A multimedia information retrieval system supporting audio and image dataset queries via acoustic feature extraction, audio humming search, and image color/texture analysis. Built for IF2123 (Linear Algebra and Geometry) at STEI ITB.
| NIM | Member |
|---|---|
| 13523011 | Muhammad Ra’if Alkautsar |
| 13523061 | Darrel Adinarya Sunanda |
| 13523063 | Syahrizal Bani Khairan |
| 13523132 | Jonathan Levi |
- Audio Retrieval:
- Search by query audio file matching
- Audio humming search via acoustic pitch tracking and MIDI comparison
- Image Retrieval:
- Color histogram and texture similarity matching
- Dataset Management:
- Audio and image dataset upload and index caching
- Mapper file upload for dataset ground-truth linking
-
Navigate to the
srcdirectory:cd src -
Create and activate a virtual environment (Python 3.11 recommended):
python3.11 -m venv venv source venv/bin/activate -
Install required dependencies:
pip install -r requirements.txt
-
Run the application:
python main.py
MIT