Machine Learning Project for the course "Machine Learning" at FH Hagenberg with the Google "Quick, Draw!" dataset (https://github.com/googlecreativelab/quickdraw-dataset)
The aim of this project was to develop a system capable of recognizing drawings, especially those depicting specific animals. To achieve this goal, different types of models were used, and their respective accuracy was compared. Users were able to make sketches of animals on a canvas, which transforms the pictures in the necessary format. The system then analyses these drawings and makes predictions about the animals they represent.
Google provides the data of the drawings, which were recorded in their game Quick, Draw! (https://quickdraw.withgoogle.com/). The dataset is available under the following link: https://github.com/googlecreativelab/quickdraw-dataset. The Quick Draw Dataset is a collection of 50 million drawings across 345 categories. The drawings were captured as timestamped vectors, tagged with metadata including what the player was asked to draw and in which country the player was located.