BananaGAN : Augmenting major banana disease detection using generated diseased pseudostem and rachis images

Vergara, Javier Alejandro

dc.contributor	Acharjee, Animesh
dc.contributor	Selvaraj,, Michael
dc.creator	Vergara, Javier Alejandro
dc.date	2024-06-08T01:22:11Z
dc.date	2024-06-08T01:22:11Z
dc.date	2021
dc.date.accessioned	2026-10-15T17:11:51Z
dc.date.available	2026-10-15T17:11:51Z
dc.identifier	https://vitela.javerianacali.edu.co/handle/11522/2021
dc.identifier.uri	https://hdl.handle.net/20.500.12032/189310
dc.description	Early detection and timely management of crop diseases are essential for reducing yield loss. Traditional manual inspection is often time-consuming, laborious, and biased. Recently, automated imaging techniques have been successfully applied to the detection of crop diseases. Almost this type of research requires a huge amount of images with key typical symptoms from rare classes. The rare class images are the key to differentiated closely related diseased symptoms, but it is mostly internal and difficult to get them. Thus we exploited generative adversarial networks for generating rare classes such as banana pseudostem and rachis images creating new datasets with synthetic images and doing domain disease translation, converting an image with a certain disease into another image with another different disease. These synthetic images were tested in pre-trained disease detection models to see if they are good enough to balance the banana disease datasets and improve the object detection models’ overall accuracy and can be applied to other deep learning techniques such as classification and semantic segmentation. mAP score from the trained models with synthetic images was between 64% and 89% accuracy, which conclude that synthetic images are a useful tool as a data augmentation technique.
dc.format	64
dc.format	application/pdf
dc.format	application/pdf
dc.format	application/pdf
dc.language	eng
dc.publisher	Pontificia Universidad Javeriana Cali
dc.rights	https://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights	https://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights	http://purl.org/coar/access_right/c_abf2
dc.subject	Artificial intelligence
dc.subject	Generative adversarial networks
dc.subject	Deep learning
dc.subject	Disease detection
dc.subject	Data augmentation
dc.subject	Pseudostem
dc.subject	rachis
dc.subject	Synthetic dat
dc.title	BananaGAN : Augmenting major banana disease detection using generated diseased pseudostem and rachis images
dc.type	http://purl.org/coar/resource_type/c_2df8fbb1
dc.type	Artículo de investigación
dc.type	https://purl.org/redcol/resource_type/ART

Ficheros en el ítem

Ficheros	Tamaño	Formato	Ver
No hay ficheros asociados a este ítem.

Este ítem aparece en la(s) siguiente(s) colección(ones)

Documentos - PUJC

Mostrar el registro sencillo del ítem