Features Reductions Using Color Moments and Classification of Brain MRI Using K-NN
Main Article Content
Abstract
This research presents an intelligent methodology for classification of brain MRI. Our suggested methodology comprises on four stages, such as pre-processing, feature extraction, feature reduction, and classification. In the first stage, a median filter is applied on brain MRI to remove the noise and then converted this image to RGB. In the second stage, discrete wavelet transform (DWT) is used for feature extraction from the image. However, the number of extracted features is still very high which is further reduced in the third namely feature reduction stage using color moments, which is our main contribution. Finally, in the last stage of methodology, the reduced features are sent to k-Nearest Neighbors (k-NN) to classify the normality and abnormality of brain MRI. The overall accuracy of our suggested method is almost 94.9745%.
Article Details
How to Cite
Ullah, Z., Lee, S.-H., Ahmed Khan, M., Fayaz, M., & Iqbal, M. (2018). Features Reductions Using Color Moments and Classification of Brain MRI Using K-NN. Technical Journal, 23(04), 77-83. Retrieved from https://tj.uettaxila.edu.pk/index.php/technical-journal/article/view/805
Section
COMPUTER SCIENCE
Copyright (c) 2019 Technical Journal
The author transfers all copyright ownership of the manuscript entitled (title of article) to the Technical Journal in the event the work is published.