harthur/kittydar

Health v2 · maintenance only

Flags: no_releases archived

Adoption not part of the score

1428 stars · 155 forks observed · 2026-08-28

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

Kittydar is a JavaScript library that detects the locations of cat faces in images using Histogram of Oriented Gradients features fed into a pre-trained neural network. It works on canvas elements in the browser or via node-canvas in Node.js.

Use cases

• find all cats in a photo and get their bounding boxes
• detect cat faces in images from the browser using canvas
• run cat detection server-side in node with node-canvas
• experiment with HOG features and neural networks for object detection
• add a fun cat-detection demo to a web page

When to choose

• you need a lightweight, dependency-free JavaScript cat detector for a demo or toy project
• you want a simple, readable example of HOG + neural network object detection
• your images show upright, forward-facing cats and speed is not a concern

When to avoid

• you need production-grade accuracy or speed - it is slow and misses or misclassifies cats
• you need detection of arbitrary objects or modern deep-learning-based detection
• you need an actively maintained library - the project is a 2012 talk demo with no ongoing development

Facets

library · maturity abandoned

computer-vision image-processing machine-learning computer-vision image-processing machine-learning browser cat-detection face-detection hog-features neural-network canvas demo-project nodejs javascript

Member repositories

For agents

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