Image Segmentation

Dr. Nilamani Bhoi

Associate Professor
Dept. of Electronics and Telecommunication
Veer Surendra Sai University of Technology, Burla
 Image Segmentation

Image segmentation is the process by which a digital image is partitioned

into various groups called image objects.

• Segmentation divides an image into groups of pixels

• Pixels are grouped because they share some local property (gray level,
color, texture, motion, etc.)

2
 Image segmentation example
Image Segmentation

4/18/2025 Dr. Nilamani Bhoi, Associate Professor, ETC Engg, VSSUT Burla 3
 USE:
Image segmentation applicable to object extraction
Image Segmentation

4/18/2025 Dr. Nilamani Bhoi, Associate Professor, ETC Engg, VSSUT Burla 4
 Different methods of image segmentation
Image Segmentation

1. Thresholding based segmentation

2. Edge based segmentation
3. Region based segmentation
4. Clustering based segmentation
5. Hybrid segmentation

4/18/2025 Dr. Nilamani Bhoi, Associate Professor, ETC Engg, VSSUT Burla 5
 Region based segmentation

The region based segmentation methods involve the

algorithm creating segments by dividing the image
Image Segmentation

into various components having similar characteristics.

Region base segmentation method can be

(i) Region growing

(ii) Region splitting and merging

4/18/2025 Dr. Nilamani Bhoi, Associate Professor, ETC Engg, VSSUT Burla 6
  Region Growing
 Region growing is a procedure that groups pixels or sub regions
into larger regions.
 The simplest of these approaches is pixel aggregation, which starts
Image Segmentation

with a set of “seed” points and from these grows regions by

appending to each seed points those neighboring pixels that have
similar properties (such as gray level, texture, color, shape).
 Region growing based techniques are better than the edge-based
techniques in noisy images where edges are difficult to detect.

4/18/2025 Dr. Nilamani Bhoi, Associate Professor, ETC Engg, VSSUT Burla 7
 8×8, 3-bit image
Seed Pixel

5 6 6 7 7 7 6 6
Image Segmentation

Region Growing
6 7 6 7 5 5 4 7

6 6 4 4 3 2 5 6

5 4 5 4 2 3 4 6

0 3 2 3 3 2 4 7

0 0 0 0 2 2 5 6

1 1 0 1 0 3 4 4

1 0 1 0 2 3 5 4

Criteria: diff(pixel, seed pixel)<Threshold

Threshold =3

4/18/2025 Dr. Nilamani Bhoi, Associate Professor, ETC Engg, VSSUT Burla 8
 Region 1
Developed Region

5 6 6 7 7 7 6 6
Image Segmentation

Region Growing
6 7 6 7 5 5 4 7

6 6 4 4 3 2 5 6

5 4 5 4 2 3 4 6

0 3 2 3 3 2 4 7

0 0 0 0 2 2 5 6

1 1 0 1 0 3 4 4

1 0 1 0 2 3 5 4

Region 2

4/18/2025 Dr. Nilamani Bhoi, Associate Professor, ETC Engg, VSSUT Burla 9
 8×8, 3-bit image
Seed Pixel

5 6 6 7 7 7 6 6
Image Segmentation

Region Growing
6 7 6 7 5 5 4 7

6 6 4 4 3 2 5 6

5 4 5 4 2 3 4 6

0 3 2 3 3 2 4 7

0 0 0 0 2 2 5 6

1 1 0 1 0 3 4 4

1 0 1 0 2 3 5 4

Criteria: diff(pixel, seed pixel)<Threshold

Threshold =3

4/18/2025 Dr. Nilamani Bhoi, Associate Professor, ETC Engg, VSSUT Burla 10
 Developed Region

5 6 6 7 7 7 6 6
Image Segmentation

Region Growing
6 7 6 7 5 5 4 7

6 6 4 4 3 2 5 6

5 4 5 4 2 3 4 6

0 3 2 3 3 2 4 7

0 0 0 0 2 2 5 6

1 1 0 1 0 3 4 4

1 0 1 0 2 3 5 4

4/18/2025 Dr. Nilamani Bhoi, Associate Professor, ETC Engg, VSSUT Burla 11
 Results - Region Growing
Image Segmentation

4/18/2025 Dr. Nilamani Bhoi, Associate Professor, ETC Engg, VSSUT Burla 12
 Results - Region Growing
Image Segmentation

4/18/2025 Dr. Nilamani Bhoi, Associate Professor, ETC Engg, VSSUT Burla 13
  Region Splitting
 Region growing starts from a set of seed points.
 An alternative is to start with the whole image as a single region
and subdivide the regions that do not satisfy a condition of
homogeneity.
Image Segmentation

 Region Merging
 Region merging is the opposite of region splitting.
 Start with small regions (e.g. 2x2 or 4x4 regions) and merge the
regions that have similar characteristics (such as gray level,
variance).
 Typically, splitting and merging approaches are used iteratively.

