Butterfly and Moth Image Recognition Based on Residual Neural Network

Fengwei Liu

2023

Abstract

Image recognition is presently a central area of study within the machine learning domain. Convolutional neural networks (CNN) are a special type of artificial network model commonly used for image processing and recognition. The design inspiration for this deep learning model comes from human visual recognition systems, whose core idea is to use convolution operations to extract features from images. Then the network utilizes a series of different functional hidden layers to ultimately recognize and classify the input image data. This article constructs a deep CNN model utilizing the ResNet50 for image recognition and classification on a dataset containing butterfly and moth images, and analyzes the classification results. After 10 epochs, the CNN model demonstrated a 94.3% accuracy rate when applied to the test dataset. According to research findings, the model exhibits commendable accuracy on the dataset. Nevertheless, owing to the limited number of training epochs, the performance on the test set fell short of optimal outcomes. Therefore, augmenting the number of epochs can be a viable approach to enhance the model’s classification accuracy for the dataset.

Paper Citation

in Harvard Style

Liu F. (2023). Butterfly and Moth Image Recognition Based on Residual Neural Network. In Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML; ISBN 978-989-758-705-4, SciTePress, pages 211-217. DOI: 10.5220/0012798500003885

in Bibtex Style

@conference{daml23,
author={Fengwei Liu},
title={Butterfly and Moth Image Recognition Based on Residual Neural Network},
booktitle={Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML},
year={2023},
pages={211-217},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012798500003885},
isbn={978-989-758-705-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Data Analysis and Machine Learning - Volume 1: DAML
TI - Butterfly and Moth Image Recognition Based on Residual Neural Network
SN - 978-989-758-705-4
AU - Liu F.
PY - 2023
SP - 211
EP - 217
DO - 10.5220/0012798500003885
PB - SciTePress