EVALUATING DATA AUGMENTATION FOR GRAPEVINE VARIETIES IDENTIFICATION

被引：0

作者：

Carneiro, Gabriel ^{[1
,2
]}

Neto, Alexandre ^{[1
,2
]}

Teixeira, Ana ^{[1
,2
]}

Cunha, Antonio ^{[1
,2
]}

Sousa, Joaquim ^{[1
,2
]}

机构：

[1] Univ Tras Os Montes & Alto Douro, Vila Real, Portugal

[2] INESC TEC, Porto, Portugal

来源：

IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM | 2023年

基金：

欧盟地平线“2020”;

关键词：

deep learning; grapevine variety identification; convolutional neural networks; data augmentation; precision viticulture;

D O I：

10.1109/IGARSS52108.2023.10283128

中图分类号：

P [天文学、地球科学];

学科分类号：

07 ;

摘要：

The grapevine variety identification is important in the wine's production chain since it is related to its quality, authenticity and singularity. In this study, we addressed the data augmentation approach to identify grape varieties with images acquired in-field. We tested the static transformations, RandAugment, and Cutmix methods. Our results showed that the best result was achieved by the Static method generating 5 images per sample (F1 = 0.89), however without a significative difference if compared with RandAugment generating 2 images. The worst performance was achieved by CutMix (F1 = 0.86).

引用

页码：3566 / 3569

页数：4

共 13 条

[1] Balestriero R., 2022, EFFECTS REGULARIZATI, DOI [10.48550/arXiv.2204.03632, DOI 10.48550/ARXIV.2204.03632]
[2] Deep Learning-Based Plant-Image Classification Using a Small Training Dataset
Batchuluun, Ganbayar
Nam, Se Hyun
Park, Kang Ryoung
[J]. MATHEMATICS, 2022, 10 (17)
[3] Carneiro Gabriel, 2021, 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, P7055, DOI 10.1109/IGARSS47720.2021.9555141
[4] GRAPEVINE VARIETIES IDENTIFICATION USING VISION TRANSFORMERS
Carneiro, Gabriel Antonio
Padua, Luis
Peres, Emanuel
Morais, Raul
Sousa, Joaquim J.
Cunha, Antonio
[J]. 2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022), 2022, : 5866 - 5869
[5] Chollet F., 2017, Deep Learning with Python
[6] Randaugment: Practical automated data augmentation with a reduced search space
Cubuk, Ekin D.
Zoph, Barret
Shlens, Jonathon
Le, Quoc, V
[J]. 2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW 2020), 2020, : 3008 - 3017
[7] Approximate statistical tests for comparing supervised classification learning algorithms
Dietterich, TG
[J]. NEURAL COMPUTATION, 1998, 10 (07) : 1895 - 1923
[8] Enkvetchakul P., 2022, Applied Science and Engineering Progress, V15, P3810
[9] A CNN-SVM study based on selected deep features for grapevine leaves classification
Koklu, Murat
Unlersen, M. Fahri
Ozkan, Ilker Ali
Aslan, M. Fatih
Sabanci, Kadir
[J]. MEASUREMENT, 2022, 188
[10] Data Augmentation for Plant Classification
Pawara, Pornntiwa
Okafor, Emmanuel
Schomaker, Lambert
Wiering, Marco
[J]. ADVANCED CONCEPTS FOR INTELLIGENT VISION SYSTEMS (ACIVS 2017), 2017, 10617 : 615 - 626

← 1 2 →