9.3-MRFinCV - Machine Learning Srihari Markov Networks in...

Info iconThis preview shows pages 1–6. Sign up to view the full content.

View Full Document Right Arrow Icon
Machine Learning Srihari 1 Markov Networks in Computer Vision Sargur Srihari srihari@cedar.buffalo.edu
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Machine Learning Srihari Topics 1. Computer Vision Applications 2. Image Segmentation 3. Denoising 2
Background image of page 2
Machine Learning Srihari Markov Networks for Computer Vision • Important application area for MNs 1. Image segmentation 2. Removal of blur/noise 3. Stereo reconstruction 4. Object recognition • Typically called MRFs in vision community 3
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Machine Learning Srihari Network Structure • Network structure is pairwise – Variables are pixels – Edges (factors): interactions betn adjacent pixels – Factors in terms of energies (negative log potential) • Values are penalties: lower value = higher probability • Association potential for nodes • Interaction potentials for edges 4
Background image of page 4
Machine Learning Srihari Image Segmentation • X i represents a region assignment for pixel i – e.g., grass, water, sky, car • To reduce computational overhead – Oversegment into superpixels (coherent regions) – Edge if two superpixels are neighbors 5
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 6
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 13

9.3-MRFinCV - Machine Learning Srihari Markov Networks in...

This preview shows document pages 1 - 6. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online