Friction stir welding is a solid-state joining process to join similar or dissimilar metals, which uses the friction developed between the metals to join them. Friction stir welding is an efficient way to join the metals but the welding defects are a little difficult to find through naked eyes. Hence, there is a chance of it being unnoticed even in final inspection in industries. So the welded joints are inspected by machine vision, using camera and an intelligent system. After obtaining the images of the welded joints and processing them using MATLAB, they are differentiated according to the various defects in them, using machine learning technique. For this, the statistical features of the image are extracted and they are classified into different defects using classifiers like Decision Trees, Discriminant Analysis, Support Vector Machine and Nearest Neighbour. © 2021 Institute of Physics Publishing. All rights reserved.