Professional Documents
Culture Documents
Abstract – In this paper a novel algorithm for image model-based methods, edge-based technique,
segmentation has been proposed based on active region-based methods, watershed technique and
contour model and level set. In this we use the signed active contour methods.
pressure force function using local information of the
image to be segmented. First the level set function is II.ACTIVE CONTOUR MODEL
selectively penalised to be binary n then a Gaussian
kernel is applied for smoothing. Thus, this model can
We have used the active contour model in oyr
work with heterogeneous images. In addition, by paper for the segmentation process. In this
taking the advantages of Geodesic active contour technique the user suggest an initial contour. This
(GAC) and Chan-Vese (C-V) model, the method framework attempts to minimize an energy
could deal with objects even with discrete blur associated to the current contour as a sum of an
boundaries and gives exact results in detecting object internal and external energy:
boundaries. One of its other advantages over C-V
method is that the cost of re initialisation is also
reduced in this method as we do not need re-
initialisation of the level set function. Experimental The external energy is supposed to be minimal
results demonstrate that the proposed model is when the snake is at the object boundary position.
effective in segmenting biomedical images and the
The internal energy is supposed to be minimal
images with blur and weak edges.
when the snake has a shape which is supposed to be
Keywords: Image Segmentation, Active Contours, relevant considering the shape of the sought object
Snakes, Level Sets, GAC, C-V method. [1][2].
Snakes are autonomous and self-adapting in their Snakes is the classical model in active contour
search for a minimal energy state. They can be method [1], [3]. It gives an efficient framework for
easily manipulated using external image forces. image segmentation, but it cannot change the
They can be made sensitive to image scale by topology in the process of segmentation process.
incorporating Gaussian smoothing in the image To overcome this drawback, the level set method
energy function. They can be used to track dynamic was proposed in order to isolate shapes from their
objects in temporal as well as the spatial background. Since then, the active contour with
dimensions. But some of the drawbacks are that level set methods has been widely applied to image
they can often get stuck in local minima states; this segmentation in the fields of computer vision and
may be overcome by using simulated annealing image processing. GAC is an edge based active
techniques at the expense of longer computation contour model that works well when the objects
times. They often overlook minute features in the and background in segmented image are
process of minimizing the energy over the entire heterogeneous, but we cannot get satisfied results
path of their contours. when dealing with object with discrete/ blur
boundaries or noise. Whereas Chen-Vese (C-V)
B. Geometric active contours model is a region-based active contour models,
which instead of using the image gradient, use the
Geometric active contours attempt to segment an statistical information inside and outside the initial
object based on its edges, in a level-set framework curve to evolve the contour towards the boundary
[4]. The initial contour is chosen to include the of desired object. It give better performance while
object. The contour evolves according to compared with the edge-based model such as the
ability to work well with the object having
blur/weak boundary, and less sensitive to the initial
position of the contour. In order to get the
Where is a function which should advantages of both GAC and C-V model, some
drop to zero at edges. The contour evolution tends hybrid model are proposed. Recently, Zhang [12]
to smooth the contour, if no other information is proposed the sign pressure force in an active
available. The contour according to this evolution contour model. This model takes the advantages of
will shrink to a point. Hence, a balloon force may GAC and C-V models and could optionally select
be added local or global segmentation.
∫ (| ( )|)| | 10)
√| |
where g is the ESF. The corresponding level set
The functional state that curves segmenting the formulation for GAC is given as:
object should try and surround it with a minimal
weighted arc length. This can be given a physical
interpretation: We are looking for the trajectory of | |
a particle on a map, where the potential energy at
where is a real constant called balloon force to is the dirac function. The regularised version is
control the expanding and velocity, к is the selected as follows:
euclidean curvature of curve C, and g is the edge
based function. ( ( ))
{
B. C-V Model
( )
Chan and Vese proposed an active contour without
edges that can be seen as a special case of IV. HYBRID MODEL
Munford-Shah problem. This model utilizes the
homogeneity information of the object as a term in In our hybrid model first of all we calculate the
the energy function unlike the GAC model which SPF (Signed Pressure Force) function. Its value
relies on the image gradient. In this method the always lies in the range [-1,1]. It is used to control
image is considered to be including two regions i.e the motion of the contour by modulating the sign of
c1 and c2 inside and outside the curve C the pressure force, so that the contour shrinks when
respectively. For a given model Ω, the C-V model outside and expands when it is inside the region of
is formulated by minimizing the following energy interest.
functional:
( )
∫ | | | |
∫ | | (17)
where c1 and c2 are the average intensities inside The significance of Eq. (17) can be explained as
and outside the contour, respectively. With the follows. Refer to Figure 1, we assume that the
level set method we assume intensities inside and outside the object are
homogeneous. It is intuitive that ( )
{ }
and the equal signs cannot be
obtained simultaneously wherever the contour is.
{ }
Hence, there is
{ }
∫ ( )
∫ ( )
[ Fig 1
]
Substituting the SPF function in Eq. (17) for the
where are fixed ESF in Eq. (11), the level set formulation of the
parameters, controls the smoothness of zero level proposed model is as follows:
set, increases the propagation velocity and λ1 and
λ2 controls the image data drive force inside and
( )( ( ) )| |
outside the contour respectively. is the gradient | |
operator. H( ) is the heaviside function and
( ) results on natural image with both the reference
model and the hybrid model.
In the traditional level set methods, the level set
function is initialized to be an SDF to its interface
in order to prevent it from being too steep or flat
near its interface, and re-initialization is required in
the evolution. Unfortunately, many existing re-
initialization methods have an undesirable side
effect of moving the zero level set away from its
interface. Furthermore, it is difficult to decide when
and how to apply the re-initialization. In addition,
re-initialization is a very expensive operation. To
solve these problems, we propose a novel level set
method, which utilizes a Gaussian filter to (a)
regularize the selective binary level set function
after each iteration. The procedure of penalizing
level set function to be binary is optional according
to the desired property of evolution. If we want
local segmentation property, the procedure is
necessary; otherwise, it is unnecessary.
Since we utilize a Gaussian filter to smooth the
level set function to keep the interface regular, the
(b) (c)
regular term | | | | is unnecessary. In
addition, the term in Eq. (19) can also be
removed, because our model utilizes the statistical
information of regions, which has a larger capture
range and capacity of anti-edge leakage. Finally,
the level set formulation of the proposed model can
be written as follows:
(d) (e)
( ) | |
Fig 2.Segmentation results on a natural image, (a)
The main procedures of the proposed algorithm are original image (b) & (c) results by the reference
summarized as follows: model after 200 and 500 iterations respectively, (d)
& (e) results from the hybrid model after 100 and
1.Initialize the level set function / as 200 iterations.