https://github.com/mathusanp/nyctodetect
Image brightness detection software
https://github.com/mathusanp/nyctodetect
ai google javascript machinelearning tensorflow
Last synced: about 2 months ago
JSON representation
Image brightness detection software
- Host: GitHub
- URL: https://github.com/mathusanp/nyctodetect
- Owner: MathusanP
- License: apache-2.0
- Created: 2023-07-05T10:15:42.000Z (almost 3 years ago)
- Default Branch: master
- Last Pushed: 2023-12-18T09:20:53.000Z (over 2 years ago)
- Last Synced: 2025-05-30T23:27:18.932Z (about 1 year ago)
- Topics: ai, google, javascript, machinelearning, tensorflow
- Language: JavaScript
- Homepage: https://www.npmjs.com/package/nyctodetect
- Size: 2.43 MB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 4
-
Metadata Files:
- Readme: readme.md
- License: LICENSE
- Code of conduct: .github/CODE_OF_CONDUCT.md
Awesome Lists containing this project
README
# nyctodetect
A Node.js package that detects the brightness level of an image from a URL, built using a [Teachable Machine](https://teachablemachine.withgoogle.com) model trained on dark and light images. Then provides a confidence score on how likely it is to trigger a pattern commonly known to be associated with [Nyctophobia](https://en.wikipedia.org/wiki/Fear_of_the_dark)
Originally created as part of a Google employer engagement programme in sixth form, as a cross-disciplinary project linking psychology (nyctophobia — fear of the dark) with machine learning.
## Installation
```bash
npm install nyctodetect
```
## Usage
```js
const nyctodetect = require('nyctodetect')
const imageUrl = 'https://www.example.com/image.jpg';
nyctodetect(imageUrl);
```
## How it works
Passes an image URL through a TensorFlow.js model trained via Google's Teachable Machine to classify the image as bright or dark.
## Notes
- Model and weights were trained using [Google Teachable Machine](https://teachablemachine.withgoogle.com)
## Status
This package is no longer actively maintained and will be deprecated soon.