mateogianolio/ocr

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1132 stars · 94 forks observed · 2026-08-28

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

A JavaScript library that trains a multi-layer perceptron neural network to perform optical character recognition on digits and characters. Training data is auto-generated from captchas or sourced from the MNIST handwritten digit database, and the trained network is exported as a standalone module.

Use cases

• recognize handwritten digits with a neural network
• train an OCR model in JavaScript
• classify characters from binary pixel arrays
• experiment with MNIST digit classification
• generate a standalone OCR prediction module
• learn how neural networks do character recognition

When to choose

• you want a small, dependency-light neural network OCR example in Node.js
• you need to train a simple MLP on MNIST or captcha-generated glyphs
• you want a trained model exported as a standalone require-able module

When to avoid

• you need production-grade OCR for documents or complex layouts
• you want actively maintained software or modern deep learning frameworks
• you need support for full alphabets, fonts, or image preprocessing pipelines

Facets

library · maturity abandoned

ocr machine-learning deep-learning machine-learning computer-vision image-processing cross-platform neural-network mlp mnist captcha character-recognition nodejs

Member repositories

For agents

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