A Spatial Clustering Method with Edge Weighting for Image Segmentation

overratedbeltΤεχνίτη Νοημοσύνη και Ρομποτική

25 Νοε 2013 (πριν από 3 χρόνια και 10 μήνες)

87 εμφανίσεις

A Spatial Clustering Method with Edge
Weighting for Image Segmentation

Abstract:


The determination of flame or fire edges is the process of
identifying a boundary between the area where there is
thermo chemical

reaction and those without. It is a precursor to image
-
based flame
monitoring, early fire detection, fire evaluation, and the determination of
flame and fire parameters. Several traditional edge
-
detection methods
have been tested to identify flame edges,
but the results achieved have
been disappointing. Some research works related to flame and fire edge
detection were reported for different applications; however, the methods
do not emphasize the continuity and clarity of the flame and fire edges.




A computing algorithm is thus proposed to define flame and fire edges
clearly and continuously. The algorithm detects the coarse and
superfluous edges in a flame/fire image first and then identifies the
edges of the flame/fire and removes th
e irrelevant artifacts. The
auto
adaptive

feature of the algorithm ensures that the primary symbolic
flame/fire edges are identified for different scenarios. Experimental
results for different flame images and video frames proved the
effectiveness and robu
stness of the algorithm.




Hardware Requirements
:
-



SYSTEM




:Pentium IV 2.4 GHz



HARD DISK


: 40 GB



R
AM



: 256 MB


Software Requirements
:
-



Operating system

:

Windows XP Professional



IDE




:

Microsoft Visual Studio .Net 2005



Coding Language

:
C#.net 2005.


Existing System:
-




The thresholds play an important role which used in the image
edge
detection.

The

edge is not only the basic feature of an image
but also the basis of shape quality analysis.



Self
-
adaptive Threshold Based on Otsu
-
There
are lots of image
segmentation methods based on

gray
-
scale histogram

Otsu method
was also used in edge detections to get the high threshold



In this Technique quality of the image is poor and doesn’t validate
the surroundings

Proposed System:
-



A computing
algorithm is thus proposed to define flame and fire
edges clearly and continuously
.



The
auto adaptive

feature of the algorithm ensures that the primary
symbolic flame/fire edges are identified for different
scenarios.
Experimental

results for different flame images and video frames

proved the effectiveness and robustness of the algorithm
.



The main idea of the method consists of focusing on the edge
intensities of sample points and the
similarity of

geometry features
of sample point
s. Using the
Eigen

analysis of normal voting tensor,
with every point of PSG, an
edge intensity

is associated by which
the PSG is decomposed into two components, one for the strong
edge intensity and another for the

non
-
strong edge intensity.



It is desirab
le to develop a dedicated edge detection method for
flame and fire image processing.
Accordingly, a

new computing
algorithm is proposed in this paper to

Process

a combustion image and to identify flame/fire edges.



By providing experimental results and comp
arisons, we
demonstrate an algorithm that

can

achieve a high
-
quality simplification result
while efficiently

preserving the features. An interesting direction
for future

research
is to apply our adaptive mean
-
shift
procedure to

segmentation and
curve
-
skeleton extraction of PSG.