Multiscale Segmentation of Three-Dimensional MR Brain Images

Segmentation of MR brain images using intensity values is severely limited owing to field inhomogeneities, susceptibility artifacts and partial volume effects. Edge based segmentation methods suffer from spurious edges and gaps in boundaries. A multiscale method to MRI brain segmentation is presented which uses both edge and intensity information. First a multiscale representation of an image is created, which can be made edge dependent to favor intra-tissue diffusion over inter-tissue diffusion. Subsequently a multiscale linking model (the hyperstack) is used to group voxels into a number of objects based on intensity. It is shown that both an improvement in accuracy and a reduction in image post-processing can be achieved if edge dependent diffusion is used instead of linear diffusion. The combination of edge dependent diffusion and intensity based linking facilitates segmentation of grey matter, white matter and cerebrospinal fluid with minimal user interaction. To segment the total brain (white matter plus grey matter) morphological operations are applied to remove small bridges between the brain and cranium. If the total brain is segmented, grey matter, white matter and cerebrospinal fluid can be segmented by joining a small number of segments. Using a supervised segmentation technique and MRI simulations of a brain phantom for validation it is shown that the errors are in the order of or smaller than reported in literature.     

Multiscale Active Contours

We propose a new multiscale image segmentation model, based on the active contour/snake model and the Polyakov action. The concept of scale, general issue in physics and signal processing, is introduced in the active contour model, which is a well-known image segmentation model that consists of evolving a contour in images toward the boundaries of objects. The Polyakov action, introduced in image processing by Sochen-Kimmel-Malladi in Sochen et al. (1998), provides an efficient mathematical framework to define a multiscale segmentation model because it generalizes the concept of harmonic maps embedded in higher-dimensional Riemannian manifolds such as multiscale images. Our multiscale segmentation model, unlike classical multiscale segmentations which work scale by scale to speed up the segmentation process, uses all scales simultaneously, i.e. the whole scale space, to introduce the geometry of multiscale images in the segmentation process. The extracted multiscale structures will be useful to efficiently improve the robustness and the performance of standard shape analysis techniques such as shape recognition and shape registration. Another advantage of our method is to use not only the Gaussian scale space but also many other multiscale spaces such as the Perona-Malik scale space, the curvature scale space or the Beltrami scale space. Finally, this multiscale segmentation technique is coupled with a multiscale edge detecting function based on the gradient vector flow model, which is able to extract convex and concave object boundaries independent of the initial condition. We apply our multiscale segmentation model on a synthetic image and a medical image.     

Multiscale Bayesian texture segmentation using neural networks and Markov random fields

This paper presents a wavelet-based texture segmentation method using multilayer perceptron (MLP) networks and Markov random fields (MRF) in a multi-scale Bayesian framework. Inputs and outputs of MLP networks are constructed to estimate a posterior probability. The multi-scale features produced by multi-level wavelet decompositions of textured images are classified at each scale by maximum a posterior (MAP) classification and the posterior probabilities from MLP networks. An MRF model is used in order to model the prior distribution of each texture class, and a factor, which fuses the classification information through scales and acts as a guide for the labeling decision, is incorporated into the MAP classification of each scale. By fusing the multi-scale MAP classifications sequentially from coarse to fine scales, our proposed method gets the final and improved segmentation result at the finest scale. In this fusion process, the MRF model serves as the smoothness constraint and the Gibbs sampler acts as the MAP classifier. Our texture segmentation method was applied to segmentation of gray-level textured images. The proposed segmentation method shows better performance than texture segmentation using the hidden Markov trees (HMT) model and the HMTseg algorithm, which is a multi-scale Bayesian image segmentation algorithm.     

