- Home
- Reverse Image Search Software
- Open Image Search
Open Image Search
Zurich, Switzerland
What it is
Open Image Search is an open-source reverse image search prototype for graphical collections and museums working with digitized prints and paintings. Its hosted demo searches more than 20,000 prints from the Graphische Sammlung of ETH Zürich. Users can also clone the project, provide their own image data, and run retrieval locally. The system extracts visual features with VGG16 and applies a k-nearest neighbors model to locate similar images. Metadata can be supplied in a CSV file using the documented column names. The Vue web interface works on mobile devices and can send a request from a phone camera. A Django REST Framework backend reformats uploaded images in memory, sends them to the model, and retrieves metadata for top matches. The repository lists Vue, Django, TensorFlow, scikit-learn, SQLite, and Nginx, and uses the MIT license. It is self-hosted or web-based, remains a prototype, and GitHub marks it read-only after archival on September 1, 2026.
For and against
For
- Hosted demo searches over 20,000 prints
- Local retrieval supports a collection's own images
- Uses VGG16 and k-nearest neighbors
- Mobile interface accepts phone-camera searches
- Released under the MIT license
Against
- Repository is archived and read-only
- Project remains in prototype development
- Finds similar images rather than source-page results
- Requires self-hosting for custom collections
The verdict
Open Image Search provides a focused visual-search workflow for museum and print collections, with hosted and local options. Its prototype status and archived repository should be considered before adoption.
Who it suits
Open Image Search is intended for museums and graphical collections managing digitized prints or paintings. It also suits developers who want to run visual retrieval with their own image data.
On the record
- Backend
- A Django REST Framework API reformats uploaded images in memory, sends them to the feature extraction model, and uses the results to retrieve metadata for top matches.github.com · read 8 Oct 2026
- Development status
- The README describes the application as in development and in a prototype phase.github.com · read 8 Oct 2026
- Hosted access
- The README links to an online application where users can upload pictures to find visually similar prints from the Graphische Sammlung of ETH Zürich.github.com · read 8 Oct 2026
- Hosted collection
- The README says the hosted demo lets users search a database of more than 20,000 prints from the Graphische Sammlung of ETH Zürich.github.com · read 7 Oct 2026
- Image handling
- Uploaded images are reformatted in memory before a request is sent to the feature extraction model.github.com · read 7 Oct 2026
- Intended users
- The project is aimed at graphical collections and museums working with digitized prints and paintings.github.com · read 7 Oct 2026
- License
- The software is distributed under the MIT License, which permits use, copying, modification, distribution, and sale subject to its terms.github.com · read 8 Oct 2026
- Local use
- The project can be cloned and run locally with a user’s own image data, metadata, and installed software dependencies.github.com · read 8 Oct 2026
- Metadata
- Users can supply image metadata in a CSV file, with permitted column names described in the project documentation.github.com · read 7 Oct 2026
- Mobile access
- The web interface is designed to work on mobile devices and supports sending search requests directly from a phone camera.github.com · read 7 Oct 2026
- Mobile interface
- The Vue web interface is designed to work on mobile devices and can send search requests from a phone’s camera.github.com · read 8 Oct 2026
- Project status
- The repository describes the application as in development and says it is in a prototype phase.github.com · read 7 Oct 2026
- Purpose
- Open Image Search is a prototype reverse image search tool for finding digitized print metadata and supporting workflows at graphical collections and museums.github.com · read 8 Oct 2026
- Repository status
- GitHub says the repository was archived by its owner on September 1, 2026, and is read-only.github.com · read 8 Oct 2026
- Search method
- The application extracts image features with VGG16 and uses a k-nearest neighbours model to find similar images.github.com · read 8 Oct 2026
- Support
- The README directs inquiries to the ETH Library Lab contact form.github.com · read 8 Oct 2026
- Technology
- The README lists TensorFlow, scikit-learn, Vue, Django, SQLite, and Nginx among the project’s libraries and frameworks.github.com · read 8 Oct 2026
