Unknown

Dataset Information

0

Feature Extraction and Machine Learning for the Classification of Brazilian Savannah Pollen Grains.


ABSTRACT: The classification of pollen species and types is an important task in many areas like forensic palynology, archaeological palynology and melissopalynology. This paper presents the first annotated image dataset for the Brazilian Savannah pollen types that can be used to train and test computer vision based automatic pollen classifiers. A first baseline human and computer performance for this dataset has been established using 805 pollen images of 23 pollen types. In order to access the computer performance, a combination of three feature extractors and four machine learning techniques has been implemented, fine tuned and tested. The results of these tests are also presented in this paper.

SUBMITTER: Goncalves AB 

PROVIDER: S-EPMC4898734 | biostudies-literature | 2016

REPOSITORIES: biostudies-literature

altmetric image

Publications

Feature Extraction and Machine Learning for the Classification of Brazilian Savannah Pollen Grains.

Gonçalves Ariadne Barbosa AB   Souza Junior Silva JS   Silva Gercina Gonçalves da GG   Cereda Marney Pascoli MP   Pott Arnildo A   Naka Marco Hiroshi MH   Pistori Hemerson H  

PloS one 20160608 6


The classification of pollen species and types is an important task in many areas like forensic palynology, archaeological palynology and melissopalynology. This paper presents the first annotated image dataset for the Brazilian Savannah pollen types that can be used to train and test computer vision based automatic pollen classifiers. A first baseline human and computer performance for this dataset has been established using 805 pollen images of 23 pollen types. In order to access the computer  ...[more]

Similar Datasets

| S-EPMC9601423 | biostudies-literature
| S-EPMC7189237 | biostudies-literature
| S-EPMC10502833 | biostudies-literature
| S-EPMC7353138 | biostudies-literature
| S-EPMC7459797 | biostudies-literature
| S-EPMC9953011 | biostudies-literature
| S-EPMC8336915 | biostudies-literature
| S-EPMC7927045 | biostudies-literature
| S-EPMC7064494 | biostudies-literature
| S-EPMC6901070 | biostudies-literature