Automatic brain tissue segmentation in MR images using hybrid atlas forest based on confidence-weighted probability matrix

The segmentation of specific tissues in an MR brain image for quantitative analysis can assist the disease diagnosis and medical research. Therefore, a robust and accurate method for automatic segmentation is necessary. Atlas-based-method is a common and effective method of automatic segmentation where an atlas refers to a pair of image consist of an intensity image and its corresponding label image. Apart from the general multi-atlas-based methods, which propagate labels through the single atlas then fuse them, we proposed a hybrid atlas forest based on confidence-weighted probability matrix to consider the atlases set as a whole and treat each voxel differently. In the framework, we first register the atlas to the image space of target and calculate the confidence of voxels in the registered atlas. Then, a confidence-weighted probability matrix is generated and it augments to the intensity image of the atlas or target for providing spatial information of the target tissue. Third, a hybrid atlas forest is trained to gather the features and correlation information among the atlases in the dataset. Finally, the segmentation of the target tissues is predicted by the trained hybrid atlas forest. The segment performance and the components efficiency of the proposed method are evaluated on the two public datasets. Based on the experiment results and quantitative comparisons, our method can gather spatial information and correlation among the atlases to obtain an accurate segmentation.     

Retinal Vessel Extraction Framework Using Modified Adaboost Extreme Learning Machine

An explicit extraction of the retinal vessel is a standout amongst the most significant errands in the field of medical imaging to analyze both the ophthalmological infections, for example, Glaucoma, Diabetic Retinopathy (DR), Retinopathy of Prematurity (ROP), Age-Related Macular Degeneration (AMD) as well as non retinal sickness such as stroke, hypertension and cardiovascular diseases. The state of the retinal vasculature is a significant indicative element in the field of ophthalmology. Retinal vessel extraction in fundus imaging is a difficult task because of varying size vessels, moderately low distinction, and presence of pathologies such as hemorrhages, microaneurysms etc. Manual vessel extraction is a challenging task due to the complicated nature of the retinal vessel structure, which also needs strong skill set and training. In this paper, a supervised technique for blood vessel extraction in retinal images using Modified Adaboost Extreme Learning Machine (MAD-ELM) is proposed. Firstly, the fundus image preprocessing is done for contrast enhancement and in-homogeneity correction. Then, a set of core features is extracted, and the best features are selected using “minimal Redundancy-maximum Relevance (mRmR).” Later, using MAD-ELM method vessels and non vessels are classified. DRIVE and DR-HAGIS datasets are used for the evaluation of the proposed method. The algorithm’s performance is assessed based on accuracy, sensitivity and specificity. The proposed technique attains accuracy of 0.9619 on the DRIVE database and 0.9519 on DR-HAGIS database, which contains pathological images. Our results show that, in addition to healthy retinal images, the proposed method performs well in extracting blood vessels from pathological images and is therefore comparable with state of the art methods.     

一种结合区域检测和语义分割的SLAM技术

提出一种结合区域检测和语义分割的即时定位和建图（SLAM）技术，通过引入高精度图像描述子SIFT来实现前端视觉里程计（VO）过程中帧间像素匹配的精度。为了降低引入操作带来的计算复杂度，设计一个实时区域检测算法，在相邻帧间检测大致相似的ROI(Region of Interest)关键区域，使得SIFT描述子的提取和匹配只在ROI区域内完成，其余区域仍旧采用精度略低、效率更高的ORB算子。同时，为了提高后端BA(Bundle Adjustment)的精度，减少累积误差，结合语义图，在原有的基本投影误差函数上添加一个语义误差。该语义图采用实时语义分割算法完成，同时只针对ROI区域进行分割。通过与原SLAM方案对比实验，表明本文提出的方法，在提高一定精度的同时，仍能满足SLAM实时定位和建图的要求。最后，在电力作业场景下验证了该方案的效果。     

磁环表面缺陷图像分割算法的研究及实时实现

为实现小型磁环表面细微缺陷图像无监督分割,并提高分割精度与计算效率,本文提出了一种基于改进2D Gabor滤波器组的自适应阈值分割方法。首先,利用多尺度、多方向的Gabor滤波器组对缺陷图像进行滤波降噪处理,抑制目标区域与背景区域内部的噪声污染,同时增强区域间的差异性；然后,通过对处理后图像的灰度统计特性分析,根据缺陷图像的灰度均值及方差构造了灰度阈值计算公式,实现了小型磁环表面细微缺陷图像的自适应分割。实验结果表明,本文算法可快速、准确地分割缺陷并抑制噪声干扰,在分割精度、计算效率等方面也优于传统的选择迭代法、OTSU、最大熵等方法,并能够在先进的SEED-DVS8168平台上实时实现,验证了此算法的可行性与实时性。     

大口径管道直管段制作技术应用

针对大口径管道施工过程中存在施工周期长,施工难度大,工程成本高等问题,提出一种新型优化管段分段技术和管段组对方案。结果表明:该制作技术能保证大口管道安装施工顺利进行;有效地解决现有大口径套管安装过程中的技术难题。该方法具有创新性、实用性、可靠性等优点,在工程建设的许多领域,具有推广应用价值。     

