Computer-vision project combining classification, detection, and retrieval.

It uses ResNet for building classification, YOLO for entrance detection, and ORB/neural features for image retrieval. The goal is to recognize buildings and detect entrances from images, with possible assistive-navigation use cases.

The project was developed as part of the Computer Vision and Cognitive Systems course at the University of Modena and Reggio Emilia. It demonstrates classical and deep visual methods in one pipeline: object detection, image classification, feature matching, and retrieval.

---

← Back to projects