基于离散平稳小波变换和FCM的纹理图像分割

采用离散平稳小波变换对纹理图像进行分解,以各层小波系数中能量为特征相向量,采用模糊c-均值聚类（FCM）对图像分割,并对分割方法进行了改进,提出采用网格法,将图像分解成若干子图像,对图像进行粗分割,再对边缘部分的网格进行细分的两步分割法。试验结果表明该方法显著提高了分割速度和精度。     

K-means Iterative Fisher (KIF) unsupervised clustering algorithm applied to image texture segmentation

The K-means Iterative Fisher (KIF) algorithm is a robust, unsupervised clustering algorithm applied here to the problem of image texture segmentation. The KIF algorithm involves two steps. First, K-means is applied. Second, the K-means class assignments are used to estimate parameters required for a Fisher linear discriminant (FLD). The FLD is applied iteratively to improve the solution. This combined K-means and iterative FLD is referred to as the KIF algorithm. Two KIF implementations are presented: a mixture resolving approach is extended to an unsupervised binary hierarchical approach. The same binary hierarchical KIF algorithm is used to properly segment images even though the number of classes, the class spatial boundaries, and the number of samples per class vary. The binary hierarchical KIF algorithm is fully unsupervised, requires no a priori knowledge of the number of classes, is a non-parametric solution, and is computationally efficient compared to other methods used for clustering in image texture segmentation solutions. This unsupervised methodology is demonstrated to be an improvement over other published texture segmentation results using a wide variety of test imagery. Gabor filters and co-occurrence probabilities are used as texture features.     

具有纹理感知能力的超像素分割方法

目的 超像素分割是计算机视觉领域常用的一项预处理技术,目标是将相邻像素聚集成为具有一定语义的子区域,能够大幅度降低后续处理的计算复杂度,但是对包含强梯度纹理的图像分割效果不佳,为此提出一种具有纹理感知能力的超像素分割方法。方法 提出一种能够区分强梯度噪声和纹理像素的颜色距离,其中利用带方向的1/4圆形窗口均值滤波后的颜色信息,提升包含强梯度噪声和纹理图像的超像素分割性能。利用区间梯度幅值与Sobel梯度幅值相乘得到混合梯度幅值,具有纹理抑制、结构保持以及边缘线条细的优点,能够提升超像素的贴合边缘性能,增强超像素形状规则程度。最后,利用混合梯度的幅值计算具有结构回避能力的综合聚类距离,进一步防止超像素跨越物体的边界,增强超像素的贴边性能。结果 在BSDS500（Berkeley segmentation dataset 500）图像数据集和强纹理马赛克图像等不同类型图像上的测试结果显示,与目前主流的超像素分割方法相比,本文算法在UE （undersegmentation error）、ASA （achievable segmentation accuracy）和CM （compactness measure）等性能指标上分别提高了1.5%、0.2%和4.3%。从视觉效果上看,能够在排除纹理干扰的情况下生成结构边缘贴合程度更好的形状规则超像素。结论 本文算法在包含强梯度纹理图像上的超像素分割性能优于对比方法,在目标识别、目标追踪和显著性检测等易受强梯度干扰的技术领域具有较大应用潜力。     

基于先验知识水平集方法的草莓图像分割

在实际应用中,当目标本身含有一些固有的颜色纹理特征时,可将这些特征作为一种先验信息,这样可以大大提高分割的准确性.为此,本文提出了一种基于先验信息的改进水平集图像分割方法.首先,利用传统的C-V模型能量项的构造思想构建了基于颜色信息的局部能量项,该项是用于处理彩色图像;然后将颜色分量引入到传统的结构张量中构建出新的扩展型结构张量,该项是用于处理纹理信息;最后,将上述新构造的能量项以及Li模型约束项引入到传统C-V模型中得到新的水平集模型.鉴于草莓果实所具有的颜色信息和纹理信息,本文将上述改进水平集方法应用到农业自动化应用中草莓果实分割中.对实验室环境与草莓生长环境下的草莓图像进行分别实验,结果显示该方法能够不仅能够分割出草莓果实且能够很好地处理草莓表面的纹理信息.另还与OTSU算法、传统C-V模型、改进C-V模型对草莓图像作对比实验,结果表明本文算法均比上述三种算法具有更好的分割效果.     