融合灰度和梯度信息的彩色细胞图像自动分割

为了开发血及骨髓涂片中白细胞自动分类及计算机辅助诊断系统,提出了一种融合灰度空间、彩色信息和数学形态学形态梯度信息的血细胞图像自动分割算法,以完成对白细胞（胞核和胞浆）的分割。在灰度空间,通过改进的迭代阈值分割算法,对白细胞的胞核进行了精确的定位和检出。通过彩色空间变换,有效地利用了图像中血细胞胞浆的颜色信息及先验知识,并且为了抑制过度分割,充分利用梯度信息,合理地对白细胞的胞核和胞浆进行了标记。在灰度梯度图像上提取血细胞的轮廓,并分别赋予不同的标记,表明数学形态梯度算法较传统的边缘检测算子具有更好的边缘提取能力。结果表明,胞核和胞浆的分割正确率分别为95.5％和92.6％,验证了该算法对彩色白细胞图像分割的有效性。     

空间可变有限混合模型

目的 有限混合模型是一种无监督学习方法,它被广泛的应用到数据分类任务中。然而,在图像分割过程中,由于有限混合模型没有引入邻域像素间的空间关系,导致了图像分割结果对噪声非常敏感。为了增强有限混合模型的抗噪性,提出一种新的空间可变有限混合模型。方法 该模型通过在像素的先验分布中引入一种新的空间关系来降低噪声对图像分割结果的干扰。在构建空间关系的过程中,利用形态学膨胀原理将空间邻域内特征值出现的概率而不是特征值本身进行膨胀操作,然后通过根据具有最大概率的分类标记在高斯混合模型迭代地计算过程中进行局部像素空间平滑,从而起到抑制噪声干扰的作用。结果 本文实验包含了人工合成图像和医学CT图像的图像分割实验。在人工合成图像分割实验中,对人工合成图像添加了不同程度的噪声来测试本文模型和对比模型对噪声抑制能力的高低;对医学CT图像进行图像分割实验,以是比较本文模型与对比模型之间在实际图像分割中的效果。结论 实验数据显示,本文提出的模型在噪声抑制能力上,图像分割精度和计算效率上均有更优的性能。     

基于图像块分类器和条件随机场的显微图像分割

针对花粉显微图像处理提出了一种自动分割方法,将有助于花粉识别系统的开发。使用归一化颜色分量训练图像块分类器,并且结合条件随机场和图割进行建模和优化,利用最大化后验概率(MAP)的方法实现花粉显微图像中花粉区域的分割。对于实验中的133幅图像,自动分割同人工分割的结果相比较,统计得到距离误差均值为7.3像素,准确率的平均值为87%。实验结果表明,使用图像块分类器和条件随机场模型可以用于花粉图像的分割。     

An area‐ratio gray‐scale method to achieve image uniformity in TFT‐LEPDs

Abstract— An area‐ratio gray‐scale method (ARG) has been developed for low‐temperature‐polysilicon thin‐film‐transistor‐driven light‐emitting‐polymer displays (LTPS TFT‐LEPDs). A pixel consists of plural sub‐pixels, which are controlled to be in either an on‐state or off‐state. The gray scale is acquired by selecting the number of the on‐state sub‐pixels, that is, the ratio of the light‐emitting area. One advantage of the ARG is to improve image uniformity. In the on‐state, since TFT resistance is negligible, the current is determined by the LEP diode resistance. Therefore, the TFT characteristic deviation has no effect on the current. Moreover, the dimensions of each sub‐pixel are the same, and the shapes of the sub‐pixel are circular in order to improve their uniformity. As a result, the image becomes uniform. Another advantage of the ARG is to achieve digital operation, which makes interfacing easy. A digital‐analog converter (DAC) automatically exists in the sub‐pixel and the naked eye.     

