Computer Vision for Blind Person
Project information
- Project duration: Dec 2020-Jan 2021
- Used pre-trained YOLOv3 model trained on Common Object in Context (COCO) Dataset for Object Detection.
- Generated the speech such as 2 Persons at center right, 2 glasses at center, 1 Chair at Bottom left
- Deployed in Google Cloud Platform (GCP) using Flask.
Github Link