基于小波变换与图割的彩色图像分割方法

为提高图割算法的分割效率与质量并改善shrinking bias现象,提出将图割理论与小波变换相结合的方法.该方法利用小波变换多分辨率分析的特点,将变换中的低频子带图像作为估计GMM参数的训练样本进行多尺度迭代分割,提高算法效率,利用简单高效的CS_LBP纹理描述子提取高频子带图像中的纹理信息,将颜色与纹理特征相结合改善分割效果,并利用高频系数进行多尺度边缘检测,用于计算局部自适应的正则化参数,改善对细长边界的分割.实验结果表明,分割效果得到了改善,算法效率得到了提高.     

结合纹理特征改进的GBIS图像分割方法

针对GBIS(efficient graph-based image segmentation)方法在分割含有较丰富纹理信息的图像时, 分割效果不理想的问题, 在L*a*b*彩色空间下, 结合图像的纹理特征, 提出了一种改进GBIS图像分割方法, 记为IGBIS(improved efficient graph-based image segmentation)。该方法首先将图像由RGB空间转换到L*a*b*颜色空间; 接着, 结合L*a*b*彩色空间, 对GBIS方法中的权值函数作了改进, 引入了一个常数s, 用于控制相邻像素之间颜色的差异程度; 然后, 用熵的方法来获取L*a*b*彩色图像的纹理特征; 最后, 结合图像的纹理信息, 改变了GBIS方法中的区域合并条件, 得到最终的分割结果。实验证明, 与原算法相比, 该方法在分割精度与分割质量上有了很大程度的提高。IGBIS有效地抑制了彩色图像在分割中存在的过分割现象, 并适合于含有丰富纹理的彩色图像。     

Spiking neural network and wavelets for hiding iris data in digital images

This paper introduces an efficient approach to protect the ownership by hiding the iris data into a digital image for authentication purposes. The idea is to secretly embed an iris code data into the content of the image, which identifies the owner. Algorithms based on Biologically inspired Spiking Neural Networks, called Pulse Coupled Neural Network (PCNN) are first applied to increase the contrast of the human iris image and adjust the intensity with the median filter. It is followed by the PCNN segmentation algorithm to determine the boundaries of the human iris image by locating the pupillary boundary and limbus boundary of the human iris for further processing. A texture segmentation algorithm for isolating the iris from the human eye in a more accurate and efficient manner is presented. A quad tree wavelet transform is first constructed to extract the texture feature. Then, the Fuzzy c-Means (FCM) algorithm is applied to the quad tree in the coarse-to-fine manner by locating the pupillary boundary (inner) and outer (limbus) boundary for further processing. Then, iris codes (watermark) are extracted that characterizes the underlying texture of the human iris by using wavelet theory. Then, embedding and extracting watermarking methods based on Discrete Wavelet Transform (DWT) to insert and extract the generated iris code are presented. The final process deals with the authentication process. In the authentication process, Hamming distance metric that measure the variation between the recorded iris code and the corresponding extracted one from the watermarked image (Stego image) to test weather the Stego image has been modified or not is presented. Simulation results show the effectiveness and efficiency of the proposed approach.     

结合分水岭的纹理梯度各向异性图像分割

目的 目前,许多图像分割算法对含有丰富纹理信息的图像的分割效果并不理想,尤其是在不同纹理的边缘信息的保持方面。为了解决这一问题,提出一种基于连续纹理梯度信息的各向异性图像分割算法。方法 在分水岭算法的基础上,引入纹理梯度各向异性算法,能够在避免纹理信息影响分割效果的前提下,最大限度地保证纹理边缘信息的完整。针对纹理特征数据敏感的特性,本文将离散的图像高度信息映射到连续的纹理梯度空间,能够有效减少由细小差异造成的过分割现象。结果 本文方法在BSD500 Dataset和Stanford Background Dataset中选择了大量的纹理信息丰富的图片与最新的分割算法进行了实验与对比。本文方法在分割效果（降低过分割现象）、保持边缘信息和分割准确率等方面均获得明显改进,并在图像分割的平均准确率方面与最新算法进行比较发现,本文算法的平均分割准确率达到90.9%,明显超过了其他最新算法,验证了本文方法的有效性。结论 本文提出的基于分水岭的纹理梯度各向异性算法对纹理图像的分割具有保边和准确的特点,采用连续梯度空间的方法能够有效地减少传统分水岭算法的过分割现象。本文方法主要适用于纹理信息丰富（自然纹理和人工纹理）的图片。     

