CS292 Computational Vision and Language

1
CS292 Computational Vision and Language

• Segmentation and Region Detection

2
(No Transcript)
3
Introduction

• All pixels belong to a region, which can be
• an object
• part of object
• background
• Find region
• By finding constituent pixels in a region
• By finding boundary pixels

4
Image Segmentation Task

• To divide the image into regions or segments,
  each of which is in some sense homogeneous, but
  the union of adjacent segments is not homogeneous
  in the same sense.
• Homogeneity here is characterized by some
  properties like
• smoothly varying intensity, similar statistics,
  or colour.

5
Region Detection

• A set of pixels P
• An homogeneity predicate H(P)
• Partition P into regions R, such that

6
Image Segmentation

• Many techniques including
• Non-contextual technique thresholding
• Contextual techniques
• region-based
• connectivity-preserving relaxation methods.
• Other methods Image primitive based
• Mixture of all these

7
Threshold techniques

• make decisions based on local pixel information
• are effective when the intensity levels of the
  objects fall squarely outside the range of levels
  in the background.

8
Global thresholds

• Compute threshold from whole image
• Incorrect in some regions

9
Local thresholds

• Divide image into regions
• Compute threshold per region
• Merge thresholds across region boundaries

10
Contextual techniques

• Contextual techniques take into account the fact
  that pixels belonging to a single object are
  close to one another.
• Approaches to contextual segmentation are based
  on the concept of discontinuity or concept of
  similarity.
• detecting abrupt changes- edge detection
  techniques,
• or to create uniform regions directly,
• Discontinuity and similarity approaches mirror
  one another, in the sense that completion of
  boundary is equivalent to breaking one region
  into two.

11
Region Growing

• All pixels belong to a region
• Select a pixel
• Grow the surrounding region
• (we will practise this in lab class)

12
Slow Algorithm

• If a pixel is
• not assigned to a region
• adjacent to region
• has colour properties not different to regions
• Then
• Add to region
• Update region properties

13
Split and Merge

• Initialise image as a region
• While region is not homogeneous
• split into quadrants and examine homogeneity

14
Recursive Splitting

• Split(P)
• If (!H(P))
• P ? subregions 1 4
• Split (subregion 1)
• Split (subregion 2)
• Split (subregion 3)
• Split (subregion 4)

15
Recursive Merging

• If adjacent regions are
• weakly split
• weak edge, depending on defined criteria
• similar
• similar greyscale/colour properties
• Merge them

16
Edge Following

• Detection
• finds candidate edge pixels
• Following
• links candidates to form boundaries

17
Representing Regions

• Constituent pixels
• Boundary pixels

18
Based on both regions and edges
19
Based on the combination of colour and texture
20
Active Contour Model- Snake

• A connectivity-preserving relaxation-based
  segmentation method, - active contour model
  snake
• The main idea is to start with some initial
  boundary shape represented in the form of spline
  curves, and iteratively modify it by applying
  various shrink/expansion operations according to
  some energy function.
• Concepts involved
• Image gradient
• Smooth operation
• Histogram equalization
• Energy functions

21
Snakes, Active/Dynamic Contours

• Borders follow outline of object
• Outline obscured?
• Snake provides a solution

22
Algorithm

• Snake computes smooth, continuous border
• Minimises
• length of border
• curvature of border
• Against an image property
• gradient?

23
Minimisation

• Initialise snake
• Integrate energy along it
• Iteratively move snake to global energy minimum

24
Active Contour Method
Case study next week, notes will be given during
the lecture
25
Summary

• Image segmentation
• Region detection
• growing
• edge following