object_tracking_based_on_kalman

Image Inpainting for object removal project report

梯度矢量扩散控制实现边缘保持的彩色图像去噪(Gradient vector diffusion denoising realize control color image edge preserving )

功能：去模糊/去马赛克 A joint demosaicking-zooming scheme for single chip digital color cameras(2007)论文以及源码(Function: to blur/demosaicing A joint demosaicking-zooming scheme for single chip digital color cameras (2007) paper and source code)

图像的特征用到了Dense Sift，通过Bag of Words词袋模型进行描述，当然一般来说是用训练集的来构建词典，因为我们还没有测试集呢。虽然测试集是你拿来测试的，但是实际应用中谁知道测试的图片是啥，所以构建BoW词典我这里也只用训练集。 其实BoW的思想很简单，虽然很多人也问过我，但是只要理解了如何构建词典以及如何将图像映射到词典维上去就行了，面试中也经常问到我这个问题，不知道你们都怎么用生动形象的语言来描述这个问题？ 用BoW描述完图像之后，指的是将训练集以及测试集的图像都用BoW模型描述了，就可以用SVM训练分类模型进行分类了。 在这里除了用SVM的RBF核，还自己定义了一种核： histogram intersection kernel，直方图正交核。因为很多论文说这个核好，并且实验结果很显然。能从理论上证明一下么？通过自定义核也可以了解怎么使用自定义核来用SVM进行分类。(Image features used in a Dense Sift, by the Bag of Words bag model to describe the word, of course, the training set is generally used to build the dictionary, because we do not test set. Although the test set is used as the test you, but who knows the practical application of the test image is valid, so I am here to build BoW dictionary only the training set. In fact, BoW idea is very simple, although many people have asked me, but as long as you understand how to build a dictionary and how to image map to the dictionary D up on the line, and interviews are often asked me this question, do not know you all how to use vivid language to describe this problem? After complete description of the image with BoW, refers to the training set and test set of images are described with the BoW model, the training of SVM classification model can be classified. Apart from having to use the RBF kernel SVM, but also their own definition of a nuclear: histogram intersection kernel, histogram )

基于深度图的图像修复，有完整的代码和实验图像。(Image restoration based on the depth chart, there is a complete code and experimental images.)

广度优先搜索和深度优先搜索在网络拓扑图上的实现。广度优先搜索是从某一节点开始，搜索与其线连接的所有节点，按照广度方向像外扩展，直到不重复遍历所有节点；深度优先搜索是从某一节点开始，沿着其搜索到的第一个节点不断深入下去，当无法再深入的时候，回溯节点，然后再在回溯中的某一节点开始沿另一个方向深度搜索，直到不重复的遍历所有节点。 (Breadth-first search and depth-first search in the network topology is realized. Breadth-first search is started from a node, searching all the nodes connected to its line, in accordance with the breadth direction as extracapsular extension, until no repeat traverse all nodes depth-first search is started from a node along its search to the first nodes deepening it, when it can not go any further, backtracking node, and then back again in the beginning of a node depth search in the other direction until the non-repetition of the traverse all nodes.)

DCT水印，简单实用，基于8*8分块的DCT域水印嵌入算法水印图像为64*64(DCT watermark, simple and practical, based on the 8* 8 sub-block DCT domain watermark image watermark embedding algorithm is 64* 64)

基于二维直方图的最大模糊熵阈值图像分割，相比于一维最大模糊熵，分割效果更好。隶属度函数采用S函数(Based on two-dimensional histogram maximum fuzzy entropy threshold image segmentation, compared to one-dimensional maximum fuzzy entropy segmentation better)

基于K均值聚类的图像分割，灰度图像分割案例，真彩图像分割案例(K-means clustering-based image segmentation, image segmentation case, the true color image segmentation case)

基于多特征描述和DPF区域匹配的图像检索(Based on multi-feature description and matching DPF Regional Image Retrieval)