{"id":13436261,"url":"https://github.com/vlfeat/vlfeat","last_synced_at":"2025-05-15T11:08:14.483Z","repository":{"id":562274,"uuid":"193263","full_name":"vlfeat/vlfeat","owner":"vlfeat","description":"An open library of computer vision algorithms","archived":false,"fork":false,"pushed_at":"2022-08-25T07:57:03.000Z","size":10399,"stargazers_count":1626,"open_issues_count":152,"forks_count":623,"subscribers_count":155,"default_branch":"master","last_synced_at":"2025-04-14T19:58:46.143Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"http://vlfeat.org/","language":"C","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-2-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/vlfeat.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"COPYING","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2009-05-05T18:14:47.000Z","updated_at":"2025-03-31T02:01:40.000Z","dependencies_parsed_at":"2022-07-08T05:10:25.614Z","dependency_job_id":null,"html_url":"https://github.com/vlfeat/vlfeat","commit_stats":null,"previous_names":[],"tags_count":26,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vlfeat%2Fvlfeat","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vlfeat%2Fvlfeat/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vlfeat%2Fvlfeat/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vlfeat%2Fvlfeat/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vlfeat","download_url":"https://codeload.github.com/vlfeat/vlfeat/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254328384,"owners_count":22052632,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-07-31T03:00:45.999Z","updated_at":"2025-05-15T11:08:14.460Z","avatar_url":"https://github.com/vlfeat.png","language":"C","funding_links":[],"categories":["Machine Learning","Uncategorized","进程间通信"],"sub_categories":["Uncategorized","机器学习"],"readme":"# VLFeat -- Vision Lab Features Library\n\n\u003e Version 0.9.21\n\nThe VLFeat open source library implements popular computer vision\nalgorithms specialising in image understanding and local featurexs\nextraction and matching.  Algorithms incldue Fisher Vector, VLAD,\nSIFT, MSER, k-means, hierarchical k-means, agglomerative information\nbottleneck, SLIC superpixes, quick shift superpixels, large scale SVM\ntraining, and many others. It is written in C for efficiency and\ncompatibility, with interfaces in MATLAB for ease of use, and detailed\ndocumentation throughout. It supports Windows, Mac OS X, and Linux.\n\nVLFeat is distributed under the BSD license (see the `COPYING` file).\n\nThe documentation is\n[available online](http://www.vlfeat.org/index.html) and shipped with\nthe library as `doc/index.html`. See also:\n\n* [Using with MATLAB](http://www.vlfeat.org/install-matlab.html)\n* [Using the command line utilities](http://www.vlfeat.org/install-shell.html)\n* [Using the C API](http://www.vlfeat.org/install-c.html)\n* [Compiling from source](http://www.vlfeat.org/compiling.html)\n\n## Quick start with MATLAB\n\nTo start using VLFeat as a MATLAB toolbox, download the latest VLFeat\n[binary package](http://www.vlfeat.org/download/). Note that the\npre-compiled binaries require MATLAB 2009B and later. Unpack it, for\nexample by using WinZIP (Windows), by double clicking on the archive\n(Mac), or by using the command line (Linux and Mac):\n\n    \u003e tar xzf vlfeat-X.Y.Z-bin.tar.gz\n\nHere X.Y.Z denotes the latest version. Start MATLAB and run the\nVLFeat setup command:\n\n    \u003e run \u003cVLFEATROOT\u003e/toolbox/vl_setup\n\nHere `\u003cVLFEATROOT\u003e` should be replaced with the path to the VLFeat\ndirectory created by unpacking the archive. All VLFeat demos can now\nbe run in a row by the command:\n\n    \u003e vl_demo\n\nCheck out the individual demos by editing this file: `edit vl_demo`.\n\n## Octave support\n\nThe toolbox should be laregly compatible with GNU Octave, an open\nsource MATLAB equivalent. However, the binary distribution does not\nship with pre-built GNU Octave MEX files. To compile them use\n\n    \u003e cd \u003cvlfeat directory\u003e\n    \u003e make MKOCTFILE=\u003cpath to the mkoctfile program\u003e\n\n# Changes\n\n- **0.9.21** Maintenance release. Bugfixes.