Recogniztion_2004_05_18

随着生产和工艺的进步，人们对产品的质量要求越来越高，基于机器视觉的在线 检测系统成为一种重要的质量控制手段。本文对应用于宽幅面、高精度的基于分布式 机器视觉的产品表面缺陷在线检测理论与算法进行了研究，并在此基础上以印刷品和 浮法玻璃的缺陷检测为例，完成了模式产品和非模式产品的缺陷在线检测系统。(With the progress of production and technology, people are increasingly demanding high quality products, based on machine vision for online 检测 system into one kind of Zhong Yao quality Kongzhishouduan. This article applies to wide format, high-precision machine vision products based on distributed-line surface defect detection theory and algorithms are studied, and on this basis, and float glass in print defect detection, for example, completed a model of products and non-model product line defect detection system.)

基于多帧图像插值（Interpolation）技术的方法是SR恢复技术当中最直观 的方法。这类方法首先估计各帧图像之间的相对运动信息，获得HR图像在非均 匀间距采样点上的象素值，接着通过非均匀插值得到HR栅格上的象素值，最后 采用图像恢复技术来去除模糊和降低噪声（运动估计!非均匀插值!去模糊和 噪声）。(In this paper, we propose a novel method for solv- ing single-image super-resolution problems. Given a low-resolution image as input, we recover its high- resolution counterpart using a set of training exam- ples. While this formulation resembles other learning- based methods for super-resolution, our method has been inspired by recent manifold learning methods, par- ticularly locally linear embedding (LLE). Speci?cally, small image patches in the low- and high-resolution images form manifolds with similar local geometry in two distinct feature spaces. As in LLE, local geometry is characterized by how a feature vector correspond- ing to a patch can be reconstructed by its neighbors in the feature space. Besides using the training image pairs to estimate the high-resolution embedding, we also enforce local compatibility and smoothness con- straints between patches in the target high-resolution image through overlapping. Experiments show that our method is very ?exible )

说明：  提出了一种基于数学形态学的多尺度熵权边缘检测方法。信息熵为图像的内在特性，由它来决定不同结构元 素所提取的边缘在最终合成边缘中所占的比重，是自适应的和客观的(A multi-scale based on mathematical morphology edge detection method of entropy. Information entropy inherent characteristics of the image, from which different structural elements to determine the edge of the extracted edge in the final synthesis of proportion, is adaptive and objective)

未来线路预测,分析误差,粒子图像分割及匹配均为自行编制的子例程，能量谱分析计算。( Future line prediction, error analysis, Particle image segmentation and matching subroutines themselves are prepared, Energy spectrum analysis and calculation.)

QT 使用向导对话框,使用QWizard类实现多窗口切换(QT uses the Wizard dialog box)

基于VisualC_和DCMTK的医学DICOM图像显示与调窗,同时在MFC 下完成鼠标拖动进行窗宽/窗位的调节(Medical image of DICOM VisualC_ and DCMTK display and window based on, at the same time in MFC complete the mouse to drag the window width/window regulator )

图像拼接：实现两幅具有重叠区域的图像的拼接；使用MFC框架，内有程序使用文档(image mosaicing)

目标跟踪matlab源代码，通过当前帧预测区域的信息同背景图像的信息的内容相差，可以很好的实现运动目标的跟踪。(Target tracking matlab source code, through the regional information predict the current frame image with the background information on the contents of the difference, you can achieve a good tracking of moving objects.)

说明：  克里金算法2.0版本，对二维插值有详细的工具箱(kriging algorithm V2.0 for matlab )

MATLAB目标跟踪仿真小程序,对一定格式的AVI视频进行处理，提取出黑色背景下的人体轮廓及行动方向(MATLAB simulation of target tracking applet, for some form of AVI video processing, to extract the black outline and context of human action)