CRFNet: Context ReFinement Network used for semantic segmentation

Recent semantic segmentation frameworks usually combine low-level and high-level context information to achieve improved performance. In addition, postlevel context information is also considered. In this study, we present a Context ReFinement Network (CRFNet) and its training method to improve the semantic predictions of segmentation models of the encoder–decoder structure. Our study is based on postprocessing, which directly considers the relationship between spatially neighboring pixels of a label map, such as Markov and conditional random fields. CRFNet comprises two modules: a refiner and a combiner that, respectively, refine the context information from the output features of the conventional semantic segmentation network model and combine the refined features with the intermediate features from the decoding process of the segmentation model to produce the final output. To train CRFNet to refine the semantic predictions more accurately, we proposed a sequential training scheme. Using various backbone networks (ENet, ERFNet, and HyperSeg), we extensively evaluated our model on three large-scale, real-world datasets to demonstrate the effectiveness of our approach.     

基于残差网络的无监督角膜视频分割算法

基于角膜形变计算出一系列生物力学特性参数是训练早期圆锥角膜分类模型的数据基础,因此圆锥角膜轮廓分割的精确性直接影响着早期圆锥角膜分类模型的准确性。本文提出了一种基于残差网络的无监督角膜视频分割方法。通过统一的网格化采样提取一组锚点被同序列视频帧所共用,从而减小网络模型学习特征表示的计算量并且提高了计算效率。同时设计了一个正则化分支对原有的视频集进行相似性转换来解决可能存在的退化解问题。与已有的无监督视频分割任务相比,本实验模型使用了少量的训练数据,但却取得了更高的分割精度和计算效率。     

Hierarchical stochastic image grammars for classification and segmentation.

We develop a new class of hierarchical stochastic image models called spatial random trees (SRTs) which admit polynomial-complexity exact inference algorithms. Our framework of multitree dictionaries is the starting point for this construction. SRTs are stochastic hidden tree models whose leaves are associated with image data. The states at the tree nodes are random variables, and, in addition, the structure of the tree is random and is generated by a probabilistic grammar. We describe an efficient recursive algorithm for obtaining the maximum a posteriori estimate of both the tree structure and the tree states given an image. We also develop an efficient procedure for performing one iteration of the expectation-maximization algorithm and use it to estimate the model parameters from a set of training images. We address other inference problems arising in applications such as maximization of posterior marginals and hypothesis testing. Our models and algorithms are illustrated through several image classification and segmentation experiments, ranging from the segmentation of synthetic images to the classification of natural photographs and the segmentation of scanned documents. In each case, we show that our method substantially improves accuracy over a variety of existing methods.     

基于生成对抗网络的语义分割方法

在语义分割模型结构不变的前提下,为提升模型对图像分割的精确度,引入生成对抗网络结构用于训练语义分割模型(SS-GAN)。SS-GAN包含3个设计环节：构建全卷积网络(FCN)结构的生成模型,进行初步的图像分割;设计具备像素间高阶关系学习能力的对抗模型,提高生成模型的学习能力;加入对抗损失辅助生成模型学习,进一步促进生成网络自主学习像素间关系。在计算机视觉竞赛数据集(PASCAL VOC)和城市景观数据集(Cityscapes)上的实验结果表明,引入生成对抗网络后取得了更好的效果,2个数据集的交并比(IoU)指标分别提高了1.56%/1.17%和1.93%/1.55%。     

基于DeepLabv3+网络的电流互感器红外图像分割方法

红外图像智能分析是变电设备故障诊断的一种有效方法,目标设备分割是其关键技术。本文针对复杂背景下电流互感器整体分割难的问题,采用基于ResNet50的DeepLabv3+神经网络,用电流互感器的红外图像训练语义分割模型的方法,对收集到的样本采用限制对比度自适应直方图均衡化方法实现图像轮廓增强,构建样本数据集,并运用图像变换扩充样本数据集,搭建语义分割网络训练语义分割模型,实现电流互感器像素与背景像素的二分类。通过文中方法对420张电流互感器红外图像测试,结果表明,该方法的平均交并比（Mean Intersection over Union, MIoU）为87.5%,能够从测试图像中精确分割出电流互感器设备,为后续电流互感器的故障智能诊断做铺垫。     

