Scribd
Upload
2 views38 pages

13 Image Segmentation

Image segmentation is the process of decomposing a scene into components to aid in tasks like object detection and recognition, with no definitive ground truth for segmentation tasks. It has various applications, including medical imaging, satellite imagery, and surveillance, utilizing methods such as thresholding and K-means clustering. Different techniques for segmentation include edge-based, color-based, texture-based, disparity-based, and motion-based methods, each suited for specific types of images.

Uploaded by

u2104050
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
2 views38 pages

13 Image Segmentation

Image segmentation is the process of decomposing a scene into components to aid in tasks like object detection and recognition, with no definitive ground truth for segmentation tasks. It has various applications, including medical imaging, satellite imagery, and surveillance, utilizing methods such as thresholding and K-means clustering. Different techniques for segmentation include edge-based, color-based, texture-based, disparity-based, and motion-based methods, each suited for specific types of images.

Uploaded by

u2104050
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Introduction

 What is image segmentation?


 Technically speaking, image segmentation refers
to the decomposition of a scene into different
components (thus to facilitate the task at higher
levels such as object detection and recognition)
 Scientifically speaking, segmentation is a
hypothetical middle-level vision task performed by
neurons between low-level and high-level cortical
areas
 There is no ground truth to a segmentation
task (an example is given in the next slide)

1
Dilemma

input result 1 result 2

What do we mean by “DIFFERENT” objects?

Another example: when we look at trees at a close distance, we consider


each of them as a different object; but as we look at trees far away, they
merge into one coherent object (woods)

2
Applications: Finding tumors, veins, etc. in medical images, finding
targets in satellite/aerial images, finding people in surveillance
images, summarizing video, etc.

• Methods: Thresholding, K-means clustering, etc.

3
Overview of Segmentation Techniques
Edge-based Document images

Color-based Medical images

Texture-based Range images

Biometric images
Disparity-based
Texture images
Motion-based

4
5
Edge-based Techniques
Segmentation
Edge Classification
by boundary
detection and analysis
detection

6
7
8
9
10
11
12
Region-Filling

13
Color-Based Techniques

 Color representations
 Device dependent: RGB (displaying) or CMYK (printing)
 Device independent: CIE XYZ or CIELAB (L*a*b*)

14
Color Space Conversion

Analog
TV

Digital
TV(MPEG)

15
16
17
18
Data Clustering via Kmeans

19
Data Clustering via Kmeans

20
21
Data Clustering via Kmeans

22
Data Clustering via Kmeans

23
24
Data Clustering via Kmeans

25
Data Clustering via Kmeans

26
27
28
29
Data Clustering via Kmeans

30
Data Clustering via Kmeans

Instead of 2D, kmeans can be applied to 3D color space RGB or L*a*b*

31
Texture-based Techniques

What is Texture?

No one exactly knows.

In the visual arts, texture


is the perceived surface quality
of an artwork.

32
Disparity-based Techniques

33
Motion Segmentation

34
Document Segmentation

 Document images
consist of texts,
graphics, photos and
so on
 Document
segmentation is useful
for compression, text
recognition
 Adobe and Xerox are
the major players

35
Medical Image Segmentation

 Medical image analysis


can be used as
preliminary screening
techniques to help
doctors
 Partial Differential
Equation (PDE) has
been used for
segmenting medical
images
active contour model (snake)

36
Range Image Segmentation

range intensity ground


truth

37
Biometric Image Segmentation

 For fingerprint, face and


iris images, we also
need to segment out
the region of interest
 Various cues can be
used such as ridge
pattern, skin color and
pupil shape
 Robust segmentation
could be difficult for
poor-quality images

38

You might also like