# Construction of GAN‐RES and Its Application to Small Sample Fusulinid Fossil Recognition

## TL;DR

This paper introduces a new method using GAN and neural networks to improve fossil recognition when only a few samples are available.

## Contribution

The novel approach combines GAN with ResNet50 and custom CNN to enhance small fossil datasets and improve recognition accuracy.

## Key findings

- The method achieved 93% accuracy in 100 epochs for rare fossil recognition.
- GAN-based data expansion outperformed traditional data augmentation methods.
- The model shows significant improvement in identifying fossils with limited samples.

## Abstract

Traditional fossil identification relies on the rich experience and knowledge of paleontologists, and existing intelligent identification methods mainly rely on deep learning to train on a large number of fossil graphic samples to achieve a high degree of precision. In order to solve the above problems and still be able to accurately recognize small samples of rare fossils, we try to use the generative adversarial network (GAN) combined with ResNet50, EfficientNet, and customized CNN architectures, which are applied to the identification of small samples of fossils. First of all, the generator of GAN is fully trained, using it to generate a large number of samples to expand the dataset, enriching the image features extracted by the model, and then through the neural network to analyze the image abstraction computation, and finally, the best fossil identification model is trained through multiple iterations. Using the method of this paper on the same dataset with a data enhancement method for comparison experiments, the experimental results show that the accuracy rate reaches 93% in the case of epochs 100, higher than the other experimental results, and has a significant advantage in the recognition of fossils with scarce samples.

Expanding the dataset using generative adversarial network (GAN) coupled with neural networks to identify small samples of rare fossils.