基于空间语义对象混合学习的复杂图像场景自动分类方法研究

场景分类是将多幅图像标记为不同语义类别的过程。该文针对现有方法对复杂图像场景分类性能欠佳的不足,提出一种新的基于空间语义对象混合学习的复杂图像场景分类方法。该方法以多尺度分割得到的图像对象而非整幅图像为主体进行产生式语义建模,统计各类有效特征挖掘对象的类别分布信息,并通过空间金字塔匹配,构建包含层次数据和语义信息的中间向量,弥补语义鸿沟的缺陷,训练中还结合判别式学习提高分类器的可信性。在实验数据集上的结果表明该方法具备较高的学习性能和分类精度,适用于多种类型和复杂内容图像的解译,具有较强的实用价值。     

利用覆盖歧义检测法和统计语言模型进行汉语自动分词

该文探讨了利用覆盖歧义检测法和统计语言模型进行汉语自动分词的问题。采用了多次迭代的方法来进行汉语词层面统计语言模型的训练。该方法能够得到更优化的语言模型。该文详细介绍了统计语言模型的训练过程,给出了语言模型复杂度随迭代次数增加而减小的实验结果。还给出了在不同的统计语言模型阶数下切分正确率变化的情况,分析了切分正确率变化的原因。     

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。     

Image and texture segmentation using local spectral histograms.

We present a method for segmenting images consisting of texture and nontexture regions based on local spectral histograms. Defined as a vector consisting of marginal distributions of chosen filter responses, local spectral histograms provide a feature statistic for both types of regions. Using local spectral histograms of homogeneous regions, we decompose the segmentation process into three stages. The first is the initial classification stage, where probability models for homogeneous texture and nontexture regions are derived and an initial segmentation result is obtained by classifying local windows. In the second stage, we give an algorithm that iteratively updates the segmentation using the derived probability models. The third is the boundary localization stage, where region boundaries are localized by building refined probability models that are sensitive to spatial patterns in segmented regions. We present segmentation results on texture as well as nontexture images. Our comparison with other methods shows that the proposed method produces more accurate segmentation results.     

Object localization and border detection criteria design in edge-based image segmentation: automated learning from examples

This paper provides methodology for fully automated model-based image segmentation. All information necessary to perform image segmentation is automatically derived from a training set that is presented in a form of segmentation examples. The training set is used to construct two models representing the objects--shape model and border appearance model. A two-step approach to image segmentation is reported. In the first step, an approximate location of the object of interest is determined. In the second step, accurate border segmentation is performed. The shape-variant Hough transform method was developed that provides robust object localization automatically. It finds objects of arbitrary shape, rotation, or scaling and can handle object variability. The border appearance model was developed to automatically design cost functions that can be used in the segmentation criteria of edge-based segmentation methods. Our method was tested in five different segmentation tasks that included 489 objects to be segmented. The final segmentation was compared to manually defined borders with good results [rms errors in pixels: 1.2 (cerebellum), 1.1 (corpus callosum), 1.5 (vertebrae), 1.4 (epicardial), and 1.6 (endocardial) borders]. Two major problems of the state-of-the-art edge-based image segmentation algorithms were addressed: strong dependency on a close-to-target initialization, and necessity for manual redesign of segmentation criteria whenever new segmentation problem is encountered.     

