Image Segmentation

IMAGE
SEGMENTATION
INTRODUCTION APPLICATIONS CLASSIFICATION

WHAT IS IMAGE SEGMENTATION ??
 Segmentation refers to the process of partitioning a digital

Image into multiple segments (sets of pixels, also known
as super pixels).
 More precisely, image segmentation is the process of assigning a

label to every pixel in an image such that pixels with the
same label share certain visual characteristics.
 The goal of segmentation is to simplify and/or change the

representation of an image into something that is more
meaningful and easier to analyze.
BEFORE
AFTER
BEFORE AFTER
BEFORE AFTER
BEFORE AFTER
APPLICATIONS
 MEDICAL IMAGING
 BIOMETRICS APPLICATIONS
 AGRICULTURAL IMAGING
 LOCATE OBJECTS IN SATELLITE IMAGES
 3-D IMAGING
 TRAFFIC CONTROL SYSTEMS, ROBOTICS

MEDICAL IMAGING
 Locate tumors and other pathologies

 Measure tissue volumes
 Computer-guided surgery
 Diagnosis
 Treatment planning
 Study of anatomical structure
M
E
D
I
C
A
L
I
M
A
G
I
N
G
BIOMETRICS APPLICATIONS
FACE RECOGNITION SYSYTEMS
 A facial recognition system is a

computer application for automatically
identifying or verifying a person from a
digital image or a video frame from a
video source. One of the ways to do this
is by comparing selected facial
features from the image and a facial
database.
 It is typically used in security systems

and can be compared to other biometrics
such as fingerprint or eye iris
recognition systems.
AGRICULTURAL IMAGING
 With increasing population

pressure throughout the world
and the need for increased
agricultural production there is a
definite need for improved
management of the world's
agricultural resources.
 To make this happen it is first

necessary to obtain reliable data
on not only the types, but also
the quality, quantity and location
of these resources..
LOCATE OBJECTS IN SATELLITE IMAGES
 Image segmentation is an important task

in image processing and analysis.
Many segmentation methods have been
used to segment satellite images.
 The success of each method depends on

the characteristics of the acquired
image such as resolution limitations and
on the percentage of imperfections in the
process of image acquisition due to
noise.
 Some of them are parametric statistical

methods that use many parameters which
3D – IMAGING
 A basic task in 3-D image

processing is the segmentation of
an image which classifies
voxels/pixels into objects or
groups.
 3-D image segmentation makes

it possible to create 3-D
rendering for multiple objects and
perform quantitative analysis for
the size, density and other
parameters of detected objects.
TRAFFIC CONTROLLING, ROBOTICS
 Image Segmentation is being

widely used by most of the traffic
systems these days. Basically it
plays a great role in controlling the
level of traffic on specific routes
and thereby accordingly
managing the traffic.
 Image segmentation is also being

used in the field of robotics. The
robots are programmed to extract
the image of interest from the
data available and send the
information about that
situation.
TYPES OF IMAGE SEGMENTATION
CLUSTERING
EDGE REGION
DETECTION GROWING
IMAGE SPLIT &

HISTOGRAM SEGMENTATION MERGE
HISTOGRAM METHOD
 In this technique , a histogram

is computed from all the pixels
in the image, and the peaks and
valleys in the histogram are
used to locate the clusters in the
image, colour and intensity can
be used as a measure.
 Vertical axis: Frequency (i.e.,
pixel counts for each bin)
 Horizontal axis: Response
variable
EDGE DETECTION METHOD
 The edge represents the step

changes in the intensity values of
adjacent pixels.
 Detects abrupt change in image

features within a small
neighborhood.
 Identifying & locating sharp

discontinuities in an image.
 It is used to obtain information from

the frames for feature extraction
and object segmentation.
EDGE DETECTION METHOD
Derivative approach
The backbone of many algorithms

is the discrete approximation of
derivative operations representing
the significant gradient of intensity
(edge).
 First order derivative

 Second order derivative
CLUSTERING METHOD
 Clustering is basically grouping together pixels that have

similar properties such as color, texture, motion, etc
 Each pixels can be treated as a data point in the feature space
 An image will be represented in terms of clusters of pixels that

belong together
 The specific criterion to be used depends on the application
 Pixels may belong together because they have the same color,
same texture, they are nearby, and so on.
CLUSTERING METHOD
Some clustering algorithms:
 DIVISION CLUSTERING:
the entire dataset is considered as a cluster, and then clusters
are recursively split to yield good clustering
 AGGLOMERATIVE CLUSTERING:
each data point is considered as a clustered, then clusters are
recursively merged to yield good clustering.
 K-MEANS CLUSTERING:
grouping the dataset into K clusters center locations
SEGMENTATION BY CLUSTERING – KMEANS
KMEANS: ITERATIVE ALGORITHM
1. Initialisation:
◮ choose K
◮ randomly guess K cluster center locations
2. Allocation: each data point finds out which center it is closest to,
and is assigned to the corresponding cluster
3. Center calculation: recompute the cluster centres by averaging all

the pixels in the cluster.
4. Repeat 2-3 until terminated (centers do not move any more)

