vlfeat/vlfeat

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1648 stars · 619 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

VLFeat is an open-source C library of popular computer vision algorithms specializing in image understanding and local feature extraction and matching, including SIFT, MSER, HOG, Fisher Vector, VLAD, k-means, and SVM training. It ships with a MATLAB/Octave toolbox and command-line utilities, and supports Windows, Mac OS X, and Linux.

Use cases

• extract SIFT features from images
• detect MSER regions in an image
• compute HOG descriptors for object detection
• train large-scale SVM classifiers
• cluster visual features with k-means
• encode image features with Fisher vectors or VLAD
• segment images into superpixels with SLIC or quick shift
• match local features for image stitching

When to choose

• you need classic computer vision feature extraction (SIFT, MSER, HOG) in C or MATLAB
• you want efficient, portable, BSD-licensed vision algorithms without heavy dependencies
• you are doing research or teaching with MATLAB and need vision algorithms
• you need Fisher Vector/VLAD encodings for image classification pipelines

When to avoid

• you need deep learning or GPU-accelerated models rather than classical vision algorithms
• you need actively developed software with frequent updates and modern language bindings
• you require Python-first tooling with a modern API
• you need real-time or mobile-optimized vision inference

Facets

library · maturity maintenance

computer-vision image-processing machine-learning math computer-vision image-processing machine-learning windows cpp python sift mser feature-extraction matlab-toolbox fisher-vector vlad kmeans svm superpixels c-library algorithms linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="vlfeat/vlfeat")