融合Hu矩与BoF-SURF支持向量机的手势识别

基于尺度不变特征变换的特征包（BoF-SIFT）支持向量机的分类方法具有较好的手势识别效果, 但是计算复杂度高、实时性较差。为此, 提出了融合Hu矩与基于快速鲁棒特征的特征包（BoF-SURF）支持向量机（SVM）的手势识别方法。特征包模型中用快速鲁棒性特征（SURF）算法替换尺度不变特征变换（SIFT）算法提取特征, 提高了实时性, 并引入Hu矩描述手势全局特征, 进一步提高识别率。实验结果表明, 算法无论是实时性还是识别率都要高于BoF-SIFT支持向量机方法。     

Pattern recognition for characterization of pharmaceutical powders

A large part of pharmaceutical manufacturing involves the use of particulate materials. It is well known that both particle size and shape affect the physical characteristics of tablets. An image processing and analysis algorithm based on the invariant image moment technique was developed in this work to determine the particle shape by comparing features (moments) extracted from templates to those extracted from each of the objects in the image. First it determines the particle shape (rectangle, circle, etc.) and then calculates its specific dimensions (diameter, aspect ratio).The statistical validation of the vision system obtained a repeatability of 0.0012 in and 0.5% relative standard deviation and accuracy within 0.1 to 0.9% of the average value considered as true value. Also the pattern recognition technique indicated high precision and accuracy for images containing particles with some level of contact between them. The shape recognition of microcrystalline cellulose (MCC) indicated that particles of equant and acicular shape as defined by USP are predominant. The results suggest that image processing and analysis would be a suitable tool for pharmaceutical process analytical technologies (PAT) and process optimization.     

Integral approximation—an approach to reduced models for particulate processes

In this contribution, a model reduction technique for population balance systems describing particulate processes is presented. This technique is based on integral approximation and allows the derivation of highly accurate moment models. In contrast to other model reduction methods which can be found in literature, this integral approximation technique can be applied for arbitrarily complex phenomena specifications. The applicability of the presented method will be demonstrated for different example processes by comparing the dynamic behavior of the original population balance models with those of the derived reduced models of moments.     

模拟尾流气泡幕的灰度图像分析

为了对舰船尾流产生的大量气泡进行实时探测,对气泡的密度分布进行了分类判别,利用灰度图像直方图统计矩法,分析了随着压强增大,灰度直方图的峰值由较暗向较亮方向移动.应用图像处理技术对不同压强下模拟尾流气泡幕的统计特性参数(均值、三阶矩、标准偏差、归一化、一致性、熵)进行分析,研究结果表明:随着压强的增大气泡幕图像的均值递增说明平均灰度级在递增;三阶矩呈递减状态反映了图像灰度直方图的"歪斜程度";在其他4个参数的曲线中0.025 MPa所对应的值说明了所采集的气泡幕图像的纹理特征比0.02 MPa,0.03 MPa,0.035 MPa压强下的要粗糙;所提取的六个特征参数准确的表征了不同压强下气泡幕的特征.     

基于Zernike矩亚像素边缘检测的改进算法

通过分析Zernike矩以及基于Zernike矩的亚像素图像边缘检测原理,针对Ghosal提出的基于Zernike矩的亚像素图像边缘检测算法检测出的图像存在边缘较粗及边缘亚像素定位精度低等不足,提出一种改进算法。推导了Zernike矩模板系数,提出一种新的边缘判断依据。改进的算法能较好检测图像边缘并实现较高的边缘定位。最后,设计两组实验,实验结果将各尺寸模板结果及与Ghosal算法进行比较,证明了改进算法的优越性。     

大尺寸图片的复制粘贴检测*

针对目前图像复制粘贴检测算法有时间复杂度高、当图像中有光滑区域时错检率大的缺点,将图像角点区域及其八方向邻接圆形区域作为伪造检测区域,提取每个检测区域的矩特征后用k-d树进行排序,并通过比较每个区域矩特征的相似性来定位伪造复制区域.该算法效率高,且对经过旋转、添加噪声、模糊、JPEG压缩等后处理的复制粘贴伪造图像检测效果很好.     

Elastoplastic Finite Element Analysis and Strength Evaluation of Adhesive Butt Joints of Similar and Dissimilar Hollow Shafts Subjected to External Bending Moments

Stress distributions and deformation of adhesive butt joints are analyzed by an elastoplastic finite element method when the joints of similar and dissimilar shafts are subjected to external bending moments. The effects of the ratio of Young's modulus for the adherends to that for an adhesive and the effects of the adhesive thickness on the interface stress distribution are investigated. Joint strength is predicted by using the elastoplastic interface stress distributions. It is found that the singular stress at the edge of the interfaces increases with an increase of the ratio of Young's modulus. Measurement of strains in joints and experiments on joint strength were conducted. The numerical results are in fairly good agreement with the experimental results. It is observed that the joint strength for dissimilar shafts are smaller than those for similar shafts. A fracture of dissimilar adhesive up-bonded shafts occurred from the interface of the adherend with smaller Young's modulus. It is seen that joint strength increases as the adhesive thickness increases.     

Implementation of the quadrature method of moments in CFD codes for aggregation-breakage problems

In this work the quadrature method of moments (QMOM) is implemented in a commercial computational fluid dynamics (CFD) code (FLUENT) for modeling simultaneous aggregation and breakage. Turbulent and Brownian aggregation kernels are considered in combination with different breakage kernels (power law and exponential) and various daughter distribution functions (symmetric, erosion, uniform). CFD predictions are compared with experimental data taken from other work in the literature and conclusions about CPU time required for the simulations and the advantages of this approach are drawn.     

竞争型小波神经网络在零件分类中的应用

文章将小波分析与竞争型神经网络相结合,构造了适应于零件分类的竞争型小波神经网络(CWN)。首先对零件先进行小波多尺度边缘检测,然后采用不变矩方法提取零件的特征,最后送入CWN加以分类。分类结果表明,CWN对相似零件能够有效分类,并且有一定的鲁棒性。     

基于颜色传递的不同季节植物表观仿真

为模拟植物在不同季节的颜色变化,提出一种在虚拟环境中实现对不同季节植物表观仿真的方法.采用基于二阶统计量的全局颜色传递算法,得到不同季节的纹理库;基于生成的纹理库实现对不同季节植物的表观仿真.为改善传递效果,引入高阶矩,调整目标图像的斜度和峰度分布,使之与样本图像一致.建立评估模型,从颜色和纹理两方面对传递效果进行评估,评估结果表明,该方法的仿真效果较好.