Application of Optimization Techniques on Brain MRI for Abnormal Intrusion Detection
Amita Kumari
Amita Kumari, ME Student, Department of ECE, NITTTR,Chandigarh, India.
Manuscript received on July 19, 2014. | Revised Manuscript received on July 20, 2014. | Manuscript published on July 25, 2014. | PP:16-19 | Volume-2 Issue-9, July 2014. | Retrieval Number: I0779072914/2014©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Brain neoplasm/tumor is defined as any abnormal growth of cells in the brain. Basically brain tumors have variety of shapes and sizes. It can occur at any location and in different intensities. It can be Benign and Malignant. Benign tumor is not cancerous. So different techniques are used to solve the problem Clustering aims at representing large datasets by a fewer no. of prototypes or clusters. It brings simplicity in modeling the data and thus plays a central role in the process of knowledge discovery and data mining. In this method a hybrid approach for classification of brain tissue in MRI based on Particle Swarm Optimization (PSO) and Support Vector Machine (SVM) wavelet based texture feature are extracted from normal and tumor region by using HAAR wavelet. These features are given as input to the SVM classifier which classified them into normal & abnormal brain neoplasm. The algorithm incorporates steps for pre-processing, image segmentation and image classification using SVM classifier.
Keywords: AIS, ACO, PSO, SVM, SI, HAAR wavelet