digital image processing in the name of god digital image processing lecture8: image segmentation m....
TRANSCRIPT
![Page 1: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/1.jpg)
In The Name Of God
Digital Image ProcessingDigital Image Processing
Lecture8:
Image Segmentation
By: M. Ghelich OghliM. Ghelich OghliE-mail: E-mail: [email protected][email protected]
Fall 2012
![Page 2: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/2.jpg)
Image Segmentation
• Description: Subdividing image into its constituent regions or objects
•There is not any absolute theory of image segmentation.
Rather, there are a collection of methods that have received some degree of popularity.
![Page 3: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/3.jpg)
Detection of Discontinuity
• Point Detection
![Page 4: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/4.jpg)
Detection of Discontinuity
• Line Detection
![Page 5: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/5.jpg)
Example of Line Detection
![Page 6: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/6.jpg)
Detection of Discontinuity
• Edge Detection: detection of discontinuity in image• Edge Model
![Page 7: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/7.jpg)
Edge Detection• using first order derivatives• using second order derivatives
![Page 8: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/8.jpg)
Noise effect in Edge Detection
Result: noise filtering is required especially in second order derivatives
![Page 9: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/9.jpg)
Gradient operators
![Page 10: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/10.jpg)
Edge Detection (first order derivatives)
![Page 11: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/11.jpg)
Edge Detection (Second order derivatives)
• Laplacian
• Laplacian of Gaussian (LoG)
![Page 12: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/12.jpg)
Edge Detection (LoG)
![Page 13: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/13.jpg)
Image Segmentation
1. Hard segmentationA pixel belongs to object or background
![Page 14: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/14.jpg)
Image Segmentation
2. Soft (Fuzzy) segmentation
First class Second class Third class
![Page 15: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/15.jpg)
Image Segmentation
Image Segmentation methods
•Pixel based methods
•Region based methods
•Clustering segmentation methods
•Boundary detection
•Texture segmentation
![Page 16: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/16.jpg)
Image Segmentation
Pixel based methodsConceptually, the simplest approach we can take for
segmentation.
But, it is not the best method.
The most sensible example of this category:
Thresholding
![Page 17: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/17.jpg)
Thresholding
• Foundation:
![Page 18: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/18.jpg)
Thresholding
• In A: light objects in dark background
• To extract the objects:
– Select a T that separates the objects from the background
– i.e. any (x,y) for which f(x,y)>T is an object point.
• A thresholded image:
(objects)
(background)
![Page 19: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/19.jpg)
Thresholding
• In B: a more general case of this approach (multilevel thresholding)
• So: (x,y) belongs:
– To one object class if T1<f(x,y)≤T2
– To the other if f(x,y)>T2
– To the background if f(x,y)≤T1
![Page 20: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/20.jpg)
Global Thresholding
![Page 21: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/21.jpg)
Multi level Thresholding
![Page 22: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/22.jpg)
Adaptive Thresholding
Advantage: Alleviates the illumination problem
Method: Divides the original image to subimages and applies threshold to each subimage individually
![Page 23: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/23.jpg)
Adaptive Thresholding
![Page 24: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/24.jpg)
Image Segmentation
Region based methodsRegion based methods doesn’t include one of the most
important disadvantage of pixel-based techniques and it is
ignoring pixel relationships and connectivity.
An object consists of not independent and not isolated
pixels.
A robust segmentation method should consider this fact.
![Page 25: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/25.jpg)
Region Growing
In this method neighboring pixels of similar amplitude
are grouped together to form a segmented region.
