A study of the dependence of wavelet-transform coefficients on the geometrical parameters of discontinuity flaws

The dependence of the wavelet-transform coefficients of the magnetic field of a continuity flaw in a ferromagnetic article on its geometrical dimensions is theoretically and experimentally studied.     

Dependence of the cutting energy on the parameters in superfinishing

Analysis of the energy consumption when using different types of abrasive bars permits the derivation of a dependence of the cutting energy on the machining conditions.     

Assessing test results on the basis of acoustic images

General concepts of the construction of tomographic images generated by systems via coherent data processing are discussed. Characteristic features of the images are analyzed.     

Dependence of the recovery parameters of objects on the characteristics of the recovery process

For the main recovery parameters of an object, the formulas of their dependence on the recovery process characteristics have been proved. The established dependences are nonparametric and, thus, applicable to the arbitrary laws of the recovery process of objects.     

Automatic segmentation of diatom images for classification

A general framework for automatic segmentation of diatom images is presented. This segmentation is a critical first step in contour-based methods for automatic identification of diatoms by computerized image analysis. We review existing results, adapt popular segmentation methods to this difficult problem, and finally develop a method that substantially improves existing results. This method is based on the watershed segmentation from mathematical morphology, and belongs to the class of hybrid segmentation techniques. The novelty of the method is the use of connected operators for the computation and selection of markers, a critical ingredient in the watershed method to avoid over-segmentation. All methods considered were used to extract binary contours from a large database of diatom images, and the quality of the contours was evaluated both visually and based on identification performance.     

Mathematical classification of tight junction protein images

We present the rationale for the development of mathematical features used for classification of images stained for selected tight junction proteins. The project examined localization of zonula occludens‐1, claudin‐1 and F‐actin in a model epithelium, Madin–Darby canine kidney II cells. Cytochalasin D exposure was used to perturb junctional localization by actin cytoskeleton disruption. Mathematical features were extracted from images to reliably reveal characteristic information of the pattern of protein localization. Features, such as neighbourhood standard deviation, gradient of pixel intensity measurement and conditional probability, provided meaningful information to classify complex image sets. The newly developed mathematical features were used as input to train a neural network that provided a robust method of individual image classification. The ability for researchers to make determinations concerning image classification while minimizing human bias is an important advancement for the field of tight junction cellular biology.     

基于多尺度特征融合的遥感图像场景分类

为了解决遥感图像场景分类中因样本量小而分类精度不高的问题,提出了一种基于多尺度特征融合(MSFF)的分类方法。首先,对遥感图像进行尺度变换,得到同一遥感源图像的多个不同尺度图像。接着,将其分别输入深度卷积神经网络(DCNN)中进行卷积操作。然后,将各卷积层和全连接层提取出的不同尺度特征进行降维和编码/平均池化操作。最后,将各尺度特征进行编码融合并利用多核支持向量机(MKSVM)进行场景分类。在两个公开遥感图像数据集UCM Land-Use和NWPU-RESISC45中进行试验,分类精度最高分别达到98.91%和99.33%。本文方法能够利用不同尺度的图像特征,结合低、中、高层语义表示,使融合特征的可辨识性更高,同时使用多核支持向量机提高了深度网络学习的泛化能力,因此分类效果更好。     

运动模糊图像点扩展函数的参数鉴别

为了更加准确地鉴别出运动模糊图像的点扩展函数参数,提出了一种在倒谱域鉴别模糊参数的方法。该方法通过对运动模糊图像的倒谱图实施灰度变换,运用Canny边缘检测精确提取出倒谱,进而计算出运动模糊的尺度;对倒谱实施RADON变换确定运动模糊的方向。对130幅不同模糊程度的计算机仿真图像和相机实拍的图像鉴别结果表明:该方法鉴别PSF参数准确,且具有较强的鲁棒性。使用鉴别出的PSF参数,运用维纳滤波对运动模糊图像进行了复原,复原结果也证实了本方法鉴别PSF参数的有效性和准确性。     

