Image augmentation for object detection of grapevines
- Autores
- Parlanti, Tatiana Sofía; Lobos, Alejandro Martín; Moyano, Luis G.; Millan, Emmanuel N.
- Año de publicación
- 2020
- Idioma
- inglés
- Tipo de recurso
- documento de conferencia
- Estado
- versión publicada
- Descripción
- 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.
Workshop: WASI – Agentes y Sistemas Inteligentes
Red de Universidades con Carreras en Informática - Materia
-
Ciencias Informáticas
Machine learning
Neural networks
Deep learning
Object detection - Nivel de accesibilidad
- acceso abierto
- Condiciones de uso
- http://creativecommons.org/licenses/by-nc-sa/4.0/
- Repositorio
.jpg)
- Institución
- Universidad Nacional de La Plata
- OAI Identificador
- oai:sedici.unlp.edu.ar:10915/113261
Ver los metadatos del registro completo
| id |
SEDICI_4ca20edcb065dea741300c12c3bd8c27 |
|---|---|
| oai_identifier_str |
oai:sedici.unlp.edu.ar:10915/113261 |
| network_acronym_str |
SEDICI |
| repository_id_str |
1329 |
| network_name_str |
SEDICI (UNLP) |
| spelling |
Image augmentation for object detection of grapevinesParlanti, Tatiana SofíaLobos, Alejandro MartínMoyano, Luis G.Millan, Emmanuel N.Ciencias InformáticasMachine learningNeural networksDeep learningObject detectionMachine 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.Workshop: WASI – Agentes y Sistemas InteligentesRed de Universidades con Carreras en Informática2020-10info:eu-repo/semantics/conferenceObjectinfo:eu-repo/semantics/publishedVersionObjeto de conferenciahttp://purl.org/coar/resource_type/c_5794info:ar-repo/semantics/documentoDeConferenciaapplication/pdf31-40http://sedici.unlp.edu.ar/handle/10915/113261enginfo:eu-repo/semantics/altIdentifier/isbn/978-987-4417-90-9info:eu-repo/semantics/reference/hdl/10915/113243info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by-nc-sa/4.0/Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)reponame:SEDICI (UNLP)instname:Universidad Nacional de La Platainstacron:UNLP2025-10-15T11:18:14Zoai:sedici.unlp.edu.ar:10915/113261Institucionalhttp://sedici.unlp.edu.ar/Universidad públicaNo correspondehttp://sedici.unlp.edu.ar/oai/snrdalira@sedici.unlp.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:13292025-10-15 11:18:14.666SEDICI (UNLP) - Universidad Nacional de La Platafalse |
| dc.title.none.fl_str_mv |
Image augmentation for object detection of grapevines |
| title |
Image augmentation for object detection of grapevines |
| spellingShingle |
Image augmentation for object detection of grapevines Parlanti, Tatiana Sofía Ciencias Informáticas Machine learning Neural networks Deep learning Object detection |
| 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 |
| dc.creator.none.fl_str_mv |
Parlanti, Tatiana Sofía Lobos, Alejandro Martín Moyano, Luis G. Millan, Emmanuel N. |
| author |
Parlanti, Tatiana Sofía |
| author_facet |
Parlanti, Tatiana Sofía Lobos, Alejandro Martín Moyano, Luis G. Millan, Emmanuel N. |
| author_role |
author |
| author2 |
Lobos, Alejandro Martín Moyano, Luis G. Millan, Emmanuel N. |
| author2_role |
author author author |
| dc.subject.none.fl_str_mv |
Ciencias Informáticas Machine learning Neural networks Deep learning Object detection |
| topic |
Ciencias Informáticas Machine learning Neural networks Deep learning Object detection |
| dc.description.none.fl_txt_mv |
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. Workshop: WASI – Agentes y Sistemas Inteligentes Red de Universidades con Carreras en Informática |
| 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. |
| publishDate |
2020 |
| dc.date.none.fl_str_mv |
2020-10 |
| dc.type.none.fl_str_mv |
info:eu-repo/semantics/conferenceObject info:eu-repo/semantics/publishedVersion Objeto de conferencia http://purl.org/coar/resource_type/c_5794 info:ar-repo/semantics/documentoDeConferencia |
| format |
conferenceObject |
| status_str |
publishedVersion |
| dc.identifier.none.fl_str_mv |
http://sedici.unlp.edu.ar/handle/10915/113261 |
| url |
http://sedici.unlp.edu.ar/handle/10915/113261 |
| dc.language.none.fl_str_mv |
eng |
| language |
eng |
| dc.relation.none.fl_str_mv |
info:eu-repo/semantics/altIdentifier/isbn/978-987-4417-90-9 info:eu-repo/semantics/reference/hdl/10915/113243 |
| dc.rights.none.fl_str_mv |
info:eu-repo/semantics/openAccess http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) |
| eu_rights_str_mv |
openAccess |
| rights_invalid_str_mv |
http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) |
| dc.format.none.fl_str_mv |
application/pdf 31-40 |
| dc.source.none.fl_str_mv |
reponame:SEDICI (UNLP) instname:Universidad Nacional de La Plata instacron:UNLP |
| reponame_str |
SEDICI (UNLP) |
| collection |
SEDICI (UNLP) |
| instname_str |
Universidad Nacional de La Plata |
| instacron_str |
UNLP |
| institution |
UNLP |
| repository.name.fl_str_mv |
SEDICI (UNLP) - Universidad Nacional de La Plata |
| repository.mail.fl_str_mv |
alira@sedici.unlp.edu.ar |
| _version_ |
1846064240531603456 |
| score |
13.22299 |