Feature Detection

Question 1

Edge Tracking

Answer 1

Edge Strength: magnitude of intensity gradient
Edge orientation: direction of intensity gradient
edge location: zero crossings of Laplace operator

Question 2

Canny Edge Operator

Answer 2

problem: seperate edge from noise
assumptions: 1. edge gradient stronger than noise gradient
2. edge direction varies slowly
3. edge strength varies slowly
thresholds: 1. t1 voxel is edge
t2 voxel is edge if neighbor is edge
+ detects parts of edges
- sensitive to noise

Question 3

Hough Transform

Answer 3

idea. find instances of specific edge model viat voting scheme
hough space represents all parameter combinations
+ robust against occlusion, signal drops, noise

Question 4

structure tensor

Answer 4

summarizes the predominant directions of the gradient neighborhood

Question 5

Harris Corner Detector

Answer 5

value depends on average intensity variations in arbitrary directions
high value = point of interest
+ detects corners and edges
- computational expensive

Question 6

SUSAN corner detector

Answer 6

intensity of poi differs from intensities in neighborhood
intensity difference is higher than threshold
poi is maximum of difference
+ detects corners and single points
+ faster computation
- sensitive to noise

Question 7

Blob detection

Answer 7

Blob: circular structures in image
use: laplacian of gaussian, difference of gaussions, determinant of hessian

Question 8

Feature detection SIFT

Answer 8

generates and uses features to detect and identify objects in image

1. key point generation
2. key point reduction
3. feature computation

Question 9

Feature detection MSER

Answer 9

seperation of image into local homogeneous regions with maximum contrast
intensity based feature detection

Question 10

Segmentation

Answer 10

part image to connected regions which can be classified

Question 11

Segmentation - Thresholding

Answer 11

image voxels into labeled voxels and background voxels based on intensity thresholds

• interactive thresholding
• automatic thresholding

Question 12

Segmentation - Otsu

Answer 12

find optimal threshold

- characteristics of foreground and background are nearly equal

Question 13

Segmentation - homogeneity based

Answer 13

seperate image into smallest number of segments that all fulfills homogeneity criterion

Question 14

Region Growing

Answer 14

start with seed point in object region
homogeneity criterion determines inclusion of adjacent voxels
neighborhood definition: bigger (robust against noise), smaller (robust against leaking into other regions)

Question 15

Region Merging

Answer 15

• each voxel is own region

- if two adjacent voxel fulfill homogeneity criterion, merge to one region

Question 16

relational structures

Answer 16

information between semantically important image parts (inside, neighboors)

Question 17

Region Splitting and Merging

Answer 17

• start: image is one region
• split until homogeneity criterion is met
• Splitting result in RAG
• merging is speed up

Question 18

Watershed Transform (WST)

Answer 18

• treat as image as landscape
• local minimum is sink
• fill sinks with water, when water meets include watershed

Question 19

Live Wire

Answer 19

find minimum cost path between user-defined markers and create contour as series of path segments

Question 20

Morphological Operations

Answer 20

• study of shape

- enhancements of object structure (skeletonization, thinning, thickening)

Question 21

Opening and Closing

Answer 21

• opening: erosion followed by delation (remove small isolated regions)
• closing: dilation followed by erosion (close holes)
• remove leakage / close gaps

Question 22

Skeletonization

Answer 22

• skelaton: minimal structure discribing topology of object
• analysis of branching objects / tree structures
• erosing from vessel surface
• hierachry position of brances (lowest levels can be irrelevant)

Question 23

Measurement of object extend

Answer 23

• identify of size of object
• use axis-oriented bounding box
• maybe need to rotate first