A Survey on Seeded Region Growing based Segmentation ... - ijcsmr

International Journal of Computer Science and Management Research Vol 2 Issue 6 June 2013
ISSN 2278-733X
A <strong>Survey</strong> on Seeded Region Growing based
Segmentation Algorithms
Savneet Dhaliwal #1 , Abhilasha Jain *2
# Computer Science Engineering, Giani Zail Singh PTU Campus,
Bathinda , Punjab , India
1
savneetdhaliwal12@gmail.com
2
abd_jain@rediffmail.com
Abstract— This paper consists a survey on various seeded region
growing based segmentation algorithms. In this survey we try to
find out the problems in existing algorithm. The main goal is
build a solid platform to automate the initial seed placement in
region growing. Because random initial seed produces dependent
regions based upon their positions. This paper also discusses the
role of the segmentation in vision theory. Various seed placement
segmentation algorithms are considered.
Keywords— Segmentation , Seed , Region split.
I. INTRODUCTION
The motivation of this research is to provide an overview
of the most recent trends and future research direction in
colour image segmentation. Rather than covering all aspects
of the domain this survey covers issues related to the most
active areas in last few years. This survey gives an overview
about the issues and problems of colour segmentation. It
focuses on the various techniques that are used for the image
segmentation with their success and weaknesses. It also
prescribes the importance of image segmentation in various
fields of engineering and medical practices like computer
vision, medical imaging processes.
Moreover image segmentation can be viewed as the core
branch for image processing as all the post coming work like
feature extraction and object recognition depends upon the
quality of image segments produced. The main goal of image
segmentation is do- main independent partitioning of an image
into a set of disjoint regions that are visually deferent,
homogeneous and meaningful with respect to some
characteristics or computed property such as grey level,
texture or colour to enable easy image analysis. Image
segmentation is a useful tool in many realms including
industry, health care, astronomy, and various other _ends.
Segmentation in concept is a very simple idea.
Simply looking at an image, one can tell what regions are
contained in a picture. Is it a building, a person, a cell, or just
simply background Visually it is very easy to determine what
a region of interest is and what is not. Doing so with a
computer algorithm on the other hand is not so easy. How do
you determine what dense a region What features distinguish
one region from another What determines how many regions
you have in a given image Discontinuity and
similarity/homogeneity are two basic properties of the pixels
in relation to their local neighbourhood used in many
segmentation methods.
The segmentation methods that are based on discontinuity
property of pixels are considered as boundary or edges based
techniques and that are based on similarity or homogeneity are
region based techniques.
II. IMAGE SEGMENTATION
Image segmentation is a process in which regions or
features sharing similar characteristics are identified and
grouped together. It is a process of extracting and representing
information from an image by grouping pixels together into
regions similarity. Most segmentation techniques are either
region-based or edge-based:
A. Region Based Segmentation
The region based segmentation is partitioning of an image
into similar/homogenous areas of connected pixels through
the application of homogeneity/similarity criteria among
candidate sets of pixels. Each of the pixels in a region is
similar with respect to some characteristics or computed
property such as colour, intensity and/or texture. Region split
and merge as well as Region growing are the points of interest
in this domain.
B. Edge Based Segmentation
Edge based segmentation is the location of pixels in the
image that core- spend to the boundaries of the objects seen in
the image. An edge or a linear feature is manifested as an
abrupt change or discontinuity in digital number of pixels
along a certain direction in an image.
Savneet Dhaliwal et.al.
2814
www.ijcsmr.org

International Journal of Computer Science and Management Research Vol 2 Issue 6 June 2013
ISSN 2278-733X
Figure 1: Segmentation Techniques
Determine the appropriate Stopping gradient or other
stopping criteria is the point of interest.
III. LITERATURE SURVEY
In the Literature <strong>Survey</strong> part research work done by
various researchers has been revisited to decide upon the
problem domain in which to pursue my thesis. The research
papers studied during the course work have been described
below brie to summarize the crux of what has been studied.
Deferent researchers have presented deferent analysis of
image segmentation techniques.
Researcher [1] describe Colour image segmentation refers
to partitioning an image into deferent regions that are
homogeneous with respect to some feature. Image
segmentation is usually the first task to any image Analysis
process. All subsequent task like feature extraction and object
recognition depends upon the quality of image segmentation.
Over segmentation an image will split an object into deferent
regions while in under segmentation it will group various
objects into one region.
