Download as pdf or txt
Download as pdf or txt
You are on page 1of 13

(11) Representation and Description

- Low-level image processing * Image enhancement, restoration, transformation


Image Image Enhancement Enhanced Image Restoration/ Transformation Restored/ Transformed Image

- Mid-level image processing (image understanding) * Object representation, description


Restored/ Transformed Image Image Segmentation Segmented Image Object Representation/ Description Representation/ Description/ Features

11-1

- High-level image processing (recognition and interpretation) * Object recognition, interpretation of object relationships
Representation/ Description/ Features Object Recognition Objects Image Interpretation Meaning/ Relationships

(a) Chain code


- Chain codes: represent a boundary by a connected sequence of straightline segments of specified length and direction * Choose an appropriate grid to approximate objects

11-2

4-direction: 1

8-direction: 2 3 1
1 1 1 0 0

0 3 3 3 3 3 2 3 3 1 2 0 2

7 6 6 6 5 5

4 5 7

1 1 2 1 2

3 2

11-3

* Chain code (clockwise): * Problem 1: different starting points result in different chain codes
4-direction: 00333332322121110101, 8-direction: 07666553321202 # Solution: normalization redefine the starting point such that the chain code forms a smallest number # E.g.: 6553320000 0000655332 # Solution: difference code coding with the difference of directions (counter-clockwise) # E.g.: 0000655332 0006706076 0006706076 (normalization)

* Problem 2: object rotation results in different chain codes

(b) Polygonal approximation


- Polygonal approximation: approximate a boundary using a polygon - Minimum perimeter polygons * Choose an appropriate grid
The boundary is enclosed by a set of concatenated cells

* Allow the boundary to shrink as a rubber band


11-4

- Merging techniques 1. Merge points along a boundary until the least square error line fit of the points merged so far exceeds a threshold 2. Record the the two end point of the line 3. Repeat Steps 1 and 2 until all boundary points are processed

11-5

- Splitting techniques Subdivide a boundary segment successively into two parts until a specified criterion is satisfied 1. Find two points on the boundary that are farthest away and draw a line
Splitting line divides the boundary into two boundary segments

2. For each boundary segment, find a point on the boundary that has a maximum perpendicular distance to its corresponding line
11-6

3. Draw two lines joining the point and the two end points, respectively, of the corresponding splitting line 4. Repeat Steps 2~3 until the perpendicular distance is less than a threshold
Subdivide the boundary segment into two parts

11-7

(c) Signature
- Signature: a 1D functional representation of a boundary * Plot the distance from the centroid to the boundary as a function of angles: signature = r(), = 0 ~ 2

(d) Boundary descriptors


- Descriptions of boundary * Perimeter: length of the chain code * Diameter: maxi,j(D(pi, pj))
11-8

pi
Ma = maxi,j(D(pi,pj))

Ma

ma

pj

Ma ma and forms a basic rectangle

* Major axis (Ma) and minor axis (ma) * Eccentricity: Ma/ma - MATLAB p = bwperim(bw, conn): find perimeter pixels * bw: binary image * conn: 4 or 8 (connectivity) * Perimeter pixels: 1-valued pixels that are connected to at least one 0valued pixels * p: returned perimeter binary image - MATLAB S = diameter(L): find descriptions of a boundary * L: a labeled image
11-9

* S: a structure with the following fields


# S.Diameter, S.MajorAxis, S.MinorAxis, S.BasicRectangle

(e) Regional descriptors


- Compactness: perimeter2/area - Topological: Euler number, E = C H (number of connected component number of holes)

E = 1 3 = 2

E=11=0

E = 1 2 = 1

- MATLAB D = regionprops(L, properties)


11-10

* L: labeled image * Properties: 'Area', 'BoundingBox', 'Centroid' * D: a structure with the fields specified when invoking regionprops( )
* E.g., D.Area

- Texture * Statisticcal approaches


* Intensity mean: m=i=0 z i p z i ,
L1

* nth moment about the mean: n =i=0 z i mn p z i


Moment Mean Standard deviation Smoothness Third moment Expression Description Measure of average intensity Measure of average contrast Measure of smoothness of intensity histogram; 0: symmetric, positive: skewed to the right; negative:
L1

L1

m=i=0 z i p z i

= z z = 2
R = 11/(1+2)
L1

3=i=0 z i m3 p z i Measure of skewness of the

11-11

skewed to the left Uniformity Entropy

U =i=0 p 2 z i
L1

L1

Measure of uniformity; maximum: all graylevels are equal

e=i=0 p z i log 2 z i Measure of randomness

* Sprectral approach: based on Fourier spectrum * Structural approach: structure of the texture primitives

11-12

(f) High-level image processing


- High-level image processing (computer vision) * Recognition and interpretation * Object recognition: identify objects based on object models * Interpretation: using artificial intelligence to infer the following
# Properties of objects: identity, size, material, 2D/3D position, orientation # Relationships among objects: occlusion, relative position Further inference: planning of path, operations, control

- Applications: robotics, industrial automatic inspection, autonomous navigation, document image analysis, bio-information recognition

11-13

You might also like