Image_Retrieval

Image_Retrieval

Finds pictures similar to a query picture in a small holiday photo collection, with three saved methods named naive, bovw and cnn. For students and developers learning image retrieval.

Made by leopoldmaillard on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: This Gradio app from leopoldmaillard is an image retrieval demo. The repository ships a folder of holiday pictures and three saved files named naive, bovw and cnn, which suggest three ways of matching images. You use it in a browser, or you run a copy on your own computer.

Who it suits: It suits students and developers who want to see how image search can work and compare simple matching with learned features. Teachers can show it as a live demo.

Industry | Who uses it | How they use it | Example
Education | Computer vision students | Compare image matching methods on the same collection | Open the Space and try a query picture
Research | Machine learning researchers | Look at a small retrieval setup with saved indexes | Read app.py next to the saved files
Software | Python developers | Run a copy locally and adapt it to their own pictures | Download the Space and start app.py

Skip it if you need to search a large private photo library, because the repository holds a small sample collection.

Where to use it:

• A web browser: go to the Space on Hugging Face and try it with no install
• Windows, macOS or Linux: run a copy with Python

Use case | Who | What they get back
Find similar pictures | Students | Pictures from the collection that match the query
Compare methods | Researchers | A view of how the three saved methods differ
Study the code | Developers | An app.py that loads saved files and a picture folder

How to set it up: You need a few things in place first.

• Python with pip, on Windows, macOS or Linux
• An internet connection to fetch the files from Hugging Face
• Disk space for a large repository, since it holds 1513 files

1. Install the Hugging Face hub package.
2. Download the Space into a local folder.
3. Move into that folder.
4. Install Gradio and the packages listed in requirements.txt.
5. Start the app.

pip install -U huggingface_hub
hf download leopoldmaillard/ImageRetrieval --repo-type space --local-dir ImageRetrieval
cd ImageRetrieval
pip install gradio
pip install -r requirements.txt
python app.py

How to use it: Online, use the Gradio interface the Space page shows. On your own computer, run the main file from the project folder and open the page it serves in your browser.

python app.py

Example: You run python app.py inside the project folder and open the page it serves. You give it a query picture, and the page shows pictures from the collection that it judges close to yours.

For newcomers and experts: If this is new to you, start online. Go to the Space and try one query picture before you install anything. A local copy is heavier, so try the hosted page first.

If you know the field, note that the saved files named naive, bovw and cnn point to a plain baseline, a bag of visual words and a convolutional network. The source does not confirm this or give scores, so read app.py to check.

Open the Space or run app.py
The Gradio page loads
You give it a query picture
The app matches it to the collection
Similar pictures appear on the page

Good to know: The repository holds saved pkl files that the app loads, so run a copy only from a source you trust.

• License: mit
• Cost to run: none named, no API key, account or paid service
• Data it reaches: the pictures and saved files in the repository, plus your query picture

On Hugging Face, 13 November 2026

• Likes: 1
• Built with: gradio
• License: mit

Links

• Space: https://huggingface.co/spaces/leopoldmaillard/ImageRetrieval
• Files: https://huggingface.co/spaces/leopoldmaillard/ImageRetrieval/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.