Machine Learning based Image Processing for Iron Ore Pellet Size Analysis

摘要

Image processing based system have been proposed for size analysis of iron ore pellets in real-time. One such commercial system named as Eye-On-Pellet is introduced by CSIR-IMMT, India which is being used in pelletization industries. Further improvement in this system by using machine learning algorithms is proposed in this paper. Two locations of image capture to derive pellet size information is dealt in this work. Eye-On-Pellet system captures the pellet size information from the disc discharge point which uses traditional image processing algorithms. In addition to this, a new approach is proposed where the image of pellets inside the disc can be used to qualitatively know if the size is small, big or normal using convolutional neural network.