Computer Vision Open Source Algorithm Implementations

출처 : http://doctory.egloos.com/10511327

Computer Vision Open Source Algorithm Implementations
http://www.cnblogs.com/seacode/archive/2010/05/08/1730599.html
Participate in Reproducible Research
WARNING: this page is not and will never be exhaustive but only try to gather robust implementations of Computer Vision state of the art


(back to computer vision resource) 
If you have additions or changes, send an e-mail (remove the "nospam").

Changelog 

RSS feed. If you have any issue please send an e-mail (remove the "nospam"). 
This material is presented to ensure timely dissemination of computer vision algorithms. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each authors copyright. 

General Image Processing
OpenCV 
(C/C++ code, BSD lic) Image manipulation, matrix manipulation, transforms 
Torch3Vision 
(C/C++ code, BSD lic) Basic image processing, matrix manipulation and feature extraction algorithms: rotation, flip, photometric normalisations (Histogram Equalization, Multiscale Retinex, Self-Quotient Image or Gross-Brajovic), edge detection, 2D DCT, 2D FFT, 2D Gabor, PCA to do Eigen-Faces, LDA to do Fisher-Faces. Various metrics (Euclidean, Mahanalobis, ChiSquare, NormalizeCorrelation, TangentDistance, ...) 
GradientShop 
(C/C++ code, GPL lic) GradientShop: A Gradient-Domain Optimization Framework for Image and Video Filtering 
ImLab 
(C/C++ code, MIT lic) A Free Experimental System for Image Processing (loading, transforms, filters, histogram, morphology, ...) 
CIMG 
(C/C++ code, GPL and LGPL lic) CImg Library is an open source C++ toolkit for image processing 
Generic Image Library (GIL) - boost integration 
(C/C++ code, MIT lic) Adobe open source C++ Generic Image Library (GIL) 
Image Acquisition, Decoding & encoding 
FFMPEG 
(C/C++ code, LGPL or GPL lic) Record, convert and stream audio and video (lot of codec) 
OpenCV 
(C/C++ code, BSD lic) PNG, JPEG,... images, avi video files, USB webcam,... 
Torch3Vision 
(C/C++ code, BSD lic) Video file decoding/encoding (ffmpeg integration), image capture from a frame grabber or from USB, Sony pan/tilt/zoom camera control using VISCA interface 
lib VLC 
(C/C++ code, GPL lic) Used by VLC player: record, convert and stream audio and video 
Live555 
(C/C++ code, LGPL lic) RTSP streams 
ImageMagick 
(C/C++ code, GPL lic) Loading & saving DPX, EXR, GIF, JPEG, JPEG-2000, PDF, PhotoCD, PNG, Postscript, SVG, TIFF, and more 
DevIL 
(C/C++ code, LGPL lic) Loading & saving various image format 
FreeImage 
(C/C++ code, GPL & FPL lic) PNG, BMP, JPEG, TIFF loading 
Segmentation
OpenCV 
(C/C++ code, BSD lic) Pyramid image segmentation 
Branch-and-Mincut 
(C/C++ code, Microsoft Research Lic) Branch-and-Mincut Algorithm for Image Segmentation 
Efficiently solving multi-label MRFs (Readme) 
(C/C++ code) Segmentation, object category labelling, stereo 
Machine Learning
Torch 
(C/C++ code, BSD lic) Gradient machines ( multi-layered perceptrons, radial basis functions, mixtures of experts, convolutional networks and even time-delay neural networks), Support vector machines, Ensemble models (bagging, adaboost), Non-parametric models (K-nearest-neighbors, Parzen regression and Parzen density estimator), distributions (Kmeans, Gaussian mixture models, hidden Markov models, input-output hidden Markov models, and Bayes classifier), speech recognition tools 
Object Detection
OpenCV 
(C/C++ code, BSD lic) Viola-jones face detection (Haar features) 
Torch3Vision 
