Image augmentation for object detection of grapevines

Machine Learning methods are widely used for data analysis in various areas. In this work we use Neural Networks for image analysis in order to detect grape fruit clusters. A set of manually tagged images is built and a comparison is made between different data augmentation techniques in order to an...

Descripción completa

Detalles Bibliográficos
Autores principales: Parlanti, Tatiana Sofía, Lobos, Alejandro Martín, Moyano, Luis G., Millan, Emmanuel N.
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2020
Materias:
Ciencias Informáticas
Machine learning
Neural networks
Deep learning
Object detection
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/113261
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-113261
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Machine learning
Neural networks
Deep learning
Object detection
spellingShingle Ciencias Informáticas
Machine learning
Neural networks
Deep learning
Object detection
Parlanti, Tatiana Sofía
Lobos, Alejandro Martín
Moyano, Luis G.
Millan, Emmanuel N.
Image augmentation for object detection of grapevines
topic_facet Ciencias Informáticas
Machine learning
Neural networks
Deep learning
Object detection
description Machine Learning methods are widely used for data analysis in various areas. In this work we use Neural Networks for image analysis in order to detect grape fruit clusters. A set of manually tagged images is built and a comparison is made between different data augmentation techniques in order to analyse the best way to expand the image set. The technique presented here obtained up to 13% better detection performance starting with only 100 images for training. The types of transformations and filters that worked the best for these images are discussed. In addition, training and detection times in five different hardware infrastructures, both CPU and GPUs, are briefly discussed.
format Objeto de conferencia
Objeto de conferencia
author Parlanti, Tatiana Sofía
Lobos, Alejandro Martín
Moyano, Luis G.
Millan, Emmanuel N.
author_facet Parlanti, Tatiana Sofía
Lobos, Alejandro Martín
Moyano, Luis G.
Millan, Emmanuel N.
author_sort Parlanti, Tatiana Sofía
title Image augmentation for object detection of grapevines
title_short Image augmentation for object detection of grapevines
title_full Image augmentation for object detection of grapevines
title_fullStr Image augmentation for object detection of grapevines
title_full_unstemmed Image augmentation for object detection of grapevines
title_sort image augmentation for object detection of grapevines
publishDate 2020
url http://sedici.unlp.edu.ar/handle/10915/113261
work_keys_str_mv AT parlantitatianasofia imageaugmentationforobjectdetectionofgrapevines
AT lobosalejandromartin imageaugmentationforobjectdetectionofgrapevines
AT moyanoluisg imageaugmentationforobjectdetectionofgrapevines
AT millanemmanueln imageaugmentationforobjectdetectionofgrapevines
bdutipo_str Repositorios
_version_ 1764820445269327875

Ejemplares similares