2CompTheories of Vision - computed and why. What problem is...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Computational Theories of Vision Problem of low-level vision : Recovery of physical properties of the visual environment, e.g., depth, surface orientation, boundaries of objects, material properties, motion etc. Problem of high-level vision : Object recognition, scene analysis. The work of David Marr (mainly low-level vision). Levels of explanation 1. Level of computational theory 2. Level of algorithm 3. Level of mechanism
Background image of page 1

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

View Full DocumentRight Arrow Icon
Level 1 (computational theory) refers to what is being
Background image of page 2
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: computed and why. What problem is being solved? What would count as an effective (optimal?) solution? What are the constraints that apply and how do they help make the problem solvable? Level 2 (algorithm) refers to how the problem is solved. What algorithm allows us to compute a solution? Level 3 (mechanism) refers to actual hardware or wetware used to implement the algorithm. What neural structures allow the algorithm to operate?...
View Full Document

This note was uploaded on 08/12/2008 for the course PSY 387R taught by Professor Diehl during the Spring '07 term at University of Texas at Austin.

Page1 / 2

2CompTheories of Vision - computed and why. What problem is...

This preview shows document pages 1 - 2. Sign up to view the full document.

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