Lung Cancer Image- Feature Extraction and Classification using GLCM and SVM Classifier
Lung cancer is the second most causing cancer when compared to all the other cancers. According to WHO (World Health Organization) lung cancer contributes about 14 per cent among all the cancers. Therefore, early detection and treatment is very much required. Now-a- days, image processing techniques are playing a major role in early detection of disease which is very helpful in further treatment stages. These techniques help in detecting the abnormality of the tissues-tumor in target cancer images. In this research, the proposed methodology is majorly carried out in five phases. In phase one lung cancer and non-lung cancer, images are collected from the lung cancer database. In phase two preprocessing is done by using the Median filter. Median filter is chosen as it preserves the edges i.e, sharp features are preserved. In Phase three, segmentation of the target image is done using Fuzzy C Means. Fuzzy C Means Clustering is chosen as it gives better performance than K-means Clustering. In phase four, the features are extracted using GLCM (Gray Level Co-occurrence Matrix). GLCM have high discrimination accuracy and less computational speed. In phase five, these extracted features are given to SVM classifier for classification of lung cancer from normal lung. The SVM classier achieved accuracy of 96.7% for detecting and classification of lung cancer.