Image Finder

A simple image finder (image search engine) built from the concept of CBIR (Content-Based Image Retrieval) systems.

Setting up this Application:

1. Clone the Repository

   $ git clone git@github.com:FredDoe/image-finder.git
   $ cd image-finder

2. Create a virtual environment with Python module venv and activate it

[Windows]
python -m venv venv
.\venv\Scripts\activate


[Linux/macOS] 
python3 -m venv venv
source venv/bin/activate

3. Install Dependencies

[Windows]
pip install -r requirements.txt

[Linux/macOS]
pip3 install -r requirements.txt

Using the Finder 💻🔎

• You need a dataset of images to work on. Populate the dataset folder with images. A sample dataset can be obtained from INRIA Holidays Dataset.

• You need to index the sample dataset. Run the following command in a terminal opened into the project directory:

[Windows]
python index.py --dataset dataset --index index.csv

[Linux/macOS]
python3 index.py --dataset dataset --index index.csv

• To perform search on the dataset, execute this command:

[Windows]
python search.py --index index.csv --query <path-to-image-search-query> --result-path dataset

Example: python search.py --index index.csv --query queries/123600.jpg --result-path dataset


[Linux/macOS]
python3 search.py --index index.csv --query <path-to-image-search-query> --result-path dataset

Example: python3 search.py --index index.csv --query queries/123600.jpg --result-path dataset

Demo 🎥

Search results from query:

Reference 📖

Content-Based Image Retrieval (CBIR)