| <p align="center"> | |
| <img src="panner.png" width="1200" alt="Vision-AN18 banner" /> | |
| </p> | |
| # Vision-AN18 | |
| Privacy-preserving computer vision for detecting and anonymizing sensitive visual information in street images. | |
| ## Overview | |
| Vision-AN18 is a deep learning pipeline designed to detect license plates and house numbers in public images, then blur the identified regions to preserve privacy while keeping the overall image useful. | |
| The project combines: | |
| - a data preparation pipeline, | |
| - a Faster R-CNN detection model, | |
| - an anonymization module, | |
| - a FastAPI inference service, | |
| - a simple Gradio demo for testing. | |
| ## Key Features | |
| - License plate detection | |
| - House number detection | |
| - Gaussian blur anonymization | |
| - Dataset preprocessing pipeline | |
| - Inference and deployment support | |
| - GPU-ready training workflow | |
| ## Model | |
| The detection model is based on Faster R-CNN with a ResNet-50 + FPN backbone. | |
| Training was performed on an NVIDIA RTX 5050, and the model is intended to be shared on Hugging Face for easier reproducibility and deployment. | |
| ## Repository Structure | |
| Avainble soon on github repo | |
| ## License | |
| This project is intended for research and privacy-oriented computer vision experiments. | |