Link to project

Open on GitHub

Introduction

This project intends to classify between cat and non-cat images by using two different methods: solving a system of linear equations with the use of Householder QR decomposition and using the Gradient Descent method.

Creating the application

The application was developed in Octave.

Key concepts used:

  • working with vectors and matrices
  • RGB and HSV histograms
  • Householder QR decomposition
  • Gradient Descent

Final notes

Thank you for taking the time to read this page; hopefully you found the project interesting and fun.