# inspirit/jsfeat

JavaScript Computer Vision library.

Repository: https://github.com/inspirit/jsfeat
Canonical: https://ross.abutalabs.com/products/jsfeat
Language: JavaScript
License: MIT
License Family: permissive
Last push: 2022-04-16T09:05:57+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 5046, "days_push": 1600, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2772, forks 374 (observed 2026-08-28T04:07:19.083452+00:00)

## What it is
JSFEAT is a JavaScript computer vision library implementing classic CV algorithms in pure JS for browser use. It includes image processing filters, feature detection/description, optical flow, object detection, and linear algebra utilities.

## Use cases
- detect faces in the browser with haar cascades
- track points in a webcam video with lucas-kanade optical flow
- detect corners and compute orb descriptors in javascript
- apply canny edge detection or sobel filters to canvas images
- estimate homography between images with ransac
- do matrix math and svd in the browser

## When to choose
- you need lightweight, dependency-free computer vision running client-side in JavaScript
- you want classic CV algorithms (FAST, ORB, LK optical flow, HAAR) without native builds or WebAssembly
- you are prototyping HTML5 canvas or webcam vision demos

## When to avoid
- you need GPU-accelerated or deep-learning-based vision (use OpenCV.js, TensorFlow.js, or ONNX runtime)
- you need actively maintained code with recent fixes and modern tooling
- you need high-performance processing of large video streams

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, image-processing, machine-learning
- domain: computer-vision, image-processing, web-development
- platform: browser
- tags: optical-flow, feature-detection, haar-cascade, orb, linear-algebra, html5-canvas, nodejs, javascript

## Member repositories
- inspirit/jsfeat (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:19.083452+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T08:16:37.955941+00:00, confidence not recorded.
  - readme: https://github.com/inspirit/jsfeat (fetched 2026-08-28T04:07:19.083452+00:00, sha 6a38c758b73e)
- Data as of 2026-08-30T08:39:29.467469+00:00.