SLIDE 1
CS262: Computer Vision Image Regions
John Magee
Slides courtesy of Diane H. Theriault
Question of the Day
- How do you identify and compute properties
- f objects found in images?
CS262: Computer Vision Image Regions John Magee Slides courtesy of - - PowerPoint PPT Presentation
CS262: Computer Vision Image Regions John Magee Slides courtesy of - - PowerPoint PPT Presentation
CS262: Computer Vision Image Regions John Magee Slides courtesy of Diane H. Theriault Question of the Day How do you identify and compute properties of objects found in images? Post-processing Basic segmentations can be messy. How can
SLIDE 2
SLIDE 3
Post-processing
- Basic segmentations can be messy. How can
you clean them up?
SLIDE 4
Morphological Operators: Erosion
image “structuring element” result Any pixel where the whole structuring element doesn’t fit in the foreground is removed
SLIDE 5
Morphological Operators
image “structuring element” result Put structuring element on every pixel and turn on all pixels the structuring element touches
SLIDE 6
Identifying Image Regions
- Image as a Graph
- Definition of Connectivity
4 Connected 8 Connected
SLIDE 7
Depth First Traversal / Flood Fill: Recursive
- Depth-first Traversal(self)
– If self marked, stop – Else
- Mark self
- For each neighbor
– Depth-first traversal(neighbor)
- What do you know about the architecture of computer
memory that might cause a problem here with a very large image region?
- [A real “Google Interview” question!
SLIDE 8
Depth First Traversal / Flood Fill: Iterative
- Solution: Use a stack data structure instead of
the program stack
- Depth-first Traversal(self)
– Stack.push(self) – While(!stack.empty())
- node = stack.pop()
- For each neighbor
– If not marked » Mark neighbor » Stack.push(neighbor)
SLIDE 9
Removing Small Image Regions
- For each image region, count number of pixels
- For any regions smaller than some threshold,
flood fill the region with a zero
SLIDE 10
Holes
- A hole is any non-foreground that you can’t reach from the
“background” e.g. the edge of the image
SLIDE 11
Defining Holes
- If Black is background and
white is foreground, are the pink squares background or a hole?
- Foreground: 8 connected
- Background 4: connected
SLIDE 12
Boundary Following
- Find any pixel in an object (e.g. by scanning
through image) then put your “right hand” on the object and walk around till you get back to your start point
SLIDE 13
Boundary Following
- How do you keep your “right hand” on the wall? Check all
neighboring pixels, always going clockwise (or counter-
- clockwise. Consistency is key)
SLIDE 14
Where is the boundary?
- The pixels themselves, or between the pixels?
SLIDE 15
Where are the boundaries?
SLIDE 16
Where are the boundaries?
- One convention: Have
boundaries between background and foreground go clockwise and boundaries between
- bjects and holes go
counter-clockwise
- Keep a tree of the
relationships between
- bjects, holes, and
- bjects in the holes
SLIDE 17
Where are the Boundaries?
- One convention: Have
boundaries between background and foreground go clockwise and boundaries between objects and holes go counter-clockwise
- Keep a tree of the
relationships between objects, holes, and objects in the holes
SLIDE 18
Properties of Image Regions
- “Location”
– Set of Pixels – Boundary – Centroid (center) – Bounding Box – Bounding Ellipse – Convex Hull
- Distance between
image regions?
Shapiro & Stockman, Chapter 3. Szeliski 3.3.4
SLIDE 19
Properties of Image Regions
- “Shape”
– Area – Perimeter – Orientation – Compactness – Circularity – Image Moments
SLIDE 20
Properties of Image Regions
- “Appearance”
– Mean brightness – Mean color – Brightness or Color histogram – Other measures of appearance
SLIDE 21