基于超像素的图像语义区域引导的色彩迁移

针对图像色彩处理技术,提出基于超像素的图像色彩迁移方法,其以图像语义区域进行引导,以LAB色彩空间进行映射。首先,采用K-means和SLIC算法对输入图像进行分割;其次,对每一子区域块进行区域协方差处理,获得其二阶语义特征并生成超像素,并利用相似度测量函数构造相似矩阵,对区域块聚类可生成图像超像素;最后,再对图像内语义信息相似的像素基于LAB空间映射,完成色彩迁移。结果显示,该方法具有处理复杂图像能力较高及颜色迁移效果准确的优点。     

基于改进的相似度度量的谱聚类图像分割方法

针对传统谱聚类图像分割方法存在分割准确度不够高的缺点,提出一种基于改进的相似度度量的谱聚类图像分割方法。该方法首先使用超像素分割算法将图像预分割为一定数目的超像素集合,并构建以超像素为节点的图;然后融合超像素的协方差描述子、颜色信息、纹理信息、梯度信息以及边缘信息作为超像素的特征来度量超像素间的相似性,进而得到超像素的相似度矩阵;最后使用NJW算法对超像素图进行分割。大量的实验结果验证表明,改进的分割方法在分割精度上优于目前存在的无监督分割方法,并且在交互式分割的模式下,该方法可以准确分割出用户指定的目标。     

结合区域协方差分析的图像显著性检测

目的 图像显著性检测的目的是为了获得高质量的能够反映图像不同区域显著性程度的显著图,利用图像显著图可以快速有效地处理图像中的视觉显著区域。图像的区域协方差分析将图像块的多维特征信息表述为一个协方差矩阵,并用协方差距离来度量两个图像块特征信息的差异大小。结合区域协方差分析,提出一种新的图像显著性检测方法。方法 该方法首先将输入的图像进行超像素分割预处理;然后基于像素块的区域协方差距离计算像素块的显著度;最后对像素块进行上采样用以计算图像像素点的显著度。结果 利用本文显著性检测方法对THUS10000数据集上随机选取的200幅图像进行了显著性检测并与4种不同方法进行了对比,本文方法估计得到的显著性检测结果更接近人工标定效果,尤其是对具有复杂背景的图像以及前背景颜色接近的图像均能达到较好的检测效果。结论 本文方法将图像像素点信息和像素块信息相结合,避免了单个噪声像素点引起图像显著性检测的不准确性,提高了检测精确度;同时,利用协方差矩阵来表示图像特征信息,避免了特征点的数量、顺序、光照等对显著性检测的影响。该方法可以很好地应用到显著目标提取和图像分割应用中。     

结合DBSCAN聚类的室内场景分割

针对RGB-D图像具有丰富的三维几何特征,复杂度高这一具有挑战性的难题,提出一种针对室内场景RGB-D图像的分割算法.首先,经过RGB-D图像过分割生成超像素,并基于超像素之间的距离度量测量超像素之间的相似性;然后,采用DBSCAN算法将具有相似的颜色信息和几何信息的超像素聚类到一个分类中.在该聚类过程中,通过限制扩散区域来降低计算复杂度.在室内场景RGB-D图像库上大量实验结果表明,文中算法分割精确度和速率均超过了其他算法,证明了其高效性和准确性.     

优化加权核K-means聚类初始中心点的SLIC算法

超像素是近年来快速发展的一种图像预处理技术,被广泛应用于计算机视觉领域。简单线性迭代聚类(simple linear iterative clustering,SLIC)算法是其中的一种图像预处理技术框架,该算法根据像素的颜色和距离特征进行聚类来实现良好的分割结果。然而,SLIC算法尚存在一些问题。基于优化加权核K-means聚类初始中心点,提出一种新的SLIC算法(WKK-SLIC算法)。算法基于图像像素之间的颜色相似性和空间相似性度量,采用超像素分割的归一化割公式,使用核函数来近似相似性度量。算法将像素值和坐标映射到高维特征空间中,通过对该特征空间中的每个点赋予适当的权重,使加权K均值和归一化割的目标函数的优化在数学上等价。从而通过在所提出的特征空间中迭代地应用简单的K-means聚类来优化归一化割的目标函数。在WKK-SLIC算法中,采用密度敏感的相似性度量计算空间像素点的密度,启发式地生成K-means聚类的初始中心以达到稳定的聚类结果。实验结果表明,WKK-SLIC算法在评估超像素分割的几个标准上优于SLIC算法。     