Faster-RCNN和Level-Set结合的高分遥感影像建筑物提取

目前Level-Set图像分割方法存在初始轮廓的确定受人为因素影响较大的问题，对目标被遮盖和目标与背景灰度值相近无法达到理想的分割效果。针对此问题，本文提出了利用Faster-RCNN网络模型确定目标初始轮廓和区域信息的先验水平集图像分割方法，搭建Caffe深度学习框架训练Faster-RCNN网络模型；通过有监督学习的方式在IAILD数据集上训练模型，检测出目标建筑物并初步提取建筑物的轮廓，并将其与形状先验的Level-Set算法结合。对比实验结果表明，本文方法解决了Level-Set算法中图像分割结果初始轮廓受人为标记框选的影响较大的问题，能够更好地完成被遮挡建筑物的分割，对于目标建筑和背景灰度值相近也能达到更好的分割效果。     

Combining strings and necklaces for interactive three-dimensional segmentation of spinal images using an integral deformable spine model

Segmentation of the spine directly from three-dimensional (3-D) image data is desirable to accurately capture its morphological properties. We describe a method that allows true 3-D spinal image segmentation using a deformable integral spine model. The method learns the appearance of vertebrae from multiple continuous features recorded along vertebra boundaries in a given training set of images. Important summarizing statistics are encoded into a necklace model on which landmarks are differentiated on their free dimensions. The landmarks are used within a priority segmentation scheme to reduce the complexity of the segmentation problem. Necklace models are coupled by string models. The string models describe in detail the biological variability in the appearance of spinal curvatures from multiple continuous features recorded in the training set. In the segmentation phase, the necklace and string models are used to interactively detect vertebral structures in new image data via elastic deformation reminiscent of a marionette with strings allowing for movement between interrelated structures. Strings constrain the deformation of the spine model within feasible solutions. The driving application in this work is analysis of computed tomography scans of the human lumbar spine. An illustration of the segmentation process shows that the method is promising for segmentation of the spine and for assessment of its morphological properties.     

基于softmax回归与图割法的脑肿瘤分割算法

从医学图像中分割脑肿瘤区域可以为脑肿瘤的诊断以及放射治疗提供帮助.但肿瘤区域的变化异常且边界非常模糊,因此自动或半自动地分割脑肿瘤非常困难.针对这一问题,本文结合softmax回归和图割法提出一种脑肿瘤分割算法.首先融合多序列核磁共振图像(MRI)并标记训练样本,再用softmax回归训练模型参数并计算每个点属于各个类别的概率,最后将概率融入到图割法中,用最小切/最大流方法得到最终分割结果.实验表明提出的方法可以更好地得到脑肿瘤的边界,并能较准确地分割出脑肿瘤区域.     

Fast algorithms for phone classification and recognition usingsegment-based models

Methods for reducing the computation requirements of joint segmentation and recognition of phones using the stochastic segment model are presented. The approach uses a fast segment classification method that reduces computation by a factor of two to four, depending on the confidence of choosing the most probable model. A split-and-merge segmentation algorithm is proposed as an alternative to the typical dynamic programming solution of the segmentation and recognition problem, with computation savings increasing proportionally with model complexity. Although the current recognizer uses context-independent phone models, the results reported for the TIMIT database for speaker-independent joint segmentation and recognition are comparable to those of systems that use context information     

基于多模型融合方法的肺结节良恶性分类

针对CT图像中肺结节因边缘模糊、特征不明显造成的分类效果有偏差的问题,本文提出一种嵌入注意力机制的多模型融合方法(简称MSMA-Net).该方法先将原始CT图像进行肺实质分割和裁剪操作后得到两种不同尺寸的图像,然后分别输入到空间注意力模型和通道注意力模型进行训练,其中,空间注意力模型着重于提取肺结节在CT图像中的空间位...     

基于超像素与图卷积神经网络的白细胞分割

白细胞分割是医学图像处理领域的一项富有挑战性的任务,针对目前白细胞分割存在的准确度不高、粘连情况不易分割等问题,将图像的分割转化为区域节点的分类问题,提出基于图卷积神经网络的白细胞分割算法.首先将训练图像经超像素分割得到若干超像素区域,把每个超像素区域作为图的一个节点,并充分利用超像素区域的彩色特征以及空间邻域关系构造稀疏加权图来训练图卷积网络,然后利用训练好的网络对测试图像进行白细胞核、质、背景的三域一次性分类.实验数据表明,本文算法对不同类白细胞均具有较好的分割效果.     

Image segmentation using hidden Markov Gauss mixture models.

