Abstract:
This research work is industry sponsored and carried out in collaboration with Tata
Steel, India. Its objective is to alleviate a bottleneck in the steel manufacturing
pipeline by the application of automated coal petrography. The problem can be
de ned as generating semantic segmentation of microscopic coal petrography images.
We are presented with a heavily imbalanced and weakly labelled dataset having major
intensity based interclass confusion.
We have attempted to solve this challenging problem by adopting a deep learning ap-
proach to do away with the painful feature engineering process that is often a necessity
in classical machine learning. The segmentation task is approached as a pixel level
multiclass classi cation problem. Our novel solution uses ve binary U-Net classi ers
in accordance with the One-vs-All approach to multiclass classi cation. These binary
classi ers are trained using loss functions having additional regularization terms that
we have developed in order to handle the interclass confusion problem. These regu-
larizers have succesfully resolved majority of this confusion. The result obtained by
amalgating the output of the binary classi ers is termed as coarse-segmentation and it
su ers from both unclassi ed and misclassi ed pixels. These errors are corrected us-
ing a post processing module having four self-developed image processing algorithms
and a ne-segmentation is obtained as the nal result. Our solution's performance is
benchmarked against two previous approaches based on a Miminum Distance Clas-
si er and a Random Forest Classi er. Our method creates superior segmentations
that have greater visual appeal and are more accurate. All experimental results are
included to support our claim. It was also observed that our results were nearest
to those obtained from the current, non-automated standard procedure used in the
industry at present.
