Using deep learning for automatic detection and segmentation of carbonate microtextures

The difficulties involved in studying micrometer-sized micrite crystals, and quantifying the associated impact on large scale geophysical properties, have long hindered our society’s understanding of both Middle Eastern and global microporous limestones. Instance segmentation procedures, from the field of deep learning, offer the ability to identify at a pixel-level each individual crystal within an SEM image, allowing for automated morphological analysis. We illustrate how the common Masked Region-based Convolution Neural Network from computer vision can be adapted to the task of identifying individual micrite crystal within gray-scale SEM images. Leveraging Transfer Learning, the ResNet50 neural architecture is used with weights initialized through a pre-training on Microsoft’s Common Objects in COntext (COCO) dataset. The resulting model accurately detects and separates a number of crystals observed within different SEM images. However the trained model is also shown to be highly susceptible to noise introduced as part of the imaging procedure, for example charging noise. Future work will aim to make the procedure more robust, reducing the impact of noise by adapting the pre-processing workflow and incorporating more noisy images into the training dataset.