# mateogianolio/ocr

Neural network OCR.

Repository: https://github.com/mateogianolio/ocr
Canonical: https://ross.abutalabs.com/products/ocr
Language: JavaScript
License: MIT
License Family: permissive
Last push: 2016-07-07T12:48:38+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 4194, "days_push": 3709, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1132, forks 94 (observed 2026-08-28T04:03:42.789245+00:00)

## What it is
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
- artifact type: library
- maturity: abandoned
- function: ocr, machine-learning, deep-learning
- domain: machine-learning, computer-vision, image-processing
- platform: cross-platform
- tags: neural-network, mlp, mnist, captcha, character-recognition, nodejs

## Member repositories
- mateogianolio/ocr (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:42.789245+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 2026-08-30T06:37:58.199814+00:00, confidence not recorded.
  - readme: https://github.com/mateogianolio/ocr (fetched 2026-08-28T04:03:42.789245+00:00, sha 9abb07549414)
- Data as of 2026-08-30T08:39:29.467469+00:00.