一种形态学彩色图像多尺度分割算法

为了对彩色图像进行快速有效的分割，提出了一种用于分割彩色图像的多尺度形态学算法。该算法首先用基于张量梯度的彩色分水岭算法来得到初始分割结果，即局部水平集连通区域，并综合考虑了面积和色彩计算区域间的相似性，构造了区域间的RAG（region adjacency graph）和NNG（nearest neighbor nraph），用于后续形态学处理；接着，基于HSV空间中的色彩全序关系，定义了彩色形态算子；然后采用顶点塌缩算法实现的彩色形态学开闭算子生成了所需的非线性尺度空间；最后，利用图像中的极值点与物体间的对应关系，逐级提取图像中包含的物体来得到分层级的表示，并用区域在不同尺度下熵的变化来决定尺度树的构成，从而完成了彩色图像的分割。试验结果表明，该算法不仅具有出色的形状保持能力，而且可提高计算效率。     

协同目标性指导下的多图像联合分割算法

提出一种协同分割算法,使包含同类目标的多幅图像相互作用,从而将目标从各自图像的背景中分离出来。首先,分别从单幅图像自身角度和多幅同类目标图像相互作用的角度出发,计算出图像中每个像素或区域属于前景或背景的似然概率,从而得到协同目标性映射图。这个映射图描述了目标的位置和几何形状信息,然后阈值化这个映射图作为图像分割真值来训练一个关于超像素的二值分类器,用训练好的分类器预测出每个超像素的前背景似然概率作为外观先验信息,与几何先验信息一并送入条件随机场模型,从而实现对图像目标的分割。在MSRC和iCoseg两个数据库上的测试结果表明该算法的分割效果优于同类方法。     

Image‐object detectable in multiscale analysis on high‐resolution remotely sensed imagery

Landscapes are complex systems composed of a large number of heterogeneous components as well as explicit homogeneous regions that have similar spectral character on high‐resolution remote sensing imagery. The multiscale analysis method is considered an effective way to study the remotely sensed images of complex landscape systems. However, there remain some difficulties in identifying perfect image‐objects that tally with the actual ground‐object figures from their hierarchical presentation results. Therefore, to overcome the shortcomings in applications of multiresolution segmentation, some concepts and a four‐step approach are introduced for homogeneous image‐object detection. The spectral mean distance and standard deviation of neighbouring object candidates are used to distinguish between two adjacent candidates in one segmentation. The distinguishing value is used in composing the distinctive feature curve (DFC) with object candidate evolution in a multiresolution segmentation procedure. The scale order of pixels is built up by calculating a series of conditional relative extrema of each curve based on the class separability measure. This is helpful in determining the various optimal scales for diverse ground‐objects in image segmentation and the potential meaningful image‐objects fitting the intrinsic scale of the dominant landscape objects. Finally, the feasibility is analysed on the assumption that the homogeneous regions obey a Gaussian distribution. Satisfactory results were obtained in applications to high‐resolution remote sensing imageries of anthropo‐directed areas.     

基于形态学梯度重构和标记提取的分水岭图像分割

为了解决传统分水岭算法的过分割问题,提出一种使用形态学梯度重构和标记提取技术进行图像预处理的分水岭图像分割方法。该方法基于多尺度概念,进行梯度重构时采用了不同尺寸的结构元素,在对重构后的各梯度图像的区域极小值进行标记后,将各标记点的并集作为最终标记图像,用其修改梯度图像,然后进行分水岭变换,实现图像的区域分割。实验结果表明,该方法既能有效解决分水岭算法的过分割问题,又保留了各尺度下的重要目标,并且可以根据图像特点和具体的分割要求,调整分割过程中所选参数,得到满意的图像分割效果。     

基于对象的最优尺度建筑物信息提取方法

针对基于像素分析方法不适用于高分辨率影像信息提取的问题,提出一种基于对象的图像分析方法来进行城市建筑信息提取。采用多分辨率图像分割方法得到图像对象,提出非监督的最优尺度判定方法解决单尺度分割造成的欠分割和过分割问题。在对象分类提取过程中,结合LiDAR数据的地形表面高程信息和光谱信息对建筑物进行提取,并利用尺寸、空间位置等信息进行误分类修正。实验区域共提取出18个建筑目标,结果表明所提出的方法有效可行。     