基于模糊连接度的近邻传播聚类图像分割方法

针对现有近邻传播聚类图像分割方法分割精度低的问题,提出一种基于模糊连接度的邻近传播聚类(FCAP)图像分割算法。针对传统模糊连接度算法不能得出任意点对间模糊连接度的不足,结合最大生成树提出了全模糊连接度算法。FCAP算法先使用Normalized Cut超像素技术进行超像素分割,这些超像素可以看作数据点以及它们之间的模糊连接度;然后使用所提出的全模糊连接度算法计算超像素间的模糊连接度,根据模糊连接度和空间信息计算超像素的相似度;最后使用近邻传播(AP)聚类算法完成分割。实验结果表明,FCAP算法明显优于超像素处理后直接使用AP聚类算法进行分割的方法,并且优于无监督图像分割方法。     

基于多代表点近邻传播的大数据图像分割算法

基于多代表点近邻传播聚类算法,提出一种有效的大数据图像的快速分割算法。 该算法首先运用均值漂移算法将彩色图像分割成很多小的同质区域,然后计算每个区域中所有 像素的颜色向量平均值,并用区域数目代替原图像像素点数目,选用区域间的距离作为相似度 的测度指标,最后应用多代表点近邻传播聚类算法在区域相似度矩阵上进行二次聚类,得到最 终的图像分割结果。实验结果证明,提出的算法在大数据图像的分割中取得了较为满意的分割 效果,且分割效率较高。     

基于双重超像素集的快速路径相似度图像分割算法

为克服基于路径相似度计算时间复杂度高以及基于单一过分割区域集的聚类方法 容易导致误合并的缺陷, 提出一种结合均值漂移和路径相似度的谱聚类算法. 该算法使用超像 素构建基于路径相似度的模型来实现加速. 首先, 利用均值漂移算法对图像进行两次预分割(不同参数), 将这些过分割区域视为两组超像素集合, 构建基于双重过分割区域集的加权图; 之后, 使用各超像素的色彩均值和超像素间存在的交叉像素计算初始相似度, 再利用路径相似度模型得 到基于路径的相似度; 最后, 采用Multiway Ncut算法进行聚类. 通过算法自身参数和图结构实验, 测试算法的鲁棒性和稳定性; 通过多幅彩 色图片的分割实验, 表明本文的方法在准确性和时效性方面都具有很好的性能.     

融合超像素与Wasserstein距离的遥感影像分割方法北大核心CSCD

图像分割技术是图像处理和计算机视觉领域中的关键技术之一。随着近年来遥感成像技术的迅猛发展,传统基于像素的影像处理方法不再适用于高分辨率遥感影像。针对传统图像分割方法在分割准确性以及分割效率等问题上存在的不足,提出了一种融合超像素与Wasserstein距离的遥感影像分割方法。首先,对遥感影像进行SLIC(simple linear iterative clustering)算法预分割,生成超像素;然后,将超像素作为K-means算法的聚类中心,利用Wasserstein距离替代传统欧氏距离计算超像素之间的距离,完成聚类。理论和实验结果表明,新方法具有收敛性,在一定程度上提高了超像素预分割后的完整性,并且Wasserstein距离能够准确计算分布之间的差异性,在超像素距离计算上表现突出。     

基于半监督的超像素谱聚类彩色图像分割算法

近年来谱聚类算法被广泛应用于图像分割领域,而相似性矩阵的构造是谱聚类算法的关键步骤。 针对传统谱聚类算法计算复杂度高难以应用到大规模图像分割处理的问题,提出了基于半监督的超像素谱聚类彩色图像分割算法。该算法利用超像素将彩色图像进行预分割,利用用户提供的少量标记信息构造预分割区域的基于半监督的模糊相似性测度,利用该相似性测度构造预分隔区域的相似性矩阵并通过规范切图谱划分准则对预分割区域进行划分得到最终的图像分割结果。由于少量标记信息和模糊理论的引入,提高了传统谱聚类的分割性能,对比实验也表明该算法在分割效果和计算复杂度上都有较大的改善。     

