Recognition of Rare Microfossils Using Transfer Learning and Deep Residual Networks

Simple Summary The collection of early Cambrian microfossils leads to the amassing of a pile of thousands of tiny tubes, grains and various fragments. Rare type of microfossils with high academic value are mingled with numerous ordinary fossils and the traditional way of manual selection is very inefficient. Many artificial intelligence (AI) technologies have already been applied in fossil image recognition, but current methods largely depend on a great number of fossil images to "train" the AI model. However, usually only a handful of samples are available for specific rare fossil taxa and these cannot provide enough photos for AI. In this study, we fine-tuned a new convolutional neural network, combining pre-trained models from a nature image database to solve the problem of the lack of training materials. Through many tests, this new model was proved valid. It presented relatively high accuracies in recognizing specific micro fossil taxa, while the required number of corresponding fossil images is very low. Various microfossils from the early Cambrian provide crucial clues for understanding the Cambrian explosion and the origin of animal phyla. However, specimens with important anatomical structures are extremely rare and the efficiency of retrieving such fossils by traditional manual selection under a microscope is quite low. Such a contradiction has hindered breakthroughs in micropaleontology for a long time. Here, we propose a solution for identifying specific taxa of Cambrian microfossils using only a few available specimens by transferring a model pre-trained on natural image datasets to the field of paleontological artificial intelligence. The method employs a 34-layer deep residual neural network as the underlying framework, migrates the ImageNet pre-trained model, freezes the low-layer network parameters and retrains the high-layer parameters to build a microfossil image recognition model. We built training sets with randomly selected images of varied number for each taxon. Our experiments show that the average recognition accuracy for specific taxa of Cambrian microfossils (50 images for each taxon) is higher than 0.97 and it can reach 0.85 with only three training samples per taxon. Comparative analyses indicate that our results are much better than those of various prevalent methods, such as the transpose convolutional neural network (TCNN). This demonstrates the feasibility of using natural images (ImageNet) for the training of microfossil recognition models and provides a promising tool for the discovery of rare fossils.