Intensity standardization simplifies brain MR image segmentation

Typically, brain MR images present significant intensity variation across patients and scanners. Consequently, training a classifier on a set of images and using it subsequently for brain segmentation may yield poor results. Adaptive iterative methods usually need to be employed to account for the variations of the particular scan. These methods are complicated, difficult to implement and often involve significant computational costs. In this paper, a simple, non-iterative method is proposed for brain MR image segmentation. Two preprocessing techniques, namely intensity-inhomogeneity-correction, and more importantly MR image intensity standardization, used prior to segmentation, play a vital role in making the MR image intensities have a tissue-specific numeric meaning, which leads us to a very simple brain tissue segmentation strategy.Vectorial scale-based fuzzy connectedness and certain morphological operations are utilized first to generate the brain intracranial mask. The fuzzy membership value of each voxel within the intracranial mask for each brain tissue is then estimated. Finally, a maximum likelihood criterion with spatial constraints taken into account is utilized in classifying all voxels in the intracranial mask into different brain tissue groups. A set of inhomogeneity corrected and intensity standardized images is utilized as a training data set. We introduce two methods to estimate fuzzy membership values. In the first method, called SMG (for simple membership based on a gaussian model), the fuzzy membership value is estimated by fitting a multivariate Gaussian model to the intensity distribution of each brain tissue whose mean intensity vector and covariance matrix are estimated and fixed from the training data sets. The second method, called SMH (for simple membership based on a histogram), estimates fuzzy membership value directly via the intensity distribution of each brain tissue obtained from the training data sets. We present several studies to evaluate the performance of these two methods based on 10 clinical MR images of normal subjects and 10 clinical MR images of Multiple Sclerosis (MS) patients. A quantitative comparison indicates that both methods have overall better accuracy than the k-nearest neighbors (kNN) method, and have much better efficiency than the Finite Mixture (FM) model-based Expectation-Maximization (EM) method. Accuracy is similar for our methods and EM method for the normal subject data sets, but much better for our methods for the patient data sets.     

空间关系信息和颜色信息相结合的地形图分层算法

在对地形图图象颜色进行误差分析的基础上，指出目前在地形图分层算法设计中，由于仅考虑地形图色彩信息而存在许多不足，因此提出了地形图像素空间关系信息的概念，并讨论了像素空间关系信息的提取方法，进而给出一个将地形图像素的空间关系信息与颜色信息相结合，以实现彩色地形图分层的新算法．实验表明，此算法可有效地抑制地形图图象的颜色误差和提高分层的精度，从而为地形图的分层识别及自动矢量化奠定了良好的基础．     

遥感影像数据的规范化处理和时空尺度整合

管理不同遥感平台和传感器数据，实现不同尺度数据的相互关联是我国典型地物标准波谱数据库建设的关键，其中涉及海量影像数据的处理，实现不同尺度影像数据的关联以及在网络环境下的压缩传输等问题。本提出了基于空间单元分割和空间区域影像数据链解决方案，通过将数据按照地形图进行单元切割，采用规范化处理流程，最终将不同尺度影像数据处理成标准化的数据，为波谱库支持下的尺度研究、模型运行提供了数据平台。     

多层次MRF重标记及映射法则下的图像分割

针对彩色图像分割问题,研究Markov 随机场(Markov random fields, MRF)模型内迭代条件模式(Iterative conditional mode, ICM)方法的标记推理策略. 通过小波分解构造图像多尺度表达,针对顶层图像先验标记获取问题,改进原始谱聚类算法, 通过近邻传播自动确定图像的聚类参数,运用集成学习提高算法的稳定性和准确度. 对其他各尺度图像,通过分析尺度关联下的区域特征变化,结合不同尺度间的特征相似性和同一尺度内空间邻域的一致性, 提出一种立体结构描述下的尺度--空间映射法则.通过定量和定性的分割实验,结果表明本文算法具有良好的准确性、鲁棒性和普适性.     

