Nowadays, Liver Cancer is spreading silently at an alarming pace since liver disease has a poor survival rate and symptoms do not manifest until cancer has progressed to an advanced stage. If the illness is detected late, the typical individual has only a one-year survival rate. As a result, we propose to diagnose liver cancer via feature extraction and classification. We go through the three detection phases of processing, pre-processing, and detection, then classify the tumours based on the retrieved characteristics for normal and abnormal stages. Three steps comprise the diagnostic method: pre-processing of MRI images, feature extraction, and classification. Following image pre-processing, the picture is segmented using fuzzy C means clustering and a level-set segmenter. Additionally, features are retrieved using the Gray-Level Co-Occurrence Matrix for Texture Analysis (GLCM). Finally, a KNN classifier is used to categorise normal and pathological livers.