In this paper researchers tested [8] Image segmentation in
track light management system. It works in the manner like
first an image is taken in a non-track mode of a track zone.
Image is converted into gravy scale. Now deferent images are
to be taken from the roads emerging towards track light.
Again those images are converted into gravy scale. Deferent
images are compared with image in non-track mode and based
on the comparison with intensity of light track management is
done.
In this paper researcher [7] proposed Image segmentation
techniques and issues. In areas such as computer vision and
image processing, image segmentation has been and still is a
relevant research area due to its wide spread usage and
application. Its accuracy but very elusive is very crucial in
areas as medical, remote sensing and image retrieval where it
may contribute to save, sustain and protect human life. This
paper provides a survey of achievements, problems being
encountered, and the open issues in the research area of image
segmentation and usage of the techniques in deferent areas.
In this survey we also suggested what must be done in
order for researchers to test their techniques performance and
to compare them among other segmentation techniques.
Researchers considered the techniques under the following
three groups i.e. Threshold Based, Edge Based and Region
Based.
In this work [11] a new approach to fully automatic colour
image segmentation, called JSEG, is presented. First, colours
in the image are quantized to several representing classes that
can be used to differentiate regions in the image. Then, image
pixel colours are replaced by their corresponding colour class
labels, thus forming a class-map of the image.
A criterion for “good” segmentation using this class-map
is proposed applying the criterion to local windows in the
class-map results in the “J-image”, in which high and low
values correspond to possible region boundaries and region
centres, respectively. A region growing method is then used to
segment the image based on the multi-scale J-images.
Experiments show that JSEG provides good segmentation
results on a variety of images.
In this paper, researcher [9] provide region based
segmentation techniques categorize as:
A. Region Split
The basic idea of region splitting is to break the image into
a set of disjoint regions, which are coherent within themselves:
Initially take the image as a whole to be the area of interest.
Look at the area of interest and decide if all pixels contained
in the region satisfy some similarity constraint, If TRUE then
the area of interest corresponds to an entire region in the
image. If FALSE split the area of interest (usually into four
equal subareas) and consider each of the sub-areas as the area
of interest in turn. This process continues until no further
splitting occurs. In the worst case this happens when the areas
are just one pixel in size. This is a divide and conquer or top
down method.
B. Region Merge
The result of region merging usually depends on the order
in which regions are merged. The simplest methods begin
merging by starting the segmentation using regions of 2x2,
4x4 or 8x8 pixels. Region descriptions are then based on their
statistical gravy level properties. A region description is
compared with the description of an adjacent region; if they
Savneet Dhaliwal et.al.
2815
www.ijcsmr.org

International Journal of Computer Science and Management Research Vol 2 Issue 6 June 2013
ISSN 2278-733X
match, they are merged into a larger region and a new region
description is computed. Otherwise regions are marked as
non-matching. Merging of adjacent regions continues between
all neighbours, including newly formed ones. If a region
cannot be merged with any of its neighbours, it is marked `-
nil' and the merging process stops when all image regions are
so marked.
In this paper [2] Active Contour Method was proposed. An
active contour is an energy minimizing spline that detects
species features within an image. It is an edible curve (or
surface) which can be dynamically adapted to required edges
or objects in the image (it can be used to automatic objects
segmentation). It consists of a set of control points connected
by straight lines. The active contour is denned by the number
of control points as well as sequence of each other. Fitting
active contours to shapes in images is an interactive process.
The user must suggest an initial contour, which is quite close
to the intended shape.
The contour will then be attracted to features in the image
extracted by internal energy creating an attractor image.
Figure 2: Basic contour formation
In paper [10] researchers has implemented Active
contours, or snakes, have been used widely for image
segment- station. A novel method incorporating geodesic
curves and region information is introduced. The extra region
force gives the active contour model a global complementary
view of the boundary information within the image. The
proposed method incorporates edge information, namely
Edgewood, into Active Contours. We refer to this as
Edgewood-driven Geometric Snake or EDGS. The partial
differential equation (PDE) resulting from this integration of
image Edgewood and region term is implemented using a
level set approach. Experimental results demonstrate that the
proposed method makes sound results, especially with respect
to images within weak boundaries, and noise.
In this paper [6] researcher propose selection of seed
points. Seed point selection is based on some user criterion.
The initial region begins as the exact location of these seeds.
