Automatic Defect Detection of Grate Conveyor Using Supervised Classifier

Image classification is widely used for automated visual inspection to detect defects in equipment. This paper presents a machine learning application for detecting defects in a traveling grate conveyor in pelletizing industry and similar industries. First, the image of each grate is extracted from a video stream.Then the image is classified by means of a set of visual primitives, including features from the Hough transform. The detection rate of the proposed method is more than 94.5%.

Keywords:

Machine Learning , Image Processing , Defect Detection