phase-history-domain

彩色图像边缘检测（canny 算子，高斯窗口可调）(image edge detection [canny])

运用harr特征+SRC（稀疏表示）分类实现的一种车辆检测方法，文件中提供了训练和测试车辆图片。由于时间原因，所用haar特征没有优化，维度过高，导致滑窗框图过慢，本代码只输出效果统计数据，以供大家参考学习稀疏表示在车辆检测中的应用。(Using harr feature+SRC (sparse representation) classification to achieve a vehicle detection method, the paper provides a training and test vehicle picture. Due to time reasons, the use of haar feature is not optimized, high dimension, resulting in sliding sash figure is too slow, the effect of the code only output statistics for your reference learning sparse representation in the vehicle detection.)

通过邻域搜索法对一个相机拍摄的序列图像中圆形非编码标志点进行匹配(Neighborhood search method by camera on a circular non-coding sequence of images to match landmarks )

利用图像的不变矩以及模式识别的内容，构造三维飞机图像的矩特征，然后再利用D-S证据理论的改进方法 吸收法对图像进行融合 对飞机的型号进行匹配(Moment invariant of image and pattern recognition of the content, structure features three-dimensional plane images of the moment, and then use the improved DS evidence theory method of absorption of the fusion images to match the type of aircraft)

说明：  图像修复算法 使用criminisi算法对破损图像进行修复。(The image restoration algorithm uses criminisi algorithm to repair the damaged image.)

去模糊的算法，有MIT做的，参考文献是siggraph06的文章，效果很好(Go fuzzy algorithms, MIT has to do the references are siggraph06 the article, very good)

该文件夹包括代码及其对应的论文。其作用在于模拟人类视觉系统的生理特性--视觉注意机制，按照人眼观察外界的方式，检测视觉显著性物体和区域，并阐述了显著性区域的显著性密度和尺度之间的关系，可应用于生物视觉模拟、视觉目标检测、视觉目标跟踪、视觉智能监控，以及视觉生理学和视觉心理学等的研究中。(This document contains codes and the corresponding paper. The aim is to simulate a physiological characteristic of human visual system called visual attention mechanism. The code is used to detect salient objects or regions following the way human eye observes the world. The relation between density and scale of salient object/region is described. It has found widespread use in numerous applications such as biological vision simulation, visual object detection, visual object tracking, visual intelligent surveillance, visual physiological, and visual psychology.)

实现论文 Active Contours without Edges 中提出的CV活动轮廓模型，用于分割图像。(To achieve paper Active Contours without Edges, in the CV active contour model for image segmentation.)

给出了灰度图像（256*256大小）的三层高斯和拉普拉斯金字塔分解的程序和实现方法。内容包括：1.matlab源码，亲身实践，因为论文需要，自己专研的。完全可用。2.国外最先最权威的关于分解原理介绍的文章。以上两个内容中都有本人的悉心注释和思路总结，内容详尽。3.图示结果(code and principle of laplacian pyramid decomposition of a gray scale image are provided in the article.Contents are given in detail including the notes and usage. )

说明：  获取图像的LBP特征：对图像的原始LBP模式、等价LBP模式、旋转不变LBP模式，以及等价旋转不变LBP模式的LBP特征进行提取以及显示(Obtaining LBP features of images: extracting and displaying the original LBP pattern, equivalent LBP pattern, rotation invariant LBP pattern and equivalent rotation invariant LBP pattern of images)