High precision image segmentation algorithm using SLIC and neighborhood rough set

A high precision image segmentation algorithm using SLIC and neighborhood rough set is proposed. The algorithm mainly includes two stages: the stage of superpixel generation and the mergence stage based on neighborhood rough set. In superpixel generation stage, based on L-channel color histogram and its peak, the scheme of initial superpixel number generation is proposed according to the complexity of the image itself. For inaccuracy segmentation edge of SLIC caused by isolated pixels, the compactness factor is appropriately increased before they are generated. After that, the scheme of reclassifying each isolated pixel is proposed just relying on the color space. In superpixel mergence stage based on neighborhood rough set, the texture information using the gray level co-occurrence matrix is introduced into the feature representation of superpixel. It can reduce the dependence of color feature and improve the accuracy of the mergence. By constructing the information table, the neighborhood granule of each superpixel is acquired under the neighborhood threshold. Finally, the superpixels within the neighborhood granule are merged on the basis of the spatial adjacency between superpixels. In Berkeley segmentation data set, compared with the SLIC algorithm, the schemes of initial superpixel number generation and the isolated pixels processing are proved to be effective. Furthermore, the experiments demonstrate that the proposed algorithm can produce high-quality and high-precision image segmentation results in comparison with the SLIC-based image segmentation algorithms on three standard metrics.     

Semantic superpixel extraction via a discriminative sparse representation

The superpixel extraction algorithm is becoming increasingly significant for pattern recognition applications. Different superpixel generation methods have different properties and lead to various over-segmentation results. In this paper, we treat the over-segmentation as an image decomposition problem, and propose a novel discriminative sparse coding (DSC) algorithm to effectively extract the semantic superpixels. Specifically, the DSC algorithm incorporates a new discriminative regularization term in the traditional sparse representation model. Then the new regularization term is combined with the reconstruction error and sparse constraint to form a unified objective function. The extracted superpixels not only respect the local image boundaries, but also are dissimilar between each other. Meanwhile, the quantity of segments is sparse. These properties benefit for the semantic superpixel extraction. The final refined superpixels are generated based on an effective Bayesian-classification criterion in a post-processing step. Experimental results show that the over-segmentation quality of DSC algorithm outperforms the state of the art methods.     

基于超像素形状特征的图像复制粘贴篡改检测算法

针对传统图像复制粘贴篡改检测方法中划分子块的数目过大导致算法时间复杂度过高且抵抗几何变换能力较弱的问题,提出一种基于超像素形状特征的图像复制粘贴篡改检测算法.首先提出基于小波对比度自适应划分超像素的方法分割图像并提取稳定的特征点;然后提出新颖的形状编码方式提取超像素形状特征,并与特征点融合,估计可疑伪造区域;最后对可疑伪造区域进行二次超像素分割和匹配,精确定位篡改区域.实验结果表明,提出的算法具有抵抗几何变换、噪声、模糊和JPEG压缩的能力.     

Superpixel Generation by Agglomerative Clustering With Quadratic Error Minimization

Superpixel segmentation is a popular image pre‐processing technique in many computer vision applications. In this paper, we present a novel superpixel generation algorithm by agglomerative clustering with quadratic error minimization. We use a quadratic error metric (QEM) to measure the difference of spatial compactness and colour homogeneity between superpixels. Based on the quadratic function, we propose a bottom‐up greedy clustering algorithm to obtain higher quality superpixel segmentation. There are two steps in our algorithm: merging and swapping. First, we calculate the merging cost of two superpixels and iteratively merge the pair with the minimum cost until the termination condition is satisfied. Then, we optimize the boundary of superpixels by swapping pixels according to their swapping cost to improve the compactness. Due to the quadratic nature of the energy function, each of these atomic operations has only O(1) time complexity. We compare the new method with other state‐of‐the‐art superpixel generation algorithms on two datasets, and our algorithm demonstrates superior performance.     

