图像分割技术在金相分析中的应用

介绍了常用的图像分割方法及其优缺点和金相图像分析中的图像分割方法。针对金相图像分割中存在的问题，提出了两步分割的图像分割方法。这种方法是先用阈值分割法把目标从背景中分割开来，然后采用数学形态学、打孔、找凹点和连分割线的方法进行粘连分割。与已有的金相图像分割方法相比，这种方法具有较强的强健性、自适应性和非监督性。     

Image denoising and quality measurements by using filtering and wavelet based techniques

An image is often corrupted by noise in its acquisition and transmission by various kinds of noises. Image denoising using thresholding methods find appropriate values (threshold) which separates noise values to actual image values without affecting the significant features of the image. Wavelet transform represents image energy in compact form and representation helps in determining threshold between noisy features and important image feature. In this paper we have worked with denoising of salt–pepper and Gaussian noise. The work is organized in four steps as follows: (1) image is denoised by filtering method, (2) image is denoised by wavelet based techniques using thresholding, (3) hard thresholding and filtering method applied simultaneously on noisy image, (4) results of PSNR (peak signal to noise ratio) and MSE (mean square error) are calculated by comparing all cases.     

A novel statistical image thresholding method

Classic statistical thresholding methods based on maximizing between-class variance and minimizing class variance fail to achieve satisfactory results when segmenting a kind of image, where variance discrepancy between the object and background classes is large. The reason is that they take only class variance sum of some form as criterions for threshold selection, but neglect discrepancy of the variances. In this paper, a novel criterion combining the above two factors is proposed to eliminate the described limitation for classic statistical approaches and improve segmentation performance. The proposed method determines the optimal threshold by minimizing the criterion. The method was compared with several classic thresholding methods on a variety of images including some NDT images and laser cladding images, and the experimental results show the effectiveness of the algorithm.     

A visual consistent adaptive image thresholding method

Image thresholding method is an important preprocessing step in many applications of image processing. In this paper, we present a visual consistent adaptive image thresholding method, by combining the thresholding process with the characteristics of human visual system. In the proposed algorithm, we first roughly classify the image pixels into two categories. Then two sub-images are constructed to retain the essential information of the original image. For each sub-image, a corresponding global optimal threshold is calculated by optimizing an objective function. Finally, a visual consistent binary image is produced by combining the results from the previous steps with the information of pixels in each category. The proposed method has been tested on some different images, and the results are also compared with a number of known algorithms in the literature. The experimental results demonstrate that the overall visual qualities of our method are more suitable for human visual perception.     

基于小波去噪的增强多尺度多传感器数据融合

建立了基于小波去噪的增强多尺度自回归模型。增强多尺度状态可以将直接基于小波变换的多尺度自回归模型的网状结构简化为二叉树结构。基于小波去噪的多尺度模型具有非参数化特性，该模型适合于系统特性不知道的分布式多分辨率多传感器进行建模。最后，应用该算法于高精度划线切割机器人系统中多传感器的建模，实现了型钢划线切割过程中型钢边缘的检测。实验结果和数值仿真表明，多分辨率多传感器的数据融合可以消除噪声的干扰，提高检测系统的测量精度。     

A novel histogram transformation to improve the performance of thresholding methods in edge detection

The gradient image is used to detect edge points, and the gradient histogram is a typical case of a unimodal histogram. It is well-documented that bi-modal thresholding methods (such as the Otsu method) detect edges poorly. Therefore, specific unimodal thresholding methods are used to detect edge points. However, unimodal thresholding methods (such as the Rosin method) sometimes obtain very noisy results. In this paper, we propose a histogram transformation to improve the performance of some thresholding methods. Using the Berkeley Segmentation Dataset, we present quantitative performance results in an edge detection task to show that our transformation improves the performance of the Otsu and Rosin methods. Our histogram transformation can be used by any histogram thresholding method, but the performance of the method, using the transformed histogram, will depend of the criterion used by this method.     

Solving the process of hysteresis without determining the optimal thresholds

Hysteresis is an important edge detection technique, but the unsupervised determination of hysteresis thresholds is a difficult problem. Thus, hysteresis has limited practical applicability. Unimodal thresholding techniques are another edge detection method. They are useful, because the histogram of a feature image (usually the feature image is an approximation of the gradient image) is unimodal, and there are many unsupervised methods to solve this problem. But such techniques do not use spatial information to detect edge points, so their performance is worse than that of the hysteresis.In this paper, we show how to formulate the hysteresis process as a unimodal thresholding problem without determining the optimal hysteresis thresholds. Using similar steps of the Canny edge detector to obtain an approximation of the gradient image we compare the performance of our method against that of a method that determines the best parameters of an edge detector and show that our method performs relatively well. Additionally, our method can adjust its sensitivity by using different unimodal thresholding techniques.     

Internal Sigmoid Dynamics in Feedforward Neural Networks

Departing from the customary view of the sigmoid thresholding function as a smooth transition non-linearity introduced into multi-layer perceptron (MLP) networks to a continuously differentiable albeit slow gradient descent toward an optimal solution minimizing some error norm, here a different, more fundamental viewpoint is proposed: the intrinsic dynamics throughout the network become those of the quadratic map of theory. This new viewpoint enables valuable insights into understanding the initial, intermediate and final dynamics of supervised learning of algorithms such as the widely used backpropagation scheme. More specifically, although approximately: the weight changes in the aforementioned three learning stages correspond to the three regimes fluctuation, periodicity and fixed points of the quadratic map. The purpose of this is to examine this basic idea, to support it theoretically, by example and through literature, and to suggest the next steps in its further investigation.     

原位分子杂交图象中银粒的分割方法研究

图象分割的图象处理的一个基本技术。运用一种改进的快速Ｏｔｓｕ阈值分割法,并结合其它处理方法原对原位分子杂效力图象中的银粒进行分割 。