The regions are then grown from these seed points to adjacent
points depending on a region membership criterion. The
criterion could be, for example, pixel intensity, gravy level
texture, or colour. Since the regions are grown on the basis of
the criterion, the image information itself is important. For
example, if the criterion were a pixel intensity threshold value,
knowledge of the histogram of the image would be of use, as
one could use it to determine a suitable threshold value for the
region membership criterion.
In this paper L et. al [5] Seed Growing method is
discussed. Segmentation of medical images using seeded
region growing technique is increasingly becoming a popular
method because of its ability to involve high-level knowledge
of anatomical structures in seed selection process. Region
based segmentation of medical images are widely used in
varied clinical applications like visualization, bone detection,
tumour detection and unsupervised image retrieval in clinical
databases.
As medical images are mostly fuzzy in nature, segmenting
regions based intensity is the most challenging task. In this
paper, authors has discussed about popular seeded region
grow methodology used for segmenting anatomical structures
in images. Researchers have proposed a gradient based
homogeneity criteria to control the region grow process while
segmenting images. Seeded region growing approach to image
segmentation is to segment an image into regions with respect
to a set of q seeds as presented in is discussed here. Given the
set of seeds, S1, S2, Sq., each step of SRG involves
identifying one additional pixel to one of the seed sets.
Moreover, these initial seeds are further replaced by the
centroids of these generated homogeneous 8 regions. The only
drawback of SRG algorithm is the docility in automating seed
generation and dependency of output on order sorting of pixel
as deferent order of processing pixels during region grow
process leads to deferent final segmentation results.
In this paper researcher [4] proposed that Segmentation of
ultrasound images is a midcult task, due to numerous artefacts
and the presence of speckled noise. Dentitions between
objects are often blurred and weakened by speckling.
Consequently, segmentation methods for ultrasound must be
resistant to noise. In this paper, a method called Seeded
Region Growing (SRG) is tested in isolating regions of
interest for later processing.
The SRG method involves selecting points called seeds as
the starting locations for the segmentation process. Seed
points may be manually or automatically selected, and both
methods of seed selection are tested and compared. The
Savneet Dhaliwal et.al.
2816
www.ijcsmr.org

International Journal of Computer Science and Management Research Vol 2 Issue 6 June 2013
ISSN 2278-733X
resulting system is tested on simulated objects and B-mode
ultrasound images of the liver with suspected lesions.
IV. HOW SEEDED REGION GROWING WORKS
Figure 3 is demonstrate that how seeded region growing
will work to grow pixel by pixel to achieve the segmentation.
Figure 3: Seed growing Method
Conclusions
By doing a deep survey on high quality journal we have found
that the placing a seed in seeded region growing segmentation
algorithm is a critical issue. Wrongly selected seed not give
much accurate results. This paper has also shown the various
algorithms which can be applied to segment a given image
using region growing based algorithms. This paper has also
shown the working of seed placement algorithms. In near
future new algorithm will be proposed which will
automatically select the seed to segment given image in
efficient manner.
REFERENCES
[1] Konstantinos N. Plataniotis Alain Tremeau, Shoji Tominaga, “Color in
image and video processing: Most recent trends and future research
directions”, pages 1-26, 2008.
[2] Marian Bakos, “Active contours and their utilization at image
segmentation”, pages 17-21, 2007.
[3] David Boen, “Seeded region growing”, 2004.
[4] David Boen, “Segmenting 2d ultrasound images using seeded region
growing”, 2006.
[5] T.R.Gopalakrishnan Nair Harikrishna Rai G.N. Gradient based seeded
region grow method for ct angiographic image segmentation. 2011.
[6] R.K.Krishna2 Shilpa Kamdi1. Image segmentation and region growing
algorithm. pages 103-107.
[7] Sunday O.Ojo Tranos Zuva, Oludayo O. Olugbara and Seleman M.
Ngwira. Image segmentation, available techniques, developments and
open issues. pages 20-29, 3, March 2011.
[8] Kshitij Pawar & S.S Rathod Vikramaditya Dangi, Amol Parab. Image
processing based intelligent traffic controller. pages 13-17, 2012.
[9] Yu-Hsiang Wang. Image segmentation. January, 2010.
[10] XIN GAO 2 YING YANG 1, 2. Image segmentation using edgeowdriven
geometric snake. pages 505-509, 2007.
[11] B.S.Manjunath Yining Deng and Hyundoo Shin. Halftone visual
cryptography. Trans.Img.Proc., August 2006.
Savneet Dhaliwal et.al.
2817
www.ijcsmr.org