基于自监督学习的病理图像层次分割

在苏木精-伊红(HE)染色病理图像中，细胞染色分布的不均匀和各类组织形态的多样性给病理图像的自动分割带来极大挑战。为解决该问题，提出了一种基于自监督学习的病理图像三步层次分割方法，对病理图像中各类组织进行由粗略到精细的全自动逐层分割。首先，根据互信息的计算结果在RGB色彩空间中进行特征选择；其次，采用K-means聚类将图像初步分割为各类组织结构的色彩稳定区域与模糊区域；然后，以色彩稳定区域为训练集采用朴素贝叶斯分类对模糊区域进行进一步分割，得到完整的细胞核、细胞质和胞外间隙这三类组织结构；最后，对细胞核部分进行结合形状和色彩强度的混合分水岭分割得到细胞核间的精确边界，进而量化计算细胞核个数、核占比、核质比等指标。对脑膜瘤HE染色病理图像的分割实验结果表明，所提方法对于染色和细胞形态差异保持较高的鲁棒性，各类组织区域分割误差在5%以内，在细胞核分割精度的对比实验中平均正确率在96%以上，满足临床自动图像分析的要求，其量化结果可以为定量病理分析提供依据。     

基于深度学习的秀丽隐杆线虫显微图像分割方法

利用计算机实现自动、准确的秀丽隐杆线虫(C.elegans)的各项形态学参数分析,至关重要的是从显微图像上分割出线虫体态,但由于显微镜下的图像噪声较多,线虫边缘像素与周围环境相似,而且线虫的体态具有鞭毛和其他附着物需要分离,多方面因素导致设计一个鲁棒性的C.elegans分割算法仍然面临着挑战。针对这些问题,提出了一种基于深度学习的线虫分割方法,通过训练掩模区域卷积神经网络(Mask R-CNN)学习线虫形态特征实现自动分割。首先,通过改进多级特征池化将高级语义特征与低级边缘特征融合,结合大幅度软最大损失(LMSL)损失算法改进损失计算;然后,改进非极大值抑制;最后,引入全连接融合分支等方法对分割结果进行进一步优化。实验结果表明,相比原始的Mask R-CNN,该方法平均精确率(AP)提升了4.3个百分点,平均交并比(mIOU)提升了4个百分点。表明所提出的深度学习分割方法能够有效提高分割准确率,在显微图像中更加精确地分割出线虫体。     

A Student's t-based density peaks clustering with superpixel segmentation (tDPCSS) method for image color clustering

Image color clustering is a basic technique in image processing and computer vision, which is often applied in image segmentation, color transfer, contrast enhancement, object detection, skin color capture, and so forth. Various clustering algorithms have been employed for image color clustering in recent years. However, most of the algorithms require a large amount of memory or a predetermined number of clusters. In addition, some of the existing algorithms are sensitive to the parameter configurations. In order to tackle the above problems, we propose an image color clustering method named Student's t-based density peaks clustering with superpixel segmentation (tDPCSS), which can automatically obtain clustering results, without requiring a large amount of memory, and is not dependent on the parameters of the algorithm or the number of clusters. In tDPCSS, superpixels are obtained based on automatic and constrained simple non-iterative clustering, to automatically decrease the image data volume. A Student's t kernel function and a cluster center selection method are adopted to eliminate the dependence of the density peak clustering on parameters and the number of clusters, respectively. The experiments undertaken in this study confirmed that the proposed approach outperforms k-means, fuzzy c-means, mean-shift clustering, and density peak clustering with superpixel segmentation in the accuracy of the cluster centers and the validity of the clustering results.     

基于机器视觉的运煤车车号识别技术研究

在铁路运煤装车过程中为了快速、准确地识别车号,提出一种基于机器视觉的运煤车车号识别技术。将连通区域提取与投影分割法结合,实现车号的粗定位、细分割,并对图像中的断裂字符进行二次分割,构建了基于BP神经网络的分类模型进行车号识别,提升了煤炭装车的效率和精度。     

ECISER: Efficient Clip-art Image SEgmentation by Re-rasterization

Clip-art image segmentation is widely used as an essential step to solve many vision problems such as colorization and vectorization. Many of these applications not only demand accurate segmentation results, but also have little tolerance for time cost, which leads to the main challenge of this kind of segmentation. However, most existing segmentation techniques are found not sufficient for this purpose due to either their high computation cost or low accuracy. To address such issues, we propose a novel segmentation approach, ECISER, which is well-suited in this context. The basic idea of ECISER is to take advantage of the particular nature of cartoon images and connect image segmentation with aliased rasterization. Based on such relationship, a clip-art image can be quickly segmented into regions by re-rasterization of the original image and several other computationally efficient techniques developed in this paper. Experimental results show that our method achieves dramatic computational speedups over the current state-of-the-art approaches, while preserving almost the same quality of results.