4/18/2025 Dr. Nilamani Bhoi, Associate Professor, ETC Engg, VSSUT Burla 14
 Region Splitting & Merging
Region Splitting

5 6 6 7 7 7 6 6
Image Segmentation

6 7 6 7 5 5 4 7

6 6 4 4 3 2 5 6

5 4 5 4 2 3 4 6

0 3 2 3 3 2 4 7

0 0 0 0 2 2 5 6

1 1 0 1 0 3 4 4

1 0 1 0 2 3 5 4

Criteria: diff(Maximum pixel, Minimum pixel)≤Threshold

Threshold =3

Splitting into 4 regions if diff > 3 Max=7, Min=0

4/18/2025 Dr. Nilamani Bhoi, Associate Professor, ETC Engg, VSSUT Burla 15
 Region Splitting Contd....

Region Splitting & Merging

Max=7, Min=4 Max=7, Min=2
5 6 6 7 7 7 6 6
Image Segmentation

6 7 6 7 5 5 4 7

6 6 4 4 3 2 5 6

5 4 5 4 2 3 4 6

0 3 2 3 3 2 4 7

0 0 0 0 2 2 5 6

1 1 0 1 0 3 4 4

1 0 1 0 2 3 5 4

Max=3, Min=0
Max=7, Min=0

Criteria: diff(Maximum pixel, Minimum pixel)≤Threshold

Threshold =3

Splitting into 4 regions if diff > 3

4/18/2025 Dr. Nilamani Bhoi, Associate Professor, ETC Engg, VSSUT Burla 16
 Splited Regions

Region Splitting & Merging

5 6 6 7 7 7 6 6
Image Segmentation

6 7 6 7 5 5 4 7

6 6 4 4 3 2 5 6

5 4 5 4 2 3 4 6

0 3 2 3 3 2 4 7

0 0 0 0 2 2 5 6

1 1 0 1 0 3 4 4

1 0 1 0 2 3 5 4

Criteria: diff(Maximum pixel, Minimum pixel)≤Threshold

Threshold =3

Splitting into 4 regions if diff > 3

4/18/2025 Dr. Nilamani Bhoi, Associate Professor, ETC Engg, VSSUT Burla 17
 Region Merging Region 1 and Region 2 Merged

Region Splitting & Merging

5 6 6 7 7 7 6 6
Image Segmentation

6 7 6 7 5 5 4 7

6 6 4 4 3 2 5 6

5 4 5 4 2 3 4 6

0 3 2 3 3 2 4 7

0 0 0 0 2 2 5 6

1 1 0 1 0 3 4 4

1 0 1 0 2 3 5 4

Region 1: Max. Pixel =7 Region 2: Max. Pixel =7

Min. Pixel=4 Min. Pixel=5

Criteria: diff(Maximum pixel, Minimum pixel)≤Threshold

Threshold =3
4/18/2025 Dr. Nilamani Bhoi, Associate Professor, ETC Engg, VSSUT Burla 18
 Region Merging Contd.. Region 2 and Region 3 Merged

Region Splitting & Merging

5 6 6 7 7 7 6 6
Image Segmentation

6 7 6 7 5 5 4 7

6 6 4 4 3 2 5 6

5 4 5 4 2 3 4 6

0 3 2 3 3 2 4 7

0 0 0 0 2 2 5 6

1 1 0 1 0 3 4 4

1 0 1 0 2 3 5 4

Region 2: Max. Pixel =7 Region 2: Max. Pixel =7

Min. Pixel=5 Min. Pixel=4

Criteria: diff(Maximum pixel, Minimum pixel)≤Threshold

Threshold =3
4/18/2025 Dr. Nilamani Bhoi, Associate Professor, ETC Engg, VSSUT Burla 19
 Developed Region using Splitting and Merging

Region Splitting & Merging

5 6 6 7 7 7 6 6
Image Segmentation

6 7 6 7 5 5 4 7

6 6 4 4 3 2 5 6

5 4 5 4 2 3 4 6

0 3 2 3 3 2 4 7

0 0 0 0 2 2 5 6

1 1 0 1 0 3 4 4

1 0 1 0 2 3 5 4

4/18/2025 Dr. Nilamani Bhoi, Associate Professor, ETC Engg, VSSUT Burla 20
 Results – Region Split
Image Segmentation

4/18/2025 Dr. Nilamani Bhoi, Associate Professor, ETC Engg, VSSUT Burla 21
 Results – Region Split and Merge
Image Segmentation

4/18/2025 Dr. Nilamani Bhoi, Associate Professor, ETC Engg, VSSUT Burla 22
 Results – Region Split
Image Segmentation

4/18/2025 Dr. Nilamani Bhoi, Associate Professor, ETC Engg, VSSUT Burla 23
 Results – Region Split and Merge
Image Segmentation

4/18/2025 Dr. Nilamani Bhoi, Associate Professor, ETC Engg, VSSUT Burla 24