Adaptive hypergraph superpixels

Superpixel segmentation, which amounts to partitioning an image into a number of superpixels each of which is a set of pixels sharing common visual meanings, requires specific needs for different computer vision tasks. Graph based methods, as a kind of popular superpixel segmentation method, regard an image as a weighted graph whose nodes correspond to pixels of the image, and partition all pixels into superpixels according to the similarity between pixels over various feature spaces. Despite their improvement of the performance of segmentation, these methods ignore high-order relationship between them incurred from either locally neighboring pixels or structured layout of the image. Moreover, they measure the similarity of pairwise pixels using Gaussian kernel where a robust radius parameter is difficult to find for pixels which exhibit multiple features (e.g., texture, color, brightness). In this paper, we propose an adaptive hypergraph superpixel segmentation (AHS) of intensity images for solving both issues. AHS constructs a hypergraph by building the hyperedges with an adaptive neighborhood scheme, which explores an intrinsic relationship of pixels. Afterwards, AHS encodes the relationship between pairwise pixels using characteristics of current two pixels as well as their neighboring pixels defined by hyperedges. Essentially, AHS models the relationship of pairwise pixels in a high-order group fashion while graph based methods evaluate it in a one-vs-one fashion. Experiments on four datasets demonstrate that AHS achieves higher or comparable performance compared with state-of-the-art methods.     

图像分割中的超像素方法研究综述

目的 超像素(superpixel)是近年来快速发展的一种图像预处理技术,它将图像快速分割为一定数量的具有语义意义的子区域,相比于传统处理方法中的基本单元——像素,超像素更有利于局部特征的提取与结构信息的表达,并且能够大幅度降低后续处理的计算复杂度,在计算机视觉领域尤其是图像分割中得到了广泛的应用,为使国内外研究者对超像素理论及其在图像分割中的应用有一个比较全面的认识,对其进行系统综述.方法 以图像分割为应用背景,在广泛调研文献特别是超像素最新发展成果的基础上,结合对比实验,对每种方法的基本思想、方法特点进行总结,并对超像素分割目前存在的局限性进行说明,对未来可能发展方向进行展望.结果 不同的超像素分割算法在分割思想、性能特点上各不相同.当前的超像素方法普遍在超像素数量、紧密度与分割质量、算法实用性之间存在相互制约,同时对于某些特殊目标的分割也难以取得较好的结果.结论 超像素作为一种有效的图像预处理手段具有较高的研究价值,但针对目前超像素存在的一些局限性还需要进行深入的研究.     

Use of Spectral Clustering Combined with Normalized Cuts (N-Cuts) in an Iterative k-Means Clustering Framework (NKSC) for Superpixel Segmentation with Contour Adherence

Superpixel segmentation methods are generally used as a pre-processing step to speed up image processing tasks. They group the pixels of an image into homogeneous regions while trying to respect existing contours. In this paper, we propose a fast Superpixels segmentation algorithm with Contour Adherence using spectral clustering, combined with normalized cuts in an iterative k-means clustering framework. It produces compact and uniform superpixels with low computational costs. Normalized cut is adapted to measure the color similarity and space proximity between image pixels. We have used a kernel function to estimate the similarity metric. Kernel function maps the pixel values and coordinates into a high dimensional feature space. The objective functions of weighted K-means and normalized cuts share the same optimum point in this feature space. So it is possible to optimize the cost function of normalized cuts by iteratively applying simple K-means clustering algorithm. The proposed framework produces regular and compact superpixels that adhere to the image contours. On segmentation comparison benchmarks it proves to be equally well or better than the state-of-the-art super pixel segmentation algorithms in terms of several commonly used evaluation metrics in image segmentation. In addition, our method is computationally very efficient and its computational complexity is linear.     

基于图像分割的森林火灾早期烟检测算法研究

针对森林这样的大空间、复杂场景下的火灾检测,提出一种在单帧视频序列图像中的烟检测方法,并研究一种新的超像素合并算法,改进现有的天地线检测算法。该方法对图像进行SLIC（Simple Linear Iterative Clustering）超像素分割,并用一种新的超像素合并算法解决过分割问题;通过改进的天地线分割算法,排除天空中云对于烟检测的干扰;根据光谱特征,运用支持向量机（SVM）对超像素块进行分类。实验结果表明,超像素合并算法高效简洁,易于编程实现,基于图像分割的烟检测技术能排除云雾等噪声对烟雾检测的干扰,在森林场景下的烟雾检测正确率为77%,可以作为人工森林火灾监测的辅助手段。