Image segmentation is an important tool in image processing and can serve as an efficient front end to sophisticated algorithms and thereby simplify subsequent processing. We develop a multiclass image segmentation method using hidden Markov Gauss mixture models (HMGMMs) and provide examples of segmentation of aerial images and textures. HMGMMs incorporate supervised learning, fitting the observation probability distribution given each class by a Gauss mixture estimated using vector quantization with a minimum discrimination information (MDI) distortion. We formulate the image segmentation problem using a maximum a posteriori criteria and find the hidden states that maximize the posterior density given the observation. We estimate both the hidden Markov parameter and hidden states using a stochastic expectation-maximization algorithm. Our results demonstrate that HMGMM provides better classification in terms of Bayes risk and spatial homogeneity of the classified objects than do several popular methods, including classification and regression trees, learning vector quantization, causal hidden Markov models (HMMs), and multiresolution HMMs. The computational load of HMGMM is similar to that of the causal HMM.     

Learning bayesian classifiers for scene classification with a visual grammar

A challenging problem in image content extraction and classification is building a system that automatically learns high-level semantic interpretations of images. We describe a Bayesian framework for a visual grammar that aims to reduce the gap between low-level features and high-level user semantics. Our approach includes modeling image pixels using automatic fusion of their spectral, textural, and other ancillary attributes; segmentation of image regions using an iterative split-and-merge algorithm; and representing scenes by decomposing them into prototype regions and modeling the interactions between these regions in terms of their spatial relationships. Naive Bayes classifiers are used in the learning of models for region segmentation and classification using positive and negative examples for user-defined semantic land cover labels. The system also automatically learns representative region groups that can distinguish different scenes and builds visual grammar models. Experiments using Landsat scenes show that the visual grammar enables creation of high-level classes that cannot be modeled by individual pixels or regions. Furthermore, learning of the classifiers requires only a few training examples.     

A new statistical model for Markovian classification of urban areas in high-resolution SAR images

We propose a classification method suitable for high-resolution synthetic aperture radar (SAR) images over urban areas. When processing SAR images, there is a strong need for statistical models of scattering to take into account multiplicative noise and high dynamics. For instance, the classification process needs to be based on the use of statistics. Our main contribution is the choice of an accurate model for high-resolution SAR images over urban areas and its use in a Markovian classification algorithm. Clutter in SAR images becomes non-Gaussian when the resolution is high or when the area is man-made. Many models have been proposed to fit with non-Gaussian scattering statistics (K, Weibull, Log-normal, Nakagami-Rice, etc.), but none of them is flexible enough to model all kinds of surfaces in our context. As a consequence, we use a mathematical model that relies on the Fisher distribution and the log-moment estimation and which is relevant for one-look data. This estimation method is based on the second-kind statistics, which are detailed in the paper. We also prove its accuracy for urban areas at high resolution. The quality of the classification that is obtained by mixing this model and a Markovian segmentation is high and enables us to distinguish between ground, buildings, and vegetation.     

Comparison and Evaluation of Methods for Liver Segmentation From CT Datasets

This paper presents a comparison study between 10 automatic and six interactive methods for liver segmentation from contrast-enhanced CT images. It is based on results from the “MICCAI 2007 Grand Challenge” workshop, where 16 teams evaluated their algorithms on a common database. A collection of 20 clinical images with reference segmentations was provided to train and tune algorithms in advance. Participants were also allowed to use additional proprietary training data for that purpose. All teams then had to apply their methods to 10 test datasets and submit the obtained results. Employed algorithms include statistical shape models, atlas registration, level-sets, graph-cuts and rule-based systems. All results were compared to reference segmentations five error measures that highlight different aspects of segmentation accuracy. All measures were combined according to a specific scoring system relating the obtained values to human expert variability. In general, interactive methods reached higher average scores than automatic approaches and featured a better consistency of segmentation quality. However, the best automatic methods (mainly based on statistical shape models with some additional free deformation) could compete well on the majority of test images. The study provides an insight in performance of different segmentation approaches under real-world conditions and highlights achievements and limitations of current image analysis techniques.