CHAPTER 5

Question 1

• In computer vision and image
  processing, a…………….is a piece of
  information about the content of an
  image; typically, about whether a
  certain region of the image has
  certain properties

Answer 1

feature

Question 2

Features may be specific structures
in the image such as ……….,…………. or ………….

Answer 2

points, edges
or objects.

Question 3

Local and Global Features in Images

Answer 3

Relevant feature (global or local)
contains discriminating
information and is able to
distinguish one object from others.

• Global features describe the
  entire image
• Local features describe the image
  patches (small group of pixels).

Question 4

• Image Matching
  using……………..

Answer 4

Feature Points

Question 5

Feature Points are Used for

Answer 5

• Image alignment (e.g., mosaics)
• 3D reconstruction
• Motion tracking
• Object recognition
• Indexing and database retrieval
• Robot navigation

Question 6

T/F
Invariant Local Features

• Image content is
  transformed into
  local feature
  coordinates that are
  invariant to
  translation, rotation,
  scale, and other
  imaging parameters

Answer 6

T

Question 7

Processing Stages

Answer 7

• Feature detection/extraction (look for stable/accurate features)
• Feature description (aim for invariance to transformations)
• Feature matching (for photo collection) or tracking (for video)

Question 8

SIFT Algorithm (Scale Invariant Feature Transform)

Answer 8

• Types of invariance
• Affine (Viewpoint Change)

Question 9

• In general, SIFT algorithm can
  be decomposed into four steps:

Answer 9

1. Feature point (also called
   keypoint) detection.
2. Feature point localization.
3. Orientation assignment.
4. Feature descriptor generation.