Image segmentation partitions the set X into the subsets R(i), i=1,
…,N having the following properties
• X = i=1,..N U R(i)
• R(i) ∩ R(j) = 0 for i ≠ j
• P(R(i)) = TRUE for i = 1,2,…,N
• P(R(i) U R(j)) = FALSE for i ≠ j
![Page 26: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/26.jpg)
Region Growing by Pixel Aggregation
• A simple approach to image segmentation is to start from some pixels (seeds) representing distinct image regions and to grow them, until they cover the entire image
• For region growing we need a rule describing a growth mechanism and a rule checking the homogeneity of the regions after each growth step
![Page 27: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/27.jpg)
Region Growing by Pixel Aggregation
• The growth mechanism – at each stage k and for each region Ri(k), i = 1,…,N, we check if there are unclassified pixels in the 8-neighbourhood of each pixel of the region border
• Before assigning such a pixel x to a region Ri(k),we check if the region homogeneity:
P(Ri(k) U {x}) = TRUE , is valid
![Page 28: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/28.jpg)
Gray Space map
Compute the seed gray level (V) and look for pixels have the same gray level and over lap the seed
Then define a set of gray levels from “V-D” to “V+D”
Region Growing by Pixel Aggregation
Ghelich Oghli, M., Fallahi, A., Pooyan, M. Automatic Region Growing Method using GSmap and Spatial Information on Ultrasound Images. In: 18th Iranian Conference on Electrical Engineering, May 11-13, pp. 35-38 (2010)
At each iteration we increase the difference D by 1
![Page 29: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/29.jpg)
Region Growing by Pixel Aggregation
Ghelich Oghli, M., Fallahi, A., Pooyan, M. Automatic Region Growing Method using GSmap and Spatial Information on Ultrasound Images. In: 18th Iranian Conference on Electrical Engineering, May 11-13, pp. 35-38 (2010)
![Page 30: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/30.jpg)
Image Segmentation
Clustering segmentation methodsSubdividing data's into classes based on some criteria's.
![Page 31: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/31.jpg)
K-Means Clustering
1. Set ic (iteration count) to 1
2. Choose randomly a set of K means m1(1), …, mK(1) (Center
of Classes).
3. For each pixel compute D(xi , mk(ic)), k=1,…K and assign
xi to the cluster Cj with nearest mean.
4. Increment ic by 1, update the means to get m1(ic),…,mK(ic).
5. Repeat steps 3 and 4 until Ck(ic) = Ck(ic+1) for all k.
![Page 32: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/32.jpg)
K-Means Clustering
In some applications (Specially medical application)
because of effect of other slices, absolutely assigning a
pixel to a class is not logically true.
So, we should classify data's by a fuzziness view.
And we should use:
Fuzzy C-Means (FCM)
algorithm
![Page 33: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/33.jpg)
Fuzzy C-Means (FCM)
•A membership function exists for each class at every pixel location
0; if the pixel does not belong to the class
1; if the pixel belongs, with absolute certainty, to the class
0-1; degree of belonging a pixel to a class
at any pixel location the sum of the membership functions
of all the classes must be 1
The fuzzy membership function reflects the similarity
between the data value at that pixel and the value of the
class centroid.
![Page 34: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/34.jpg)
Fuzzy C-Means (FCM)
![Page 35: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/35.jpg)
Fuzzy C-Means (FCM)
![Page 36: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/36.jpg)
Boundary Detectionor
Curve Fitting • It is possible to segment an image into regions of common
attribute by detecting the boundary of each region for which there is a significant change in attribute across the boundary.
• Methodology
Initial guess
Iteratively deforming curves according to the minimization of
internal and external energy functional and controls the smoothness of the curve.
![Page 37: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/37.jpg)
Boundary Detectionor
Curve Fitting
![Page 38: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/38.jpg)
Boundary Detectionor
Curve Fitting
Drawback(Speckle Noise)
Example
![Page 39: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/39.jpg)
Deformable models– Parametric Deformable models (Snake)
– Geometric Deformable models (Level set)
Boundary Detectionor
Curve Fitting
![Page 40: Digital Image Processing In The Name Of God Digital Image Processing Lecture8: Image Segmentation M. Ghelich Oghli By: M. Ghelich Oghli E-mail: m.g31_mesu@yahoo.com](https://reader036.vdocuments.us/reader036/viewer/2022062718/56649e935503460f94b98aa8/html5/thumbnails/40.jpg)
LevelsetThis figure illustrates several important ideas about the level set method.
A bounded regionBoundary=zero level set
Graph of a level set function
Changing (Evolving) in Region…
Moving X-Y plane through …