Research Article
Classification of Wheat Species Using Convolutional Neural Networks: A Comparative Study
@INPROCEEDINGS{10.1007/978-3-031-72393-3_1, author={Piotr A. Kowalski and Ernest Jeczmionek and Malgorzata Charytanowicz and Szymon Łukasik and Jerzy Niewczas and Piotr Kulczycki}, title={Classification of Wheat Species Using Convolutional Neural Networks: A Comparative Study}, proceedings={Future Access Enablers for Ubiquitous and Intelligent Infrastructures. 8th EAI International Conference, FABULOUS 2024, Zagreb, Croatia, May 9--10, 2024, Proceedings}, proceedings_a={FABULOUS}, year={2024}, month={10}, keywords={data set algorithm validation deep learning convolutional neural network prediction ability benchmark}, doi={10.1007/978-3-031-72393-3_1} }- Piotr A. Kowalski
Ernest Jeczmionek
Malgorzata Charytanowicz
Szymon Łukasik
Jerzy Niewczas
Piotr Kulczycki
Year: 2024
Classification of Wheat Species Using Convolutional Neural Networks: A Comparative Study
FABULOUS
Springer
DOI: 10.1007/978-3-031-72393-3_1
Abstract
This paper introduces a novel image dataset tailored for evaluating machine learning solutions, particularly focusing on deep neural networks. Derived from X-ray images of wheat grains, the dataset encompasses three distinct species: Kama, Rosa, and Canadian. We provide a comprehensive overview of the dataset’s structure and conduct experiments using ten pretrained deep neural networks to classify wheat species. TheSeeds ImageData Set offers a competitive alternative to established object recognition benchmarks such as CIFAR-10, CIFAR-100, SVHN, and ImageNet. Its compact size streamlines computational processes, making it an efficient resource for exploratory data analysis. The dataset will be publicly available, serving as a foundational resource for future research endeavors in the field.
