# Practicals

## Practical 3: Segmenting images using Markov Random Fields

**Due:** April 12, 2018 (23:59)

In this practical, you will use graphical models to segment a given image using a graph-cut-based formulation.

In particular, the purpose of this homework is to make you familiarize with the following concepts:

- Markov Random Fields (MRFs),
- GraphCut and GrabCut segmentation algorithms,

You will use the starter code provided here.

For more details on the homework, please read this document.

## Practical 2: Patched-based image denoising using learned dictionaries

**Due:** March 29, 2018 (23:59)

In this practical, you will use sparse representations to denoise a given image using a visual dictionary of patches.

In particular, the purpose of this homework is to make you familiarize with the following concepts:

- sparse modelling of images,
- using K-SVD algorithm (M. Aharon et al., 2006),
- experimental evaluation of denoising methods.

You will use the starter code provided here.

For more details on the homework, please read this document.

## Practical 1: Boundary Detection via Sketch
Tokens

**Due:** March 8, 2018 (23:59)

In this practical, you will implement a slightly simplified version of the so-called Sketch Tokens boundary detection method (Lim, Zitnick, and Dollar, 2013).

In particular, the purpose of this homework is to make you familiarize with the following concepts:

- using machine learning to detect boundaries in images,
- working on a benchmark dataset, namely Berkeley Segmentation dataset,
- experimental evaluation of boundary detection methods.

You will use the starter code provided here.

For more details on the homework, please read this document.