Two approaches to derive LED driving signals for high‐dynamic‐range LCD backlights

Abstract— The LED‐array backlight technique dramatically enhances the dynamic range of an LCD and hence extends its ability to present images with high reality. This is achieved by modulating LEDs individually, thus providing an area‐adaptive backlight for the display. The spatial overlap of light from the LED (crosstalk) occurs due to the diffusion screen placed between the backlight and LCD layer. However, the crosstalk is not only a blessing for supplying high brightness but is also a curse for causing potential artifacts, making the derivation of an LED driving signal a challenging task. This paper formulates the problem into two mathematical models: an iterative de‐convolution approach and a linear optimization approach. Algorithms for solving these two models are provided. The first approach provides instantaneous and satisfactory results except for high‐intensity highlights in the image. The linear optimization method conquers this drawback, but requires much more computation, possibly requiring preprocessing of the target, and also introduces undesired artifacts. These two approaches are extensively evaluated by building an image database composed of 161 high‐dynamic‐range images.     

Scale selection for supervised image segmentation

Finding the right scales for feature extraction is crucial for supervised image segmentation based on pixel classification. There are many scale selection methods in the literature; among them the one proposed by Lindeberg is widely used for image structures such as blobs, edges and ridges. Those schemes are usually unsupervised, as they do not take into account the actual segmentation problem at hand. In this paper, we consider the problem of selecting scales, which aims at an optimal discrimination between user-defined classes in the segmentation. We show the deficiency of the classical unsupervised scale selection paradigms and present a supervised alternative. In particular, the so-called max rule is proposed, which selects a scale for each pixel to have the largest confidence in the classification across the scales. In interpreting the classifier as a complex image filter, we can relate our approach back to Lindeberg's original proposal. In the experiments, the max rule is applied to artificial and real-world image segmentation tasks, which is shown to choose the right scales for different problems and lead to better segmentation results.     

Influence of 3‐D cross‐talk on qualified viewing spaces in two‐ and multi‐view autostereoscopic displays

Abstract— To estimate the qualified viewing spaces for two‐ and multi‐view autostereoscopic displays, the relationship between image quality (image comfort, annoying ghost image, depth perception) and various pairings between 3‐D cross‐talk in the left and right views are studied subjectively using a two‐view autostereoscopic display and test charts for the left and right views with ghost images due to artificial 3‐D cross‐talk. The artificial 3‐D cross‐talk was tuned to simulate the view in the intermediate zone of the viewing spaces. It was shown that the stereoscopic images on a two‐view autostereoscopic display cause discomfort when they are observed by the eye in the intermediate zone between the viewing spaces. This is because the ghost image due to large 3‐D cross‐talk in the intermediate zone elicits different depth perception from the depth induced by the original images for the left and right views, so the observer's depth perception is confused. Image comfort is also shown to be better for multi‐views, especially the width of the viewing space, which is narrower than the interpupillary distance, where the parallax of the cross‐talking image is small.     

Scale‐aware Structure‐Preserving Texture Filtering

This paper presents a novel method to enhance the performance of structure‐preserving image and texture filtering. With conventional edge‐aware filters, it is often challenging to handle images of high complexity where features of multiple scales coexist. In particular, it is not always easy to find the right balance between removing unimportant details and protecting important features when they come in multiple sizes, shapes, and contrasts. Unlike previous approaches, we address this issue from the perspective of adaptive kernel scales. Relying on patch‐based statistics, our method identifies texture from structure and also finds an optimal per‐pixel smoothing scale. We show that the proposed mechanism helps achieve enhanced image/texture filtering performance in terms of protecting the prominent geometric structures in the image, such as edges and corners, and keeping them sharp even after significant smoothing of the original signal.