本文共 7689 字，大约阅读时间需要 25 分钟。

发现这个博客里都是宝贝啊，所以，都转载过来 原文在这里：

一、特征提取Feature Extraction：

   SIFT [1] [][] []    PCA-SIFT [2] []    Affine-SIFT [3] []    SURF [4] [] []    Affine Covariant Features [5] []    MSER [6] [] []    Geometric Blur [7] []    Local Self-Similarity Descriptor [8] []    Global and Efficient Self-Similarity [9] []    Histogram of Oriented Graidents [10] [] []    GIST [11] []    Shape Context [12] []    Color Descriptor [13] []    Pyramids of Histograms of Oriented Gradients []    Space-Time Interest Points (STIP) [14][] []    Boundary Preserving Dense Local Regions [15][]    Weighted Histogram[]    Histogram-based Interest Points Detectors[][]    An OpenCV - C++ implementation of Local Self Similarity Descriptors []    Fast Sparse Representation with Prototypes[]    Corner Detection []    AGAST Corner Detector: faster than FAST and even FAST-ER[] 二、图像分割Image Segmentation：      Normalized Cut [1] []      Gerg Mori’ Superpixel code [2] []      Efficient Graph-based Image Segmentation [3] [] []      Mean-Shift Image Segmentation [4] [] []      OWT-UCM Hierarchical Segmentation [5] []      Turbepixels [6] [] [] []      Quick-Shift [7] []      SLIC Superpixels [8] []      Segmentation by Minimum Code Length [9] []      Biased Normalized Cut [10] []      Segmentation Tree [11-12] []      Entropy Rate Superpixel Segmentation [13] []      Fast Approximate Energy Minimization via Graph Cuts[][]      Efficient Planar Graph Cuts with Applications in Computer Vision[][]      Isoperimetric Graph Partitioning for Image Segmentation[][]      Random Walks for Image Segmentation[][]      Blossom V: A new implementation of a minimum cost perfect matching algorithm[]      An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Computer Vision[][]      Geodesic Star Convexity for Interactive Image Segmentation[]      Contour Detection and Image Segmentation Resources[][]      Biased Normalized Cuts[]      Max-flow/min-cut[]      Chan-Vese Segmentation using Level Set[]      A Toolbox of Level Set Methods[]      Re-initialization Free Level Set Evolution via Reaction Diffusion[]      Improved C-V active contour model[][]      A Variational Multiphase Level Set Approach to Simultaneous Segmentation and Bias Correction[][]     Level Set Method Research by Chunming Li[] 三、目标检测Object Detection：      A simple object detector with boosting []      INRIA Object Detection and Localization Toolkit [1] []      Discriminatively Trained Deformable Part Models [2] []      Cascade Object Detection with Deformable Part Models [3] []      Poselet [4] []      Implicit Shape Model [5] []      Viola and Jones’s Face Detection [6] []      Bayesian Modelling of Dyanmic Scenes for Object Detection[][]      Hand detection using multiple proposals[]      Color Constancy, Intrinsic Images, and Shape Estimation[][]      Discriminatively trained deformable part models[]      Gradient Response Maps for Real-Time Detection of Texture-Less Objects: LineMOD []      Image Processing On Line[]      Robust Optical Flow Estimation[]      Where's Waldo: Matching People in Images of Crowds[] 四、显著性检测Saliency Detection：      Itti, Koch, and Niebur’ saliency detection [1] []      Frequency-tuned salient region detection [2] []      Saliency detection using maximum symmetric surround [3] []      Attention via Information Maximization [4] []      Context-aware saliency detection [5] []      Graph-based visual saliency [6] []      Saliency detection: A spectral residual approach. [7] []      Segmenting salient objects from images and videos. [8] []      Saliency Using Natural statistics. [9] []      Discriminant Saliency for Visual Recognition from Cluttered Scenes. [10] []      Learning to Predict Where Humans Look [11] []      Global Contrast based Salient Region Detection [12] []      Bayesian Saliency via Low and Mid Level Cues[]      Top-Down Visual Saliency via Joint CRF and Dictionary Learning[][] 五、图像分类、聚类Image Classification, Clustering      Pyramid Match [1] []      Spatial Pyramid Matching [2] []      Locality-constrained Linear Coding [3] [] []      Sparse Coding [4] [] []      Texture Classification [5] []      Multiple Kernels for Image Classification [6] []      Feature Combination [7] []      SuperParsing []      Large Scale