Theory of edge perception for computer vision feedback control

In this paper, the authors address the problem of edge-perception for its applications to vision-feedback control in robotic systems.In natural vision, the recognition of objects takes place through the process consisting of eye system, neural networks and cognition. The cognitive process, in turn yields a phenomenon known as perception. This is the phenomenon of perception of physical attributes, such as edges, color and texture, etc., which is responsible for the recognition of objects through the natural vision processes.In this paper, we make an attempt to postulate the theory of perception for gray-level images. The gray-level images, when going through the cognitive and perception processes, are contaminated by the uncertainty; here we call it cognitive uncertainty.The studies in this paper are confined to the phenomenon of edge-perception for two-dimensional gray-level images, however, these studies can be extended to other types of visual attributes both in two-dimensional and three-dimensional spaces. Indeed, the perception of these attributes, which attempts to emulate the human vision system, may help in the design of a truly robust computer vision-feedback control system for robotic applications.     

基于滤波的SAR影像去噪方法分析

根据SAR(Synthetic Aperture Radar)影像相干噪声的特点,对现在广泛应用的各种抑制噪声的滤波方法如均值滤波、Frost滤波、增强型Lee滤波、Lee滤波、中值滤波等进行分析,并提出适合本研究区影像的基于小波变换的分量滤波处理去噪方法,利用均值、标准差、平滑指数、PM值、信息熵和平均梯度等评价指标对各种滤波去噪后的影像质量进行评价,并对去噪效果进行对比分析,证明本文所采用的滤波方法对SAR影像噪声有很好的抑制作用,并且较好的保存了图像纹理信息。     

高斯颜色模型在瓷片图像分类中的应用

由于RGB颜色空间不能很好贴近人的视觉感知,同时也缺少对空间结构的描述,因此采用兼顾颜色信息和空间信息的高斯颜色模型以获取更全面的特征,提出了一种基于高斯颜色模型和多尺度滤波器组的彩色纹理图像分类法,用于瓷器碎片图像的分类。首先将原始图像的RGB颜色空间转换到高斯颜色模型;再用正规化多尺度LM滤波器组对高斯颜色模型的3个通道构造滤波图像,并借助主成分分析寻找主特征图,接着选取各通道的最大高斯拉普拉斯和最大高斯响应图像,与特征图联合构成特征图像组用以进行参数提取;最后以支持向量机作为分类器进行学习和分类。实验结果表明,与基于灰度的、基于RGB模型的和基于RGB_bior 4.4小波的方法相比,本文方法具有更好的分类结果,其中在Outex纹理图像库上获得的分类准确率为96.7%,在瓷片图像集上获得的分类准确率为94.2%。此方法可推广应用到其他彩色纹理分类任务。     

基于卡尔曼滤波SVM图像鉴别方法研究

研究如何区分自然图像和计算机图形判别图像问题。由于人眼难以判别真伪图像,针对传统的图像鉴别方法由于参数的设置而造成识别准确率低,从而无法准确的区分自然图像和计算机图形。提出了一种卡尔曼滤波和支持向量机分类算法相结合的高性能图像真伪鉴别方法。算法首先采用卡尔曼滤波器提取图像的各个级别的分量,求解出各级分量和判别的误差值并作为特征数据,然后采用支持向量机分类算法对特征数据进行训练判别。仿真结果表明,提出的算法可以有效的判别图像的真伪,可以有效的识别出原始自然图像和合成图像,识别率高达99%以上,同时算法的稳定性较高,具有一定的实际应用价值。     

基于叶片形态特征的葡萄品种自动识别

葡萄在全世界种植范围较广,葡萄品种识别对葡萄资源统计、新品种鉴定及遗传资源保护都有重要意义。以成熟叶片为基本材料,不变矩、面积、周长、主叶脉长度和叶柄长度等11维特征向量为基础数据,采用叶片特征选择、图像处理、特征值提取、建立分类模型等方法,运用国际葡萄与葡萄酒组织形态分类方法和改进的欧式距离等技术开发一个基于葡萄叶片数字图像的葡萄品种自动识别软件。共测试17种酿酒和3种野生葡萄,识别率达87%。该方法具有自动化、识别速度快、花费低、省时省力等特点,可应用于葡萄病虫害的识别、杂交新品种双亲的判定等。     

