2. • The process partitioning a digital image into multiple
regions (set of pixels).
• The partitions are different objects in image which have
the same texture or colour.
• The result of the image segmentation is a set of regions
that collectively cover the entire image.
• All of the pixels in a region are similar with respect to
some characteristics such as colour, intensity, or texture.
3.
4. Industrial inspection
Optical character recognition (OCR)
Tracking of objects in a sequence of images
Classification of terrains visible in satellite images.
Detection and measurement of bone,tissue, etc. in medical images
Detection of Pest in images
7. In this method threshold value
is given manually and value is
fixed one.
Case A: The image is composed of one light object
on a dark
background, in such a way that object and
background pixels
have gray levels grouped into two dominant modes.
Case B: Two types of light objects on a dark
background.
8. In this method threshold value for segmentation is calculated using
iterative method.
Steps
1. Select an initial estimate for T.
2. Segment the image using T. This will produce two groups of pixels: G1
consisting of all pixels with gray level values > T and G2 consisting of
pixels with gray level values <=T.
3. Compute the average gray levels μ1 and μ 2 for the pixels in regions G1
and G2.
4. Compute a new threshold value: T = (μ1+μ2)/2.
5. Repeat step 2 through 4 until the difference in Ts in successive iterations is
smaller than a predefined parameter T0.
9. • Clustering can be thought of as a form of data compression , where a large
number of samples are converted into a small number of representative
prototypes or clusters.
The partition should have two properties:
1. Homogeneity inside clusters (the data which belong to one cluster should be as
similar as possible).
Heterogeneity between the clusters (the data which belong to different clusters
should be as different as possible).
• The main idea behind fuzzy clustering is that an object can belong to more than
one class and does so to varying degrees called memberships.
10. • The fuzzy c means algorithm is an iterative method, which tries to separate the set X
into C compact clusters.
• Fuzzy c-means (FCM) is a method of clustering which allows one piece of data to
belong to two or more clusters.
• The algorithm is based on minimization of the following function
• where m is any real number greater than 1,
• uij is the degree of membership of xi in the cluster j,
• xi is the ith of dimensional measured data,
• cj is the d-dimension center of the cluster,
• and ||*|| is any norm expressing the similarity between any measured data and the
center
11. • This algorithm (Bezdek, J. C. 1981) realizes an iterative optimization.
• Algorithm-
The algorithm is composed of the following steps:
1. Initialize U=[uij] matrix, U(0)
2. At k-step: calculate the centers vectors C(k)=[cj] with U(k)
3. Update U(k) , U(k+1)
4. If || U(k+1) - U(k)||< ε then STOP where ε is a number
between 0 and 1; otherwise return to step 2
12.
13. A . Energy
The gray level energy [9] indicates how the gray levels are distributed. It is
formulated as
Where E(x) represents the gray level energy with 256 bins and p(i) represents the
probability distribution functions.
B. Entropy
The entropy is the measure of image information content, which is interpreted as
the average uncertainty of information source. It is
calculated as the summation of the products of the probability of outcome
multiplied by the log of the inverse of the outcome probability.
14. It is formulated as
C. Normalized Mutual Information
It is the measure of covering contents from both discrete entropies and mutual information
16. Disadvantages of FCM means algo-
Before performing the algorithm, an assumption of the number of clusters has to be made
in advance.
may often lead to local minima solutions, and hence misdiagnosis could occur.
Simulated Annealing (SA) [2] is an intelligence searching algorithm proposed by
Kirkpatrick, It is proofed that this algorithm is convergence to global optimization in
probability one. It adopts Metropolis acceptance criteria and a serial of parameters called
cooling schedule to control the process of simulate annealing to get an approximate global
optimization within a polynomial time.
17. s ← s0; e ← E(s) // Initial
state, energy.
sbest ← s; ebest ← e // Initial
"best" solution
k ← 0 // Energy evaluation
count.
while k < kmax and e > emax //
While time left & not good
enough:
snew ← neighbour(s) // Pick some
neighbour.
enew ← E(snew) // Compute its
energy.
if enew < ebest then // Is this
a new best?
sbest ← snew; ebest ← enew //
Save 'new neighbour' to 'best
found'.
if P(e, enew, temp(k/kmax)) >
random() then // Should we move
to it?
s ← snew; e ← enew // Yes,
change state.
k ← k + 1 // One more evaluation
done
return sbest // Return the best
solution found.
Simulated annealing
Algorithm
19. Image segmentation is the most practical approach among virtually all automated
image recognition systems. The performance of an image segmentation algorithm
depends on its simplification of image. The different segmentation algorithms
namely, fixed threshold, Iteration method, and fuzzy c-means segmentation are
implemented for pest images and they are compared using nonlinear assessment or
the quantitative measures like gray level energy, entropy, and normalized mutual
information. The non-linear objective assessment used to evaluate the different
segmentation techniques. After evaluation it is concluded that fuzzy c means
cluster which gives less value of Normalized Mutual Information (NMI) and
Entropy which is most suited for pest image segmentation. At the same time
gray level energy gives better performance related to Entropy and Normalized
Mutual Information.
20. [1] Xiao-Ying Wang, Jonathan M. Garibaldi, “Simulated Annealing Fuzzy Clustering in
Cancer Diagnosis”, Automated Scheduling, Optimisation and Planning (ASAP)
Research Group, Issue-8, August 2004
[2] Pravin kumar.S.K1, Dr.M.G.Sumithra2,Prof.P.Saranya,” Design and Development
of Pest Image Segmentation Technique Using Soft computing Algorithm”,
International Journal of Soft Computing and Engineering (IJSCE) ISSN: 2231-2307,
Volume: 2 Issue: 2 25-Oct-2014,ISSN_NO: 2347 -7210
[3] Xiaojun Qi,” Image Segmentation” .
[4] Navkirat Kaur, V. K. Banga,” Color Image Segmentation Using Soft Computing”
[5]Binamrata Baral, Sandeep Gonnade, Toran Verma,“Image Segmentation and
Various Segmentation Techniques – A Review”, International Journal of Soft
Computing and Engineering (IJSCE) ISSN: 2231-2307, Volume-4, Issue-1, March
2014