基于纹理分水岭的斜坡单元提取算法

斜坡单元在以滑坡为主的地质灾害预防和评价中有着广泛的应用，其提取和划分是滑坡灾害风险评估的首要工作和重要基础。针对传统地理信息系统（GIS）方法提取的斜坡单元存在平行边界和误分割问题，提出了基于纹理分水岭的斜坡单元提取方法，通过分割地形图像划分斜坡单元。首先通过预处理地形数据得到数字高程模型（DEM）图像，利用灰度共生矩阵提取DEM纹理特征；然后计算融合灰度和纹理特征的梯度图像，对梯度图像进行基于标记的分水岭分割，使其能够准确获取山体和流域边界；最后，结合正负地形，对山体对象进行分水岭分割以实现斜坡单元的提取。实验结果表明，所提方法对不同地貌类型和分辨率的DEM图像都有良好的划分效果；相较于传统的GIS方法，该方法能够正确分割水平面和倾斜面，有效避免因洼地填平处理而产生的平行边界问题。     

Species classification of aquatic plants using PSVM and ANFIS

This work presents a method for plant species identification using the images of flowers. It focuses on the stable feature extraction of flowers such as color, texture and shape features in addition to fractal dimension. Color based segmentation using K-means clustering and active contour model is used to extract the color features. Texture segmentation using texture filter is used to segment the image and obtain texture features. Sobel, Prewitt and Robert operators are used to extract the boundary of image and to obtain the shape features. Classification of the plants is done using Proximal Support Vector Machine (PSVM) and Adaptive Neuro Fuzzy Inference System (ANFIS) classifiers.     

融合颜色与纹理的复杂场景下的服装图像分割算法

针对复杂场景下拍摄到的服装图像的分割问题,提出一种基于先验知识的融合颜色和纹理特征的无监督分割算法。首先利用块截断编码思想将传统的三维颜色空间截断成为六维空间,得到更为精细的颜色特征,并结合改进的局部二值模式纹理特征实现对图像的特征描述;然后根据目标区域和背景区域在图像中出现的统计规律,提出了一种基于先验知识的两分法来对图像进行分割。由于对图像做了分块处理,因此在子图像块的基础上进行的图像分割将更加高效。实验表明,设计的算法能快速有效地将目标区域从各类不同的复杂场景中分割出来,且整个过程无须人工设定任何参数,对后续的图像理解和图像检索具有重要意义。     

多注意力机制网络卫星图像分割算法

针对深度学习的语义分割法,在卫星图像分割中对半岛、小岛和湖泊细小支流的边缘信息提取丢失问题,提出了多注意力机制网络（MA-Net）卫星图像分割算法,弥补了边缘信息提取丢失问题。该算法的框架采用了端到端的对称结构,由编码和解码两部分组成。编码部分采用改进的VGG16网络提取湖泊的纹理特征,解码部分引入全局平均池化注意力融合机制（GPA）,能够有效融合编码部分提取的纹理特征,得到高分辨率的卫星图像特征图。在网络的输出端加入注意力机制模块（Attention）,充分提取湖泊边缘信息,有效分割出半岛、小岛和湖泊细小支流。实验结果表明,该模型相比现有语义分割算法,具有更好的分割精度,各项分割指标都有提升,并且在公共数据集City Scapes上验证了模型具有通用性。     

基于特征加权的自适应FCM彩色图像分割算法

图像分割是模式识别、图像理解、计算机视觉等领域的重要研究内容.基于模糊C均值聚类(FCM)的图像分割是应用较为广泛的方法之一,但其存在需预先给出初始聚类数目,且要考虑各个特征对分类的不同影响等问题.通过引入ReliefF技术进行特征加权,结合聚类有效性指数自适应确定初始聚类数目、根据Laws纹理测度提取图像特征等措施,提出了一种新的FCM彩色图像分割算法.实验结果表明,该算法可以有效地提高图像分割效果,分割结果优于现有FCM图像分割方案.     

