# loopr-ocr

> Use the power of Machine Learning to detect Azure Logos in the web browser

Latest version **1.0.0** (published 2023-09-05) · MIT license · 0 weekly downloads

## Install

```sh
npm install loopr-ocr
pnpm add loopr-ocr
yarn add loopr-ocr
bun add loopr-ocr
```

## Health

**Score 15/100 (F)** — status: abandoned.

Positive: no vulnerabilities.

Warnings: low downloads; no types; no esm support; large bundle.

Negative: abandoned; low maintenance score.

## Facts

| | |
|---|---|
| Version | 1.0.0 |
| Published | 2023-09-05 |
| First published | 2023-09-05 |
| Weekly downloads | 0 |
| License | MIT |
| TypeScript types | none |
| Module format | CommonJS |
| Dependencies | 3 |
| Unpacked size | 11.7 MB |
| Known vulnerabilities | 0 |
| Install scripts | no |
| GitHub stars | 14 |
| Author | Sascha Dittmann |
| Maintainers | mahendrapamidi |

## Links

- npm: https://www.npmjs.com/package/loopr-ocr
- Repository: https://github.com/SaschaDittmann/tfjs-cv-objectdetection
- Homepage: https://github.com/SaschaDittmann/tfjs-cv-objectdetection#readme
- Issues: https://github.com/SaschaDittmann/tfjs-cv-objectdetection/issues
- npm.io page: https://npm.io/package/loopr-ocr

## Dependencies (3)

- [canvas](https://npm.io/package/canvas.md) ^2.9.0
- [express](https://npm.io/package/express.md) ^4.17.1
- [@tensorflow/tfjs-backend-webgpu](https://npm.io/package/@tensorflow/tfjs-backend-webgpu.md) ^4.10.0

## Recent versions

- 1.0.0 (latest) — 2023-09-05

## README

[![Software License](https://img.shields.io/badge/license-MIT-brightgreen.svg?style=flat-square)](LICENSE)
[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com)

# TensorFlow.js: Digit Detection

This code is built off Sascha Dittman's object detection with TensorFlow.JS demo: https://github.com/SaschaDittmann/tfjs-cv-objectdetection. The model is a custom-trained YOLOv8 model, converted to the TensorFlow.JS format with this tutorial: https://docs.ultralytics.com/modes/export/#arguments. The code to convert raw model output into coherent bounding boxes comes from https://github.com/Hyuto/yolov8-tfjs/. Also, big shout-out to netron.app for making life much easier.

## Setup 

Prepare the node environments:
```sh
$ yarn
```

Run the local web server script:
```sh
$ node server.js
```

Then, to get a URL to the port this has ran the server on, install localtunnel and use it:
```sh
$ npm install -g localtunnel
$ lt --port 3000
```

---
_Source: https://npm.io/package/loopr-ocr · Machine-readable twin of the npm.io package page. Health data is recomputed on every publish._