Computational

# Computational - Computer Vision A. Problems Studied. i. ii....

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

Computer Vision A. Problems Studied. i. Edge Detection ii. Region Growing iii. Texture Segmentation iv. Texture Classification v. Shape from Shading vi. Shape from Texture vii. Shape from Motion viii. Shape from Disparity Computer Vision A. Problems Studied. Edge Detection Computer Vision A. Problems Studied. Region Growing Computer Vision A. Problems Studied. Texture Classification and Segmentation 1

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

View Full Document
Computer Vision A. Problems Studied. Shape from Shading Computer Vision A. Problems Studied. Shape from Texture Blocks World Winograd (1972): SHRDLU 2
Blocks World Roberts (1965): Edge Extraction Blocks World Waltz (1975): Line Labelling Blocks World A. Waltz (1975) i. We will consider a simplified blocks world in which all vertexes are trihedral , there are no shadows and no accidental alignments . non-trihedral vertexes accidental alignments 3

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

View Full Document
Blocks World A. Waltz (1975) ii. In this world lines are either boundary lines (or occluding lines) or interior lines that can be convex or concave. Occluding lines are labelled with ‘ > ’, convex lines with ‘ + ’ and concave lines with ‘ - ’. Blocks World A. Waltz (1975) iii. In this world lines there are only four junction types (vertexes) to consider: Arrow, Fork, T and L (not shown). Blocks World A. Waltz (1975) iv. Examples of objects formed exclusively with triherdral vertexes. Blocks World A. Waltz (1975) v. In this blocks world there are only 18 legal junction/vertex labellings. In this blocks world these junction labels would never occur. 4
Blocks World A. Waltz (1975) vi. Legal labellings can be enumerated by considering all possible ways of filling this space, which comprises eight octants. Blocks World

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

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

## This note was uploaded on 04/20/2011 for the course PSYC 212 taught by Professor Shahin during the Fall '11 term at McGill.

### Page1 / 13

Computational - Computer Vision A. Problems Studied. i. ii....

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

View Full Document
Ask a homework question - tutors are online