IJSRD - International Journal for Scientific Research & Development| Vol. 5, Issue 03, 2017 | ISSN (online): 2321-0613

Lung cancer is the leading cancer among both men and women. A quality preprocessing technique is necessary to ensure effective removal of noise that interferes with the features of the image and hence improves lung cancer detection rate and accuracy. In this proposed research, we will extract basic Geometric Features from Lang DICOM as well as JPEG image Format and Based on Random Forest Classifier and Features Extracted for nodule classification as benign, malignant or normal. Random forest classifier gives better accuracy for identification and classification rather than other classifier such as KNN, ANN and MSVM. Experimental results based on data from Collected from lung LIDC image database.