计算机视觉相关领域论文和源代码大集合

这篇博客汇总了计算机视觉领域的关键技术和资源,包括特征提取、图像分割、目标检测、显著性检测、图像分类和聚类、抠图、以及目标跟踪等方面的方法、论文和源代码。涵盖SIFT、SURF、HOG等经典特征提取算法,以及Normalized Cut、Mean-Shift等图像分割技术,还有Viola-Jones等人脸检测方法和各种目标检测模型。此外,还列举了大量用于图像分类、聚类、显著性检测和跟踪的工具和代码库。

摘要生成于 C知道 ,由 DeepSeek-R1 满血版支持, 前往体验 >


计算机视觉、机器学习相关领域论文和源代码大集合

一、特征提取Feature Extraction:

·         SIFT [1] [Demo program][SIFT Library] [VLFeat]

·         PCA-SIFT [2] [Project]

·         Affine-SIFT [3] [Project]

·         SURF [4] [OpenSURF] [Matlab Wrapper]

·         Affine Covariant Features [5] [Oxford project]

·         MSER [6] [Oxford project] [VLFeat]

·         Geometric Blur [7] [Code]

·         Local Self-Similarity Descriptor [8] [Oxford implementation]

·         Global and Efficient Self-Similarity [9] [Code]

·         Histogram of Oriented Graidents [10] [INRIA Object Localization Toolkit] [OLT toolkit for Windows]

·         GIST [11] [Project]

·         Shape Context [12] [Project]

·         Color Descriptor [13] [Project]

·         Pyramids of Histograms of Oriented Gradients [Code]

·         Space-Time Interest Points (STIP) [14][Project] [Code]

·         Boundary Preserving Dense Local Regions [15][Project]

·         Weighted Histogram[Code]

·         Histogram-based Interest Points Detectors[Paper][Code]

·         An OpenCV - C++ implementation of Local Self Similarity Descriptors [Project]

·         Fast Sparse Representation with Prototypes[Project]

·         Corner Detection [Project]

·         AGAST Corner Detector: faster than FAST and even FAST-ER[Project]

·         Real-time Facial Feature Detection using Conditional Regression Forests[Project]

·         Global and Efficient Self-Similarity for Object Classification and Detection[code]

·         WαSH: Weighted α-Shapes for Local Feature Detection[Project]

·         HOG[Project]

·         Online Selection of Discriminative Tracking Features[Project]

                        

二、图像分割Image Segmentation:

·           Normalized Cut [1] [Matlab code]

·           Gerg Mori’ Superpixel code [2] [Matlab code]

·           Efficient Graph-based Image Segmentation [3] [C++ code] [Matlab wrapper]

·           Mean-Shift Image Segmentation [4] [EDISON C++ code] [Matlab wrapper]

·           OWT-UCM Hierarchical Segmentation [5] [Resources]

·           Turbepixels [6] [Matlab code 32bit] [Matlab code 64bit] [Updated code]

·           Quick-Shift [7] [VLFeat]

·           SLIC Superpixels [8] [Project]

·           Segmentation by Minimum Code Length [9] [Project]

·           Biased Normalized Cut [10] [Project]

·           Segmentation Tree [11-12] [Project]

·           Entropy Rate Superpixel Segmentation [13] [Code]

·           Fast Approximate Energy Minimization via Graph Cuts[Paper][Code]

·           Efficient Planar Graph Cuts with Applications in Computer Vision[Paper][Code]

·           Isoperimetric Graph Partitioning for Image Segmentation[Paper][Code]

·           Random Walks for Image Segmentation[Paper][Code]

·           Blossom V: A new implementation of a minimum cost perfect matching algorithm[Code]

·           An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Computer Vision[Paper][Code]

·           Geodesic Star Convexity for Interactive Image Segmentation[Project]

·           Contour Detection and Image Segmentation Resources[Project][Code]

·           Biased Normalized Cuts[Project]

·           Max-flow/min-cut[Project]

·           Chan-Vese Segmentation using Level Set[Project]

·           A Toolbox of Level Set Methods[Project]

·           Re-initialization Free Level Set Evolution via Reaction Diffusion[Project]

·           Improved C-V active contour model[Paper][Code]

·           A Variational Multiphase Level Set Approach to Simultaneous Segmentation and Bias Correction[Paper][Code]

·          Level Set Method Research by Chunming Li[Project]

·          ClassCut for Unsupervised Class Segmentation[code]

·         SEEDS: Superpixels Extracted via Energy-Driven Sampling[Project][

机器学习涵盖了许多不同的算法,用于解决各种类型的问题。以下是一些常见的机器学习算法: 监督学习算法:线性回归(Linear Regression)逻辑回归(Logistic Regression)决策树(Decision Trees)随机森林(Random Forests)支持向量机(Support Vector Machines)朴素贝叶斯(Naive Bayes)K近邻算法(K-Nearest Neighbors)深度学习(Deep Learning)算法,如神经网络(Neural Networks) 无监督学习算法:K均值聚类(K-Means Clustering)层次聚类(Hierarchical Clustering)高斯混合模型(Gaussian Mixture Models)主成分分析(Principal Component Analysis,PCA)关联规则学习(Association Rule Learning) 这只是机器学习领域中的一小部分算法,还有许多其他的算法技术。根据问题的性质数据的特点,选择适合的算法是非常重要的。不同的算法有不同的假设适用场景,因此在学习应用机器学习算法时,需要综合考虑问题的需求数据的特点。机器学习(Machine learning)是人工智能的子集,是实现人工智能的一种途径,但并不是唯一的途径。它是一门专门研究计算机怎样模拟或实现人类的学习行为,以获取新的知识或技能,重新组织已有的知识结构使之不断改善自身的性能的学科。概在上世纪80年代开始蓬勃发展,诞生了一批数学统计相关的机器学习模型。 深度学习(Deep learning)是机器学习的子集,灵感来自人脑,由人工神经网络(ANN)组成,它模仿人脑中存在的相似结构。在深度学习中,学习是通过相互关联的「神经元」的一个深层的、多层的「网络」来进行的。「深度」一词通常指的是神经网络中隐藏层的数量。概在2012年以后爆炸式增长,广泛应用在很多的场景中。机器学习研究的是计算机怎样模拟人类的学习行为,以获取新的知识或技能,并重新组织已有的知识结构,使之不断改善自身。 从实践的意义上来说,机器学习是在数据的支撑下,通过各种算法让机器对数据进行深层次的统计分析以进行「自学」,使得人工智能系统获得了归纳推理决策能力。
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值