k-NN Based Classification of Brain MRI Images using DWT and PCA to Detect Different Types of Brain Tumour

The treatment of any tumour is completely depended what type it is. This paper proposes a set of algorithms which work for the better detection and classification of brain tumour. The MRI image based brain tumour analysis would efficiently deal with classification process for brain tumour analysis. The proposal suggests using three stages namely feature extraction, feature reduction and classification. The discrete wavelet transformation methods (DWT) and principal component analysis (PCA) are used for feature extraction and feature reduction respectively. The k-Nearest Neighbours (k-NN) classifier is used for the classification of the tumour and to tell what type the tumour is Benign or Malignant. By using different methods for feature extraction, feature reduction and classification techniques to extract and calculate the average values of the features of the MRI image and to match the values to the values extracted from the set of input image and classify them to be benign or malignant.