基于多任务卷积神经网络的虹膜图像质量评估方法

为了自动、准确、高效地评估采集图像的质量,设计了一个名为MTIQA的卷积神经网络。该网络能够输出与主观评价指标保持较高一致性的客观评估结果。MTIQA采用多任务学习策略,包含网络训练质量评估和失真类型分类两个任务,将两个任务的损失融合并构成新的损失函数。为了评估算法所得到的客观指标的可靠性,建立了名为SIR2019的单眼虹膜质量评估数据集,并召集志愿者进行主观实验以得到主观评价指标。在SIR2019和CASIA-Iris-Distance-Lamp数据集上的实验结果表明,该网络在虹膜图像质量评估上具有较好的可行性、准确性和鲁棒性。     

一种面向弱纹理图像的特征点描述子

现有的大多数特征点提取算法适用于处理纹理丰富的图像,而对于弱纹理图像则无法提取有效的特征点. 对此,提出了多邻域结构张量特征(MNSTF)算法. 基于一系列固定的邻域和图像结构张量,通过表达局部图像的结构和纹理信息,解决了弱纹理和无纹理场景下特征点提取和匹配等相关问题;同时,通过计算邻域之间的相对方向,实现了MNSTF算法特征描述子的旋转不变性. 实验结果表明,MNSTF算法在经过旋转的弱纹理图像测试集上的特征点匹配准确率达到了99.9%以上,验证了其良好的适用性、旋转不变性和鲁棒性.     

Physiological Imaging Methods for Evaluating Response to Immunotherapies in Glioblastomas

Glioblastoma (GBM) is the most malignant brain tumor in adults, with a dismal prognosis despite aggressive multi-modal therapy. Immunotherapy is currently being evaluated as an alternate treatment modality for recurrent GBMs in clinical trials. These immunotherapeutic approaches harness the patient’s immune response to fight and eliminate tumor cells. Standard MR imaging is not adequate for response assessment to immunotherapy in GBM patients even after using refined response assessment criteria secondary to amplified immune response. Thus, there is an urgent need for the development of effective and alternative neuroimaging techniques for accurate response assessment. To this end, some groups have reported the potential of diffusion and perfusion MR imaging and amino acid-based positron emission tomography techniques in evaluating treatment response to different immunotherapeutic regimens in GBMs. The main goal of these techniques is to provide definitive metrics of treatment response at earlier time points for making informed decisions on future therapeutic interventions. This review provides an overview of available immunotherapeutic approaches used to treat GBMs. It discusses the limitations of conventional imaging and potential utilities of physiologic imaging techniques in the response assessment to immunotherapies. It also describes challenges associated with these imaging methods and potential solutions to avoid them.     

New software developments for quality mesh generation and optimization from biomedical imaging data

In this paper we present a new software toolkit for generating and optimizing surface and volumetric meshes from three-dimensional (3D) biomedical imaging data, targeted at image-based finite element analysis of some biomedical activities in a single material domain. Our toolkit includes a series of geometric processing algorithms including surface re-meshing and quality-guaranteed tetrahedral mesh generation and optimization. All methods described have been encapsulated into a user-friendly graphical interface for easy manipulation and informative visualization of biomedical images and mesh models. Numerous examples are presented to demonstrate the effectiveness and efficiency of the described methods and toolkit.     

基于各向异性滤波和空间FCM的MRI图像分割方法

针对具复杂目标和边界模糊的MRI图像中多感兴趣区域的分割中分割MRI图像软组织难的问题, 提出了一种基于各向异性滤波和空间模糊C-均值聚类(SFCM)的MRI图像分割方法; 用新型各向异性滤波对图像进行预处理, 解决去噪平滑的同时弱化图像细节的问题; 用邻域空间信息设计空间函数, 改进传统FCM的目标函数; 用图像的空间信息实现图像各目标准确分类、有效解决孤立区域的正确归类问题, 进而使分割区域完整; 用直方图拟合曲线初始化分类数和初始聚类中心, 加快算法迭代到最优解, 进而减少运行时间。通过实验证实了各向异性滤波和空间FCM的MRI图像分割方法的综合应用显著提高了分割灰度重叠、目标不连续和目标边界模糊的MRI图像的分割效果。