This project was developed as part of the Image Processing for Computer Vision course at the University of Bologna. The goal of this project is to implement a neural network that classifies smartphone pictures of products found in grocery stores. The project is be divided into two parts: first, A neural network is implemented from scratch for image classification; then, a pretrained network provided by PyTorch is fine-tuned.
- Grocery Store Dataset
- The dataset of natural images of grocery items. All natural images was taken with a smartphone camera in different grocery stores.
- Self-designed neural network reached 66% accuracy on test set
- A fine-tuned Resnet-18 reached 87% accuracy on test set