Generating High-quality Superpixels in Textured Images

Superpixel segmentation is important for promoting various image processing tasks. However, existing methods still have difficulties in generating high-quality superpixels in textured images, because they cannot separate textures from structures well. Though texture filtering can be adopted for smoothing textures before superpixel segmentation, the filtering would also smooth the object boundaries, and thus weaken the quality of generated superpixels. In this paper, we propose to use the adaptive scale box smoothing instead of the texture filtering to obtain more high-quality texture and boundary information. Based on this, we design a novel distance metric to measure the distance between different pixels, which considers boundary, color and Euclidean distance simultaneously. As a result, our method can achieve high-quality superpixel segmentation in textured images without texture filtering. The experimental results demonstrate the superiority of our method over existing methods, even the learning-based methods. Benefited from using boundaries to guide superpixel segmentation, our method can also suppress noise to generate high-quality superpixels in non-textured images.     

Forest delineation of aerial images with Gabor wavelets

Clearly delineated forest boundaries are important for sustainable forest management. Interpreting aerial images for forest boundary delineation is a necessary, but labour-intensive process. The results are partly subjective and may include inconsistencies. In this article, we present an automatic approach to delineating forest boundaries in natural colour aerial images from the Swiss National Forest Inventory (NFI). This method is based on JSEG (J-measure-based Segmentation) image segmentation and can be used to obtain forest delineations using the green vegetation index (GVI) feature, Gabor wavelet texture features as well as curvature features from airborne laser scanning (ALS). This approach is compared with the commonly used method of supervised classification, nearest neighbour (NN), which requires local training, and is found to work well in several different landscape types after establishing thresholds. Although we tested the method in a variety of different landscape types, further development and testing are required to cope with complex terrain topography, for example, in regions at the upper tree line in the Alps.     

An MLP-based texture segmentation method without selecting a feature set

A texture segmentation technique which employs a multilayer perceptron (MLP) and does not consider the selection of features is presented in this paper. Thus, users can avoid selection and computation of the feature set and hence real-time segmentation may be possible. The technique apparently works in a fashion similar to our visual system whereby we do not consciously compute any feature for texture discrimination. A detailed study has been made for the selection of the network size. A newly proposed variant of the back-propagation algorithm has been used for more efficient training of the network. An edge-preserving noise-smoothing approach has been proposed to remove noise from the segmented image.     

结合多特征和SVM的SAR图像分割

为实现灰度共生矩阵(GLCM)多尺度、多方向的纹理特征提取, 提出了一种结合非下采样轮廓变换(NSCT)和GLCM的纹理特征提取方法。先用NSCT对合成孔径雷达(SAR)图像进行多尺度、多方向分解; 再对得到的子带图像使用GLCM提取灰度共生量; 然后对提取的灰度共生量进行相关性分析, 去除冗余特征量, 并将其与灰度特征构成多特征矢量; 最后, 充分利用支持向量机(SVM)在小样本数据库和泛化能力方面的优势, 由SVM完成多特征矢量的划分, 实现SAR图像分割。实验结果表明, 基于NSCT域的GLCM纹理提取方法和多特征融合用于SAR图像分割, 可以提高分割准确率, 获得较好的边缘保持效果。     

Design considerations for image segmentation quality assessment measures

Factors to consider when designing quality assessment measures for image segmentation are discussed. Quality assessment requires one manually generated segmentation (for reference) plus computer-generated segmentations corresponding to different image segmentation algorithms or algorithm parameter settings. Since true pixel class assignments are seldom available, one must typically rely on a trained human analyst to produce a reference by using a mouse to draw boundaries of perceived regions on a digital image background. Different algorithms and parameter settings can be compared by ranking computed disparities between maps of computer-generated region boundaries and region boundaries from a common reference.Proximity-based association between two boundary pixels is discussed in the context of association distance. Motivated by the concept of phase-modulated signals, a penalty factor on the degree of association is then introduced as some non-negative power (phase modulation order) of the cosine of disparity in phase (boundary direction) between two boundary pixels. Families of matching measures between maps of region boundaries are defined as functions of associations between many pairs of boundary pixels. The measures are characterized as one-way (reflecting relationships in one direction between region boundaries from two segmentations) vs. two-way (reflecting relationships in both directions). Measures of inconsistency between perceived and computed matches of computer and manually generated region boundaries are developed and exercised so that effects of association distance, phase modulation, and choice of matching measure on image segmentation quality assessment can be quantified. It is quantitatively established that consistency can be significantly improved by using two-way measures in conjunction with high-order phase modulation and moderate association distances.