(C/C++ code, BSD lic) MLP & cascade of Haar-like classifiers face detection 
Hough Forests 
(C/C++ code, Microsoft Research Lic) Class-Specific Hough Forests for Object Detection 
Efficient Subwindow Object Detection 
(C/C++ code, Apache Lic) Christoph Lampert "Efficient Subwindow" algorithms for Object Detection 
Object Category Labelling
Efficiently solving multi-label MRFs (Readme) 
(C/C++ code) Segmentation, object category labelling, stereo 
Optical flow
OpenCV 
(C/C++ code, BSD lic) Horn & Schunck algorithm, Lucas & Kanade algorithm, Lucas-Kanade optical flow in pyramids, block matching 
GPU-KLT+FLOW 
(C/C++/OpenGL/Cg code, LGPL) Gain-Adaptive KLT Tracking and TV-L1 optical flow on the GPU 
Features Extraction & Matching
SIFT by R. Hess 
(C/C++ code, GPL lic) SIFT feature extraction & RANSAC matching 
OpenSURF 
(C/C++ code) SURF feature extraction algorihtm (kind of fast SIFT) 
ASIFT (from IPOL) 
(C/C++ code, Ecole Polytechnique and ENS Cachan for commercial Lic) Affine SIFT (ASIFT) 
VLFeat (formely Sift++) 
(C/C++ code) SIFT, MSER, k-means, hierarchical k-means, agglomerative information bottleneck, and quick shift 
SiftGPU 
A GPU Implementation of Scale Invariant Feature Transform (SIFT) 
Groupsac 
(C/C++ code, GPL lic) An enhance version of RANSAC that considers the correlation between data points 
Nearest Neighbors matching
FLANN 
(C/C++ code, BSD lic) Approximate Nearest Neighbors (Fast Approximate Nearest Neighbors with Automatic Algorithm Configuration) 
ANN 
(C/C++ code, LGPL lic) Approximate Nearest Neighbor Searching 
Tracking
OpenCV 
(C/C++ code, BSD lic) Kalman, Condensation, CAMSHIFT, Mean shift, Snakes 
KLT: An Implementation of the Kanade-Lucas-Tomasi Feature Tracker 
(C/C++ code, public domain) Kanade-Lucas-Tomasi Feature Tracker 
GPU_KLT 
(C/C++/OpenGL/Cg code, ) A GPU-based Implementation of the Kanade-Lucas-Tomasi Feature Tracker 
GPU-KLT+FLOW 
(C/C++/OpenGL/Cg code, LGPL) Gain-Adaptive KLT Tracking and TV-L1 optical flow on the GPU 
Simultaneous localization and mapping
Real-Time SLAM - SceneLib 
(C/C++ code, LGPL lic) Real-time vision-based SLAM with a single camera 
PTAM 
(C/C++ code, Isis Innovation Limited lic) Parallel Tracking and Mapping for Small AR Workspaces 
Camera Calibration & constraint
OpenCV 
(C/C++ code, BSD lic) Chessboard calibration, calibration with rig or pattern 
Geometric camera constraint - Minimal Problems in Computer Vision 
Minimal problems in computer vision arise when computing geometrical models from image data. They often lead to solving systems of algebraic equations. 
Camera Calibration Toolbox for Matlab 
(Matlab toolbox) Camera Calibration Toolbox for Matlab by Jean-Yves Bouguet (C implementation in OpenCV) 
Multi-View Reconstruction
Bundle Adjustment - SBA 
(C/C++ code, GPL lic) A Generic Sparse Bundle Adjustment Package Based on the Levenberg-Marquardt Algorithm 
Bundle Adjustment - SSBA 
(C/C++ code, LGPL lic) Simple Sparse Bundle Adjustment (SSBA) 
Stereo
Efficiently solving multi-label MRFs (Readme) 
(C/C++ code) Segmentation, object category labelling, stereo 
Structure from motion
Bundler 
(C/C++ code, GPL lic) A structure-from-motion system for unordered image collections 
Patch-based Multi-view Stereo Software (Windows version) 
(C/C++ code, GPL lic) A multi-view stereo software that takes a set of images and camera parameters, then reconstructs 3D structure of an object or a scene visible in the images 
libmv - work in progress 
(C/C++ code, MIT lic) A structure from motion library