Core Box Image Recognition and its Improvement with a New Augmentation Technique

TL;DR

This paper introduces a novel template-like augmentation technique to improve machine learning-based core box image recognition, significantly enhancing detection accuracy across diverse imaging conditions.

Contribution

The work presents a new augmentation method (TLA) for core box images, improving robustness and detection performance in varied environments compared to traditional training.

Findings

TLA improves detection metrics across different imaging conditions.

Training with TLA data enhances the model's ability to detect cores in new images.

The automated system speeds up core box processing by 20 times.

Abstract

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.