Performance Analysis of Machine Learning Based Classifiers for the Diagnosis of Lung Cancer & Comparison Mathews Arun B.1, Jeyakumar M. K.2 1Research Scholar, Department of Computer Science Noorul Islam Centre for Higher Education, Tamil Nadu, India 2Professor, Department of Computer Applications, Noorul Islam Centre for Higher Education, Tamil Nadu, India Online published on 2 February, 2019. Abstract Objective In this paper, diagnosing in premature stages a detection system has been designed which contains the following digital image processing techniques. Analysis Lung cancer is the most injurious form of cancer which affects the human. Lung cancer has quickly increased in western part of the country among the world. Various feature combinations are given as the input to the KNN and ANN classifiers. Method First, dermoscopy image of lung is taken, and it is subjected to the pre-processing step for noise removal and post-processing step for image enhancement. Then the processed image undergoes image segmentation using Otsu method & Morphological processing. Second, features are extracted using feature extraction technique-GLCM, and FOS. Findings KNN classifier is used to classify the data set into two classes. ANN classifier is used to classify the data set based on the number of layers. Performance is analyzed based on the accuracy of the learning classifier output. Result The proposed system defines an effective way to detect the lung lesion more accurately and faster by segmenting the lesions images. Top Keywords Lung Cancer, Otsu, Morphological, Feature extraction, KNN, and ANN. Top |