image_segmentation马尔科夫随机场

图像拼接，利用互相关函数自动寻找匹配点。(Image mosaic, using cross-correlation function automatically find matching points.)

箔条干扰的特性与雷达抗箔条技术研究，对雷达制导导引头的干扰技术进行系统研究(Characteristics of the anti-radar chaff and chaff research technology, the interference radar guidance seeker system research)

最大熵双阈值分割算法，基于遗传算法优化的快速最大熵双阈值分割算法。(Maximum Entropy Double Threshold Segmentation and Fast Maximum Entropy Double Threshold Segmentation Based on Genetic Algorithms.)

说明：  使用matlab 的GUI界面，添加图像锐化增强函数，进行交互式操作(Image sharpening enhancement)

对低质量图像分割和计数，以大米照片为例。(Of low-quality image segmentation and counting to rice as an example photo.)

利用形态学分水岭算法对图像进行分割，对细胞图像能达到较好的分割效果(Using morphological watershed algorithm for image segmentation, the cell image segmentation can achieve better results)

说明：  图像处理小工具箱，包括中值滤波，高斯滤波，均值滤波，canny边缘提取等小程序(Image processing toolbox, including median filter, gaussian filter, mean filter, canny edge extraction and other small procedures)

说明：  PWLS算法主要用于CT重建前的投影数据处理，能够很好的用于CT迭代算法中，对图像进行去噪(PWLS algorithm is mainly used for projection data processing before CT reconstruction. It can be well used in CT iterative algorithm to denoise images.)

结合维纳滤波的小波降噪方法，滤波效果很好(Combination of Wiener filtering of wavelet noise reduction method, filter works well)

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 )