Automated classification and visualization of fluorescent live cell microscopy images

Robotic, high‐throughput microscopy is a powerful tool for small molecule screening and classifying cell phenotype, proteomic and genomic data. An important hurdle in the field is the automated classification and visualization of results collected from a data set of tens of thousands of images. We present a method that approaches these problems from the perspective of flow cytometry with supporting open‐source code. Image analysis software was created that allowed high‐throughput microscopy data to be analysed in a similar manner as flow cytometry. Each cell on an image is considered an object and a series of gates similar to flow cytometry is used to classify and quantify the properties of cells including size and level of fluorescent intensity. This method is released with open‐source software and code that demonstrates the method's implementation. Accuracy of the software was determined by measuring the levels of apoptosis in a primary murine myoblast cell line after exposure to staurosporine and comparing these results to flow cytometry.     

Retrieving modulation parameters from HRTEM images of modulated structures

Quantitative high-resolution transmission electron microscopy (qHRTEM) is methodologically extended towards the assessment of occupationally and positionally modulated structures. For this purpose, iterative digital image matching has been combined with data processing within the Rietveld refinement code JANA2000. In this approach, the number of free parameters is kept low and rather complicated modulated structures become assessable by qHRTEM. The feasibility of the improved methodology is demonstrated for the 1D modulated structure of Ba(2)TiGe(2)O(8).     

Characterization of shapes for use in classification of starch grains images

As tradition Chinese herbal medicine becomes increasingly popular, there is an urgent need for efficient and accurate methods for the authentication of the Chinese Materia Medica (CMM) used in the herbal medicine. In this work, we present a denoising filter and introduce the use of chord length distribution (CLD) for the classification of starch grains in microscopic images of Chinese Materia Medica. Our simple denoising filter is adaptive to the background and is shown to be effective to remove noise, which appears in CMM microscopic starch grains images. The CLD is extracted by considering the frequency of the chord length in the binarized starch grains image, and we shall show that the CLD is an efficient and effective characterization of the starch grains. Experimental results on 240 starch grains images of 24 classes show that our method outperforms benchmark result using the current state-of-the-art method based on circular size distribution extracted by morphological operators at much higher computational cost.     

On the influence of some test parameters on the results of oscillating sliding tests

The friction and wear behaviour of materials is often characterised in laboratory tests using a simple ball-on-flat configuration. From this type of test can be derived information useful in guiding the development of tribomaterials and in helping select candidate materials for specific applications. A large variety of tribotesting methods exists, and indeed several are not yet standardised. One of these methods is the oscillating sliding test, where a ball moves in relation to a disc, usually with small strokes. This method is almost non-destructive and can be applied to very small specimens. One of the most important parameters in laboratory tests is the humidity of the surrounding air. Experimental results on the friction and wear characteristics of different ceramics tested against different ball materials at room temperature in oscillating sliding contact are presented here and discussed, taking into account the effects of the test duration, relative humidity, and counterbody material.     

Dependence of the measured size of the objects on the parameters of the transmitted light source in video measurement microscopy

Parameter adjustment of the transmitted light source yields a good‐quality image for video measurement microscopy. However, a disadvantage is that the measured size of the objects changes simultaneously while the parameters of the transmitted light source are adjusted, which directly affects the measurement accuracy adversely. Furthermore, the variation of the objects’ measured size leads to the magnification variation as well. In order to analyse how the measured size of the objects varies with the parameters, we apply a photometric method and an operator algebra method to derive a unified mathematical model that correlates the parameters of the transmitted light source with the measured size of the objects. Theoretical results show that factors including the illumination intensity, the diameter of the aperture stop and the field stop and the object thickness are important to the measured size of the objects. The simulation results have been verified thoroughly using a wide variety of internal and external diameter measurement experiments. The proposed method has proved to be suitable to determine how these parameters affect measured size of the objects.     

