Image classification using texture features has been increased the success rate and texture-based classification very useful in identification of abnormal and normal tissues images. In this paper, analyze first-order statistical features and Segmentation-based fractal texture analysis (SFTA) features-based classification of MRI images using K-Nearest Neighbor (KNN) classifier. The performance of KNN classifier is compared to various distance metrics like Euclidean, City block, Correlation and Cosine. The classification results show that first-order statistical features produce better classification accuracy than segmentation-based fractal texture analysis. The KNN classifier with Euclidean distance yields better classifier accuracy compare to other distance metrics.
CITATION STYLE
Ganesan, K., & Rajaguru, H. (2019). Performance analysis of KNN classifier with various distance metrics method for MRI images. In Advances in Intelligent Systems and Computing (Vol. 900, pp. 673–682). Springer Verlag. https://doi.org/10.1007/978-981-13-3600-3_64
Mendeley helps you to discover research relevant for your work.