between neighboring regions is ambiguous. In this paper, we propose an approach that uses the information theoretic rough sets concept (ITRS) to model the ambiguous boundary of the object for further segmentation. The advantage of this approach is incorporating the prior knowledge of the object for effective extraction despite its ambiguous boundary. This approach starts with an assumption that seed points of the regions are available. It then computes the probability of association of the pixels with the seed points. Rough sets theory is invoked on this probability or likelihood map to identify positive, negative, and boundary states of the object. Optimal threshold for the boundary region is determined using histogram based segmentation algorithm for final object extraction. The main contribution relies on the application of ITRS in categorizing the object by combining both the prior and image information. The proposed approach, ITRS segmentation, is compared with different image segmentation methods on simulated brain images, and the result is encouraging with its state-of-the-art performance.     

Combining static and dynamic features using neural networks and edge fusion for video object extraction

Semantic object representation is an important step for digital multimedia applications such as object-based coding, content-based access and manipulations. The authors propose an image sequence segmentation scheme which provides region information for the semantic object representation of those applications. The objective is to develop a hardware-friendly segmentation algorithm by combining static and dynamic features simultaneously in one scheme. In the initial stage, a multiple feature space is transformed to one-dimensional label space by using self-organising feature map (SOFM) neural networks. The next stage is an edge fusion process in which edge information is incorporated into the neural network outputs to generate more precisely located boundaries of segmentation. The proposed algorithm differs from existing methods as follows: it can segment textured images with low-dimensional features; leads to more meaningful segmentation region boundaries; and is easier to map into hardware than existing methods. Experimental results are compared with an existing segmentation method using evaluation metrics to clarify the advantages of the proposed algorithm objectively.     

Hybrid image segmentation using watersheds and fast region merging

A hybrid multidimensional image segmentation algorithm is proposed, which combines edge and region-based techniques through the morphological algorithm of watersheds. An edge-preserving statistical noise reduction approach is used as a preprocessing stage in order to compute an accurate estimate of the image gradient. Then, an initial partitioning of the image into primitive regions is produced by applying the watershed transform on the image gradient magnitude. This initial segmentation is the input to a computationally efficient hierarchical (bottom-up) region merging process that produces the final segmentation. The latter process uses the region adjacency graph (RAG) representation of the image regions. At each step, the most similar pair of regions is determined (minimum cost RAG edge), the regions are merged and the RAG is updated. Traditionally, the above is implemented by storing all RAG edges in a priority queue. We propose a significantly faster algorithm, which additionally maintains the so-called nearest neighbor graph, due to which the priority queue size and processing time are drastically reduced. The final segmentation provides, due to the RAG, one-pixel wide, closed, and accurately localized contours/surfaces. Experimental results obtained with two-dimensional/three-dimensional (2-D/3-D) magnetic resonance images are presented.