plantsphoto: A Tiny Browser AI That Rewards You for Touching Grass
The image itself is passed directly to the local model in the browser. There is no image upload API, database, or server-side image processing. The source code and deployment workflow are available on GitHub: https://github.com/M-Taka-Shin/Touch-Grass The site is deployed with GitHub Pages, and updates to the master branch are automatically deployed through GitHub Actions. Why open innovation…
The plantsphoto browser AI project allows users to take a photo and receive a confirmation that it's a plant. This is achieved through a local machine-learning model that runs within the user's browser, without needing to send the image to a remote server. The entire project is open-source and deployed on GitHub Pages, making it easy to view, modify, and share.
The key advantages of this approach include privacy, affordability, and the ability to inspect and update the model and application flow. The project also promotes portability, as it can run on a normal laptop or phone browser, and is replaceable, allowing for the potential use of another model as the project evolves. Through this simple design, the project demonstrates that an AI feature doesn't need to dominate a product, but rather can serve as a small confirmation step in an otherwise observational experience.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