Mapping and fuzzy classification of macromolecular images using self-organizing neural networks

In this work the effectiveness of the fuzzy kohonen clustering network (FKCN) in the unsupervised classification of electron microscopic images of biological macromolecules is studied. The algorithm combines Kohonen's self-organizing feature maps (SOFM) and Fuzzy c-means (FCM) in order to obtain a powerful clustering technique with the best properties inherited from both. Exploratory data analysis using SOFM is also presented as a step previous to final clustering. Two different data sets obtained from the G40P helicase from B. Subtilis bacteriophage SPP1 have been used for testing the proposed method, one composed of 2458 rotational power spectra of individual images and the other composed by 338 images from the same macromolecule. Results of FKCN are compared with self-organizing feature maps (SOFM) and manual classification. Experimental results prove that this new technique is suitable for working with large, high-dimensional and noisy data sets and, thus, it is proposed to be used as a classification tool in electron microscopy.     

MRT letter: segmentation and texture-based classification of breast mammogram images

Breast cancer is the most common cancer diagnosed among women. In this article, support vector machine is used to classify digital mammogram images into malignant and benign. Wiener filter is used to handle the possible quantum noise, which is more likely to occur in mammograms. Stack-based connected component method is proposed for background removal, and the image is enhanced using retinax method. Seeded region growing algorithm is used to remove the pectoral muscle part of the mammogram. We have extracted 13 different multidomains' features for classification. Results show the superiority of the proposed algorithm in terms of sensitivity, specificity, and accuracy. We have used MIAS database of mammography for experimentation.     

Estimation of optimal parameters of the multiplicative algorithm of wavelet filtering of images

In most widely used wavelet filtering algorithms, the decomposition coefficients are processed with the use of threshold functions, which makes it possible to account for the “energy” feature of each decomposition coefficient. To some extent, this disadvantage is removed in a class of multiplicative algorithms, which account for the energy of decomposition coefficients located in a given proximity from a processed decomposition coefficient. However, the effective error minimization in wavelet filtering of images requires that a parameter, the choice of the optimal value of which remains to be an unsolved problem, is introduced into these processing algorithms. Therefore, the problem solved in this paper is the estimation of the optimal value of this parameter, which minimizes the root-mean-square error of the filtering. The performed studies showed the effectiveness of the proposed estimation algorithm and the possibility of its use in practice.     

The effect of major parameters on simulation results of gas pipelines

Predictions of the gas temperature and pressure profiles are vital to the design and operation of gas transmission lines. Available analytical methods for the calculation of these profiles are evaluated and a numerical framework for the rigorous calculation has been developed. The predictions from both the analytical and numerical procedure have been compared to field data from the Iranian Gas Trunk-lines (IGAT). These comparisons showed that all the available methods were tuned using data obtained from small to medium diameter pipes extrapolated poorly to large diameter pipelines. In order to improve the predictions for large diameter pipelines, the effect of model parameters such as soil thermal conductivity, pipe relative roughness and velocity profile correction factor has been evaluated. The results show that temperature and pressure profiles at high Reynolds number are sensitive to the Fanning friction factor; however, thermal conductivity and velocity distribution correction factor have almost no effect on the temperature and pressure profiles provided these parameters were set at an average acceptable industry value. Since the pressure profile for large diameter pipes was most sensitive to the Fanning friction factor a parameter optimization method was used to fine-tune the Fanning friction factor as a function of Reynolds number at an average accepted industry relative pipe roughness.     

Analysis of the efficiency of classification of hyperspectral satellite images of natural and man-made areas

The efficiency of a number of the classical methods of supervised classification of hyperspectral data is estimated by an example of discriminating the types of the underlying surface in natural and man-made areas. The minimum distance, support vector machine, Mahalanobis, and maximum likelihood methods are considered. Particular attention is paid to studying the dependence of the data classification accuracy on the number of spectral features and the way of choosing them in the above-mentioned methods. Experimental results obtained by processing real hyperspectral images of landscapes of various types are reported.