Classification of Tumors in Human Brain MRI using Wavelet and Support Vector Machine
Journal Title: IOSR Journals (IOSR Journal of Computer Engineering) - Year 2012, Vol 8, Issue 2
Abstract
The task of classification in recovery systems is to differentiate between normal and abnormal brain. In this paper feature extraction from MR Images is carried out by DAUB-4 Wavelet method. DAUB-4 is an efficient tool for feature extraction because it gives better contrast to an image. Due to better contrast it improves easily hanging signals of an image and reduces the overhead. PCA is used to select the best features for classification. These PCA selected features are given as an input to SVM for classification. In this work we are using two SVM kernel functions which are Linear Kernel and Radial Basis Kernel. Experimental results show that the proposed system have high classification accuracy of 98.7% with Radial Basis Kernel
Authors and Affiliations
Mubashir Ahmad
Keywords
Related Articles
- EP ID EP93396
- DOI -
- Views 117
- Downloads 0
Comparative analysis of Stegnography Algorithms on the Basis of PSNR value & cover file size
Abstract: With the rapid growth in the field of technology, there is always a requirement of development of fast and secure algorithms. Steganography is used to provide confidentiality over the transmitted data or...
An Optimal Approach to derive Disjunctive Positive and Negative Rules from Association Rule Mining using Genetic Algorithm
Mining frequent itemsets and association rules is a popular and well researched approach for discovering interesting relationships between variables in large databases. Association rule mining is one of the  ...
An innovative scheme for representation of signed numbers employing ternary logic and method of development of semiconductor optical amplifiers based wavelength encoded optical ternary half adder
Abstract: In binary logic, two different logical states are used to represent signed as well as unsigned numbers. In case of signed numbers one bit, usually the Most Significant Bit is solely devoted to represent the sig...
Optimizing Migration of the Application Data in Cloud Environment Using ACO Algorithm and RSA Encryption
Abstract: Taking the advantages of the capabilities offered by cloud computing requires either an application to be built especially for it, or for existing application to migrated to it. The main focus on migrate the ap...
Detection of Cancer in Pap smear Cytological Images Using Bag of Texture Features
We present a visual dictionary based method for content based image retrieval in cervical microscopy images using texture features. The nucleus region in each image is identified by a simple and reliable se...