期刊名称：International Journal of Signal Processing, Image Processing and Pattern Recognition
印刷版ISSN：2005-4254
出版年度：2016
卷号：9
期号：10
页码：11-20
出版社：SERSC
摘要：The analysis of MRI images is a manual process carried by experts which need to be automated to accurately classify the normal and abnormalimages.We have proposed a reduced,three stagedmodel havingpre-processing, feature extraction and classificationsteps. In preprocessing the noise has beenremoved from grayscale imagesusingamedian filter,andthengrayscale images havebeenconverted to color (RGB)images. In feature extraction,red,green and blue channelsfrom each channel of the RGB has been extracted because they areso much informativeand easier to process. The first three color moments mean,variance,and skewness are calculated for eachred,green and blue channel ofimages. The features extracted inthefeature extraction stage are classifiedinto normal and abnormalwith K-Nearest Neighbors(k-NN).This method is applied to 100 images (70 normal, 30abnormal). The proposed method gives 98.00%training and 95.00%testaccuracy with datasetsof normal images and100%training and 90.00%testaccuracywithabnormal images. The average computation time for each image was.06s.