\n- **0.9.20** Maintenance release. Bugfixes.\n- **0.9.19** Maintenance release. Minor bugfixes and fixes compilation\n  with MATLAB 2014a.\n- **0.9.18** Several bugfixes. Improved documentation, particularly of\n  the covariant detectors. Minor enhancements of the Fisher vectors.\n- **0.9.17** Rewritten SVM implementation, adding support for SGD and\n  SDCA optimisers and various loss functions (hinge, squared hinge,\n  logistic, etc.) and improving the interface. Added infrastructure to\n  support multi-core computations using OpenMP (MATLAB 2009B or later\n  required). Added OpenMP support to KD-trees and KMeans. Added new\n  Gaussian Mixture Models, VLAD encoding, and Fisher Vector encodings\n  (also with OpenMP support). Added LIOP feature descriptors. Added\n  new object category recognition example code, supporting several\n  standard benchmarks off-the-shelf.\n- **0.9.16** Added `VL_COVDET`. This function implements the following\n  detectors: DoG, Hessian, Harris Laplace, Hessian Laplace, Multiscale\n  Hessian, Multiscale Harris. It also implements affine adaptation,\n  estiamtion of feature orientation, computation of descriptors on the\n  affine patches (including raw patches), and sourcing of custom\n  feature frame.\n- **0.9.15** Added `VL_HOG` (HOG features). Added `VL_SVMPEGASOS` and\n  a vastly improved SVM implementation. Added `VL_IHASHSUM` (hashed\n  counting). Improved INTHIST (integral histogram). Added\n  `VL_CUMMAX`. Improved the implementation of `VL_ROC` and\n  VL_PR(). Added VL_DET() (Detection Error Trade-off (DET)\n  curves). Improved the verbosity control to AIB. Added support for\n  Xcode 4.3, improved support for past and future Xcode\n  versions. Completed the migration of the old test code in\n  `toolbox/test`, moving the functionality to the new unit tests\n  `toolbox/xtest`.\n- **0.9.14** Added SLIC superpixels. Added VL_ALPHANUM(). Improved\n  Windows binary package and added support for Visual\n  Studio 2010. Improved the documentation layout and added a proper\n  bibliography. Bugfixes and other minor improvements. Moved from the\n  GPL to the less restrictive BSD license.\n- **0.9.13** Fixed Windows binary package.\n- **0.9.12** Fixes `vl_compile` and the architecture string on Linux 32 bit.\n- **0.9.11** Fixes a compatibility problem on older Mac OS X versions.\n  A few bugfixes are included too.\n- **0.9.10** Improves the homogeneous kernel map. Plenty of small\n  tweaks and improvements. Make maci64 the default architecture on the\n  Mac.\n- **0.9.9** Added: sift matching example. Extended Caltech-101\n  classification example to use kd-trees.\n- **0.9.8** Added: image distance transform, PEGASOS, floating point\n  K-means, homogeneous kernel maps, a Caltech-101 classification\n  example. Improved documentation.\n- **0.9.7** Changed the Mac OS X binary distribution to require a less\n  recent version of Mac OS X (10.5).\n- **0.9.6** Changed the GNU/Linux binary distribution to require a\n  less recent version of the C library.\n- **0.9.5** Added kd-tree and new SSE-accelerated vector/histogram\n  comparison code.  Improved dense SIFT (dsift) implementation.  Added\n  Snow Leopard and MATLAB R2009b support.\n- **0.9.4** Added quick shift. Renamed dhog to dsift and improved\n  implementation and documentation. Improved tutorials.  Added 64 bit\n  Windows binaries. Many other small changes.\n- **0.9.3** Namespace change (everything begins with a vl_ prefix\n  now). Many other changes to provide compilation support on Windows\n  with MATLAB 7.\n- **beta-3** Completes to the ikmeans code.\n- **beta-2** Many additions.\n- **beta-1** Initial public release.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvlfeat%2Fvlfeat","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvlfeat%2Fvlfeat","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvlfeat%2Fvlfeat/lists"}