cores (Wittchen et al., (2020). In the oil and gas industry, Guisiano et al. (2023) applied YOLOv8 for infrastructure identification. These architectures, CNNs and Transformers, have shown significant potential in automating the analysis of rock thin sections, considering challenges such as data availability and the required computational capacity. 2. OBJECTIVES AND SCOPE This research aims to implement Detectron2 and scikit-image to identify and measure minerals in thin sections of intrusive igneous rocks by generating a labeled image dataset for training, validation, and evaluation of the model, and developing a web application that allows external users to perform automated petrographic analyses within an AI and data-driven analytical workflow. 2. METHODOLOGY The identification and measurement of minerals on rock thin sections images can be automated using a deep learning workflow. Figure 1 illustrates the methodology, which consists of two main stages. The first stage focuses on data handling, while the second involves the AI model development. Figure 1 – Workflow for mineral identification and measurement using Deep Learning 2.1 Dataset creation Deep Learning relies on data. Several open-access online sources provide images of rock thin sections. Paucar et al. (2025) accessed platforms such as Virtual Microscope-The Open University (s.f.) and Britrocks-British Geological Survey (BGS) (2025), which host large image repositories. Using ShareX software, 80 images were collected, 40 in PPL and 40 in XPL, from five rock types: diorite, gabbro, granite, granodiorite, and syenite. In total, 400 images of 960 × 600 px in PNG (RGB) format were collected for the training and validation sets, along with an additional set of 20 images for evaluation. 2.2 Dataset preparation The BGS images present an overlap issue between PPL and XPL. To address this, the images were cropped so that all have dimensions of 900 × 540 px and were exported in JPG (RGB) format to reduce file size. This process was carried out using the trial version of Photoshop. The minerals were labeled using Roboflow, a platform that also allows the dataset to be split into training, validation, and evaluation subsets, as well as the application of data augmentation techniques (flipping, rotation, shearing, etc.).
RkJQdWJsaXNoZXIy MTM0Mzk2