Identification of living (Rose Bengal) stained benthic foraminifera using automated image recognition

This repository contains the datasets and supporting files used in the study “Identification of benthic foraminifera using automated image recognition.” It includes the image data, training and validation sets, and derived statistics used to develop and evaluate convolutional neural network (CNN) models for the automatic identification of living and dead benthic foraminifera. The datasets originate from low-diversity (Atlantic, MUDSURV project) and high-diversity (Mediterranean, MEDIT) coastal environments.