Most methods for automated full-bore rock core image analysis (description, colour, properties distribution, etc.) are based on separate core column analyses. The core is usually imaged in a box because of the significant amount of time taken to get an image for each core column. The work presents an innovative method and algorithm for core columns extraction from core boxes. The conditions for core boxes imaging may differ tremendously. Such differences are disastrous for machine learning algorithms which need a large dataset describing all possible data variations. Still, such images have some standard features - a box and core. Thus, we can emulate different environments with a unique augmentation described in this work. It is called template-like augmentation (TLA). The method is described and tested on various environments, and results are compared on an algorithm trained on both 'traditional' data and a mix of traditional and TLA data. The algorithm trained with TLA data provides better metrics and can detect core on most new images, unlike the algorithm trained on data without TLA. The algorithm for core column extraction implemented in an automated core description system speeds up the core box processing by a factor of 20.
@article{arxiv.2204.08853,
title = {Core Box Image Recognition and its Improvement with a New Augmentation Technique},
author = {E. E. Baraboshkin and A. E. Demidov and D. M. Orlov and D. A. Koroteev},
journal= {arXiv preprint arXiv:2204.08853},
year = {2022}
}
Comments
20 pages, 16 figures, 1 table, the augmentation pipeline code samples published as Open-Source code for TLA at https://github.com/BEEugene/TemplateArtification/, continue of the research from arXiv:1909.10227