Foundations of Deep Learning

Authors:

Gaetano Chiriaco

Gianmarco Russo

Data Science MSc @ University of Milan-Bicocca.

Pill Quality Control

Image classification and augmentation using traditional techniques and Generative Adversarial Neural Networks.

• The first objective of this project is to perform classification on pills, specifically trying to detect if in a quality control scenario is possibile to detect pills with cosmetics defects like chips or dirt. This task has been carried out training CNNs from scratch and comparing them with pre-trained nets.
• The second objective is to remedy for the lack of training data using generative adversarial neural networks (GANs), combined with traditional data augmentation.

Files

• Code_Pill notebooks contains all the code used for this project, from CNN to GANs.
• The pdf is the presentation of the project.