POLLEN73S: An image dataset for pollen grains classification

被引：32

作者：

Astolfi, Gilberto ^{[1
,2
]}

Goncalves, Ariadne Barbosa ^{[3
,4
]}

Menezes, Geazy Vilharva ^{[1
]}

Brito Borges, Felipe Silveira ^{[6
]}

Melo Nunes Astolfi, Angelica Christina ^{[5
]}

Matsubara, Edson Takashi ^{[1
]}

Alvarez, Marco ^{[7
]}

Pistori, Hemerson ^{[1
,6
]}

机构：

[1] Univ Fed Mato Grosso do Sul, Coll Comp, Campo Grande, MS, Brazil

[2] Sci & Technol Mato Grosso do Sul, Fed Inst Educ, Campo Grande, MS, Brazil

[3] Univ Fed Mato Grosso do Sul, Postgrad Dept Nat Resources, Campo Grande, MS, Brazil

[4] Univ Estadual Mato Grosso do Sul, Dept Environm Engn, Maracaju, MS, Brazil

[5] Univ Fed Mato Grosso do Sul, Fac Engn Architecture & Urbanism & Geog, Campo Grande, MS, Brazil

[6] Univ Catolica Dom Bosco, Campo Grande, MS, Brazil

[7] Univ Rhode Isl, Dept Comp Sci & Stat, Kingston, RI 02881 USA

来源：

ECOLOGICAL INFORMATICS | 2020年 / 60卷

关键词：

Pollen classification; Convolutional neural networks; Image dataset;

D O I：

10.1016/j.ecoinf.2020.101165

中图分类号：

Q14 [生态学（生物生态学）];

学科分类号：

071012 ; 0713 ;

摘要：

The classification of pollen species and types is an important task in many areas like forensic palynology, archaeological palynology, and melissopalynology. This paper presents a new public annotated image dataset for the Brazilian Savanna called POLLEN73S composed of 2523 images from 73 pollen types. Using the state-of-the-art Convolutional Neural Networks (CNNs), we provide a baseline for pollen grain classification. Our experiments showed evidence that DenseNet-201 and ResNet-50 have superior performance against the other CNNs tested, achieving precision results of 95.7% and 94.0%, respectively. Due to its category coverage and satisfactory diversity of examples, POLLEN73S offers a diversity of pollen grain to guide progress in computer vision to solve Palynology problems.

引用

页数：9

共 37 条

[1]

[Anonymous], 2015, ICLR

[2] Benchmark Analysis of Representative Deep Neural Network Architectures [J].

Bianco, Simone ;

Cadene, Remi ;

Celona, Luigi ;

Napoletano, Paolo .

IEEE ACCESS, 2018, 6 :64270-64277

[3]

CHOLLET F, 2017, PROC CVPR IEEE, P1800, DOI [DOI 10.1109/CVPR.2017.195, 10.1109/CVPR.2017.195]

[4]

Chollet F., 2015, KERAS

[5]

Chung J., 2014, CORR, DOI DOI 10.48550/ARXIV.1412.3555

[6] TRANSFORMATION TO NORMALITY OF NULL DISTRIBUTION OF G1 [J].

DAGOSTIN.RB .

BIOMETRIKA, 1970, 57 (03) :679-&

[7]

Daood Amar, 2016, Advances in Visual Computing. 12th International Symposium, ISVC 2016. Proceedings: LNCS 10072, P321, DOI 10.1007/978-3-319-50835-1_30

[8]

Duchi J, 2011, J MACH LEARN RES, V12, P2121

[9] MULTIPLE COMPARISONS USING RANK SUMS [J].

DUNN, OJ .

TECHNOMETRICS, 1964, 6 (03) :241-&

[10] Feature Extraction and Machine Learning for the Classification of Brazilian Savannah Pollen Grains [J].

Goncalves, Ariadne Barbosa ;

Souza, Junior Silva ;

da Silva, Gercina Goncalves ;

Cereda, Marney Pascoli ;

Pott, Arnildo ;

Naka, Marco Hiroshi ;

Pistori, Hemerson .

PLOS ONE, 2016, 11 (06)

← 1 2 3 4 →