project reviewppt
DESCRIPTION
image processingTRANSCRIPT
Detection of Brain Tumor Using Segmentation based Encryption for
MRI images
Guide: Dr.S.Nirmala Devi
T.Arumugasamy
Reg. No: 2010278001
06th Semester, ME - Medical Electronics (SS PT)
Objective
To detect the Brain tumor in MRI image. Tumor area consider as ROI and rest of the area consider as RONI.
To secure the transmitted data (Medical image) among the medical centers for telemedicine in the health care.
Literature Survey
Year Author Paper Title
2012 Ajala Funmilola A, Oke O.A, Et al
Fuzzy k-c-means Clustering Algorithm for Medical Image Segmentation
2012 M.C.Jobin Christ, Dr.R.M.S.Parvathi
Medical Image Segmentation Using Fuzzy C-means Clustering And Marker Controlled Watershed
Algorithm
2010 Vasant Manohar, Yuhua GuMRI Segmentation Using Fuzzy C-Means and Finite
Gaussian Mixture Model
2010 Kuo-Lung Wu Analysis of parameter selections for Fuzzy C-Means
1994Chaur-Heh Hsieh, Chung-Ming Kuo, Chung-Woei
Chao, Po-Chiang Lu
Image Segmentation Based On Fuzzy Clustering Algorithm
Proposed Idea
Introduction
Clustering is one of the most fundamental issues in pattern recognition.
It plays a key role in searching for structures in data.
Fuzzy C-Means Clustering
Fuzzy C-Means (FCM) is a method of clustering which allows one piece of data to belong to two or more clusters.
This method (developed by Dunn in 1973 and improved by Bezdek in 1981) is frequently used in pattern recognition.
Fuzzy C-Means Clustering
Fuzzy C-Means Clustering(FCM), is also known as Fuzzy
ISODATA.
The FCM employs fuzzy partitioning such that a data
point can belong to all groups with different membership
grades between 0 and 1.
FCM is an iterative algorithm. The aim of FCM is to find
cluster centers (centroids) that minimize a dissimilarity
function.
Fuzzy C-Means Clustering
Fuzzy C-Means Clustering
This algorithm is based upon iterative optimization of the objective function, with update of membership and cluster centers.
This is based upon initial membership matrix for each item in a cluster.
Center of clusters are calculated based upon the membership function.
Once the centers are determined the membership matrix is updated
When the difference between two sequential membership matrix is less than the initial termination criterion the algorithm is stopped. Otherwise step 2 and 3 are repeated.
Fuzzy C - Means : Flow chart
Input Image
No of Clusters
Initialize Partition Matrix
Find Membership matrix
Find the center Values
If Obj fun diff b/w two iteration is min End
No
Yes
Distance b/w data and centers
Find objective function
Update Membership
values
Image encryption & decryption
Encryption and decryption are both methods used to ensure the secure passing of messages and other sensitive documents and information.
Encryption basically means to convert the message into code or scrambled form, so that anybody who does not have the 'key' to unscramble the code, cannot view it.
A key is the actual 'described method' that was used to scramble the data, and hence the key can also unscramble the data.
Image decryption
When the data is unscrambled by the use of
a key, that is what is known as 'decryption'.
It is the opposite of encryption and the
'described method' of scrambling is basically
applied in reverse, so as to unscramble it.
Hence, the jumbled and unreadable text
becomes readable once again.
Segmented image
Encrypted image