SEGMENTATION BY CLUSTERING
SEGMENTATION BY CLUSTERING
SEGMENTATION BY CLUSTERING – KMEANS RESULTS
INFLUENCE OF THE CHOICE OF K

REGION GROWING
 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.
SPLIT AND MERGE METHOD
 This method starts at the root of the tree that represents the
whole image. If it is found non-uniform (not
homogeneous), then it is split into four son-squares (the
splitting process), and so on so forth.
 Conversely, if four son-squares are homogeneous, they can

be merged as several connected components (the merging
process).
QUADTREE
 Split-and-merge segmentation is based on a quadtree partition of

an image. It is sometimes called quadtree segmentation.
 Split and Merge method is an iterative algorithm that
includes both splitting and merging at each iteration.
R0 R1 R0
R1
R3
R2
R00 R01 R02 R04

RESULTS – REGION GROW
RESULTS – REGION SPLIT
RESULTS – REGION SPLIT AND MERGE
CONCLUSION
 THUS WE HAVE SEEN THE VARIOUS APPLICATIONS AND
METHODS OF IMAGE SEGMENTATION. THE PURPOSE OF
VARIOUS METHODS IS THE SAME THAT IS IMAGE
SEGMENTATION BUT THE APPROACH IS SOMEWHAT
DIFFERENT.
 WE HAVE SEEN THE VARIOUS APPLICATIONS OF IMAGE

SEGMENTATION IN VARIOUS FIELDS. THOUGH DIRECTLY WE
CANNOT OBSERVE THE USE OF THIS TECHNIQUE BUT IN
ONE WAY OR THE OTHER IT IS BEING EXTENSIVELY USED IN
VARIOUS FIELDS STARTING FROM MEDICAL TO THE
TRAFFIC, AGRICULTURE AND SO ON.
 SO WE CAN SAY THAT IMAGE SEGMENTATION FINDS A LOT OF

APPLICATION IN VARIOUS FIELDS AND VARIOUS
RESEARCHES AND EXPERIMENTS ARE GOING ON THIS
TECHNIQUE FOR ITS BETTER, SCIENTIFIC AND IMPROVED
APPROACH..

Image Segmentation

Uploaded by

Copyright:

Available Formats

Image Segmentation

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Image Segmentation

Uploaded by

Copyright:

Available Formats

IMAGE

INTRODUCTION APPLICATIONS CLASSIFICATION

 Segmentation refers to the process of partitioning a digital

 More precisely, image segmentation is the process of assigning a

 The goal of segmentation is to simplify and/or change the

 LOCATE OBJECTS IN SATELLITE IMAGES

 TRAFFIC CONTROL SYSTEMS, ROBOTICS

 Locate tumors and other pathologies

FACE RECOGNITION SYSYTEMS

 A facial recognition system is a

 It is typically used in security systems

 With increasing population

 To make this happen it is first

 Image segmentation is an important task

 The success of each method depends on

 Some of them are parametric statistical

 A basic task in 3-D image

 3-D image segmentation makes

 Image Segmentation is being

 Image segmentation is also being

IMAGE SPLIT &

 In this technique , a histogram

 The edge represents the step

 Detects abrupt change in image

 Identifying & locating sharp

 It is used to obtain information from

The backbone of many algorithms

 First order derivative

 Clustering is basically grouping together pixels that have

 Each pixels can be treated as a data point in the feature space

 An image will be represented in terms of clusters of pixels that

 The specific criterion to be used depends on the application

Some clustering algorithms:

KMEANS: ITERATIVE ALGORITHM

3. Center calculation: recompute the cluster centres by averaging all

4. Repeat 2-3 until terminated (centers do not move any more)

INFLUENCE OF THE CHOICE OF K

 A simple approach to image segmentation is to start from some

 Conversely, if four son-squares are homogeneous, they can

 Split-and-merge segmentation is based on a quadtree partition of

R00 R01 R02 R04

 WE HAVE SEEN THE VARIOUS APPLICATIONS OF IMAGE

 SO WE CAN SAY THAT IMAGE SEGMENTATION FINDS A LOT OF

You might also like