使用一些卷积神经网络架构进行花粉粒分类

Pollen Grain Classification Using Some Convolutional Neural Network Architectures.

作者信息

Garga Benjamin, Abboubakar Hamadjam, Sourpele Rodrigue Saoungoumi, Gwet David Libouga Li, Bitjoka Laurent

机构信息

ENSAI, Laboratory of Energy, Signal, Imaging and Automation, University of Ngaoundere, Ngaoundere P.O. Box 455, Cameroon.

Departement of Computer Engineering, University Institute of Technology, University of Ngaoundere, Ngaoundere P.O. Box 455, Cameroon.

出版信息

J Imaging. 2024 Jun 28;10(7):158. doi: 10.3390/jimaging10070158.

DOI:10.3390/jimaging10070158

PMID:39057729

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11277931/

Abstract

The main objective of this work is to use convolutional neural networks (CNN) to improve the performance in previous works on their baseline for pollen grain classification, by improving the performance of the following eight popular architectures: InceptionV3, VGG16, VGG19, ResNet50, NASNet, Xception, DenseNet201 and InceptionResNetV2, which are benchmarks on several classification tasks, like on the ImageNet dataset. We use a well-known annotated public image dataset for the Brazilian savanna, called POLLEN73S, composed of 2523 images. Holdout cross-validation is the name of the method used in this work. The experiments carried out showed that DenseNet201 and ResNet50 outperform the other CNNs tested, achieving results of 97.217% and 94.257%, respectively, in terms of accuracy, higher than the existing results, with a difference of 1.517% and 0.257%, respectively. VGG19 is the architecture with the lowest performance, achieving a result of 89.463%.

摘要

这项工作的主要目标是通过提升以下八种流行架构的性能，利用卷积神经网络（CNN）来改进先前工作在花粉粒分类基线方面的表现，这八种架构分别是：InceptionV3、VGG16、VGG19、ResNet50、NASNet、Xception、DenseNet201和InceptionResNetV2，它们是多个分类任务（如在ImageNet数据集上）的基准模型。我们使用了一个著名的、带有注释的巴西热带稀树草原公共图像数据集，名为POLLEN73S，它由2523张图像组成。本研究采用的方法是留出法交叉验证。所进行的实验表明，DenseNet201和ResNet50的表现优于其他测试的CNN，在准确率方面分别达到了97.217%和94.257%，高于现有结果，分别高出1.517%和0.257%。VGG19是性能最低的架构，准确率为89.463%。