Correlation Clustering Optimization[]      Detecting and Sketching the Common[]      Self-Tuning Spectral Clustering[][]      User Assisted Separation of Reflections from a Single Image Using a Sparsity Prior[][]      Filters for Texture Classification[]      Multiple Kernel Learning for Image Classification[]     SLIC Superpixels[] 六、抠图Image Matting      A Closed Form Solution to Natural Image Matting []      Spectral Matting []      Learning-based Matting [] 七、目标跟踪Object Tracking：      A Forest of Sensors - Tracking Adaptive Background Mixture Models []      Object Tracking via Partial Least Squares Analysis[][]      Robust Object Tracking with Online Multiple Instance Learning[][]      Online Visual Tracking with Histograms and Articulating Blocks[]      Incremental Learning for Robust Visual Tracking[]      Real-time Compressive Tracking[]      Robust Object Tracking via Sparsity-based Collaborative Model[]      Visual Tracking via Adaptive Structural Local Sparse Appearance Model[]      Online Discriminative Object Tracking with Local Sparse Representation[][]      Superpixel Tracking[]      Learning Hierarchical Image Representation with Sparsity, Saliency and Locality[][]      Online Multiple Support Instance Tracking [][]      Visual Tracking with Online Multiple Instance Learning[]      Object detection and recognition[]      Compressive Sensing Resources[]      Robust Real-Time Visual Tracking using Pixel-Wise Posteriors[]      Tracking-Learning-Detection[][]      the HandVu：vision-based hand gesture interface[] 八、Kinect：      Kinect toolbox[]      OpenNI[]      zouxy09 CSDN Blog[] 九、3D相关：      3D Reconstruction of a Moving Object[] []      Shape From Shading Using Linear Approximation[]      Combining Shape from Shading and Stereo Depth Maps[][]      Shape from Shading: A Survey[][]      A Spatio-Temporal Descriptor based on 3D Gradients (HOG3D)[][]      Multi-camera Scene Reconstruction via Graph Cuts[][]      A Fast Marching Formulation of Perspective Shape from Shading under Frontal Illumination[][]      Reconstruction:3D Shape, Illumination, Shading, Reflectance, Texture[]      Monocular Tracking of 3D Human Motion with a Coordinated Mixture of Factor Analyzers[]      Learning 3-D Scene Structure from a Single Still Image[] 十、机器学习算法：      Matlab class for computing Approximate Nearest Nieghbor (ANN) [ providing interface to]      Random Sampling[]      Probabilistic Latent Semantic Analysis (pLSA)[]      FASTANN and FASTCLUSTER for approximate k-means (AKM)[]      Fast Intersection / Additive Kernel SVMs[]      SVM[]      Ensemble learning[]      Deep Learning[]      Deep Learning Methods for Vision[]      Neural Network for Recognition of Handwritten Digits[]      Training a deep autoencoder or a classifier on MNIST digits[]     THE MNIST DATABASE of handwritten digits[]     Ersatz：deep neural networks in the cloud[]     Deep Learning []     sparseLM : Sparse Levenberg-Marquardt nonlinear least squares in C/C++[]     Weka 3: Data Mining Software in Java[]     Invited talk "A Tutorial on Deep Learning" by Dr. Kai Yu (余凯)[]     CNN - Convolutional neural network class[]     Yann LeCun's Publications[]     LeNet-5, convolutional neural networks[]     Training a deep autoencoder or a classifier on MNIST digits[]     Deep Learning 大牛Geoffrey E. Hinton's HomePage[] 十一、目标、行为识别Object, Action Recognition：      Action Recognition by Dense Trajectories[][]      Action Recognition Using a Distributed Representation of Pose and Appearance[]      Recognition Using Regions[][]      2D Articulated Human Pose Estimation[]      Fast Human Pose Estimation Using Appearance and Motion via Multi-Dimensional Boosting Regression[][]      Estimating Human Pose from Occluded Images[][]      Quasi-dense wide baseline matching[]      ChaLearn Gesture Challenge: Principal motion: PCA-based reconstruction of motion histograms[] 十二、图像处理：      Distance Transforms of Sampled Functions[]     The Computer Vision Homepage[] 十三、一些实用工具：      EGT: a Toolbox for Multiple View Geometry and Visual Servoing[] []      a development kit of matlab mex functions for OpenCV library[]      Fast Artificial Neural Network Library[] 

转载地址：https://jianzhuwang.blog.csdn.net/article/details/51548590 如侵犯您的版权，请留言回复原文章的地址，我们会给您删除此文章，给您带来不便请您谅解！