Cookies
O website necessita de alguns cookies e outros recursos semelhantes para funcionar. Caso o permita, o INESC TEC irá utilizar cookies para recolher dados sobre as suas visitas, contribuindo, assim, para estatísticas agregadas que permitem melhorar o nosso serviço. Ver mais
Aceitar Rejeitar
  • Menu
Publicações

Publicações por Gabriel António Carneiro

2021

Grapevine Variety Identification Through Grapevine Leaf Images Acquired in Natural Environment

Autores
Carneiro, GS; Pádua, L; Sousa, JJ; Peres, E; Morais, R; Cunha, A;

Publicação
IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021, Brussels, Belgium, July 11-16, 2021

Abstract
In this paper we present a Deep Learning-based methodology to automatically classify 12 of the most representative grapevarieties existing in the Douro Demarked region, Portugal. The dataset used consisted of images of leaves at different stages of development, collected on their natural environment. The development of such methodologies becomes particularly important, in a scenario in which ampeleographers are disappearing, creating a gap in the task of inspection of grape varieties. Our approach was based on the transfer learning of the Xcepetion model, using Focal Loss, adaptive learning rate decay and SGD. The model obtained a F1 score of 0.93. To clearly understand the predictions of the model, and realize which regions of the image contributed the most to the classification, the LIME library was used. This way it was possible to identify the parts of the images that were considered for and against each prediction.

2021

A Convolutional Neural Network-based Ancient Sundanese Character Classifier with Data Augmentation

Autores
Carneiro, GS; Ferreira, A; Morais, R; Sousa, JJ; Cunha, A;

Publicação
5TH INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND COMPUTATIONAL INTELLIGENCE 2020

Abstract
With an increasing interest in the digitization effort of ancient manuscripts, ancient character recognition becomes one of the most important areas in the automated document image analysis. In this regard, we propose a Convolutional Neural Network (CNN)-based classifier to recognize the ancient Sundanese characters obtained from a digital collection of Southeast Asian palm leaf manuscripts. In this work, we utilize two different preprocessing techniques for the dataset. The first technique involves the use of geometric transformations, noise background addition, and brightness adjustment to augment the imbalanced samples to be fed into the classifier. The second technique makes use of the Otsu's threshold method to binarize the characters and only uses the usual geometric transformations for the data augmentation. The proposed network with different data augmentation processes is trained on the training set and tested on the testing set. Image binarization from the second technique can outperform the performance of the CNN-based classifier upon the first technique by achieving a testing accuracy of 97.74%. (C) 2021 The Authors. Published by Elsevier B.V.

2021

Grapevine Segmentation in RGB Images using Deep Learning

Autores
Carneiro, GA; Magalhães, R; Neto, A; Sousa, JJ; Cunha, A;

Publicação
Procedia Computer Science

Abstract
Wine is the most important product from the Douro Region, in Portugal. Ampelographs are disappearing, and farmers need new solutions to identify grapevine varieties to ensure high-quality standards. The development of methodology capable of automatically identify grapevine are in need. In the scenario, deep learning based methods are emerging as the state-of-art in grapevines classification tasks. In previous work, we verify the deep learning models would benefit from focus classification patches in leaves images areas. Deep learning segmentation methods can be used to find grapevine leaves areas. This paper presents a methodology to segment grapevines images automatically based on the U-net model. A private dataset was used, composed of 733 grapevines images frames extracted from 236 videos collected in a natural environment. The trained model obtained a Dice of 95.6% and an Intersection over Union of 91.6%, results that fully satisfy the need of localise grapevine leaves.

2022

SEGMENTATION AS A PREPROCESSING TOOL FOR AUTOMATIC GRAPEVINE CLASSIFICATION

Autores
Carneiro, GA; Padua, L; Peres, E; Morais, R; Sousa, JJ; Cunha, A;

Publicação
2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022)

Abstract
The grapevine variety plays an important role in wine chain production, thus identifying it is crucial for control activities. However, the specialists responsible for identifying the different varieties, mainly through visual analysis, are disappearing. In this scenario, Deep Learning (DL) classification techniques become a possible solution to handle professionals' scarcity. Nevertheless, previous experiments show that trained classification models use the background information to make decisions, which should be avoided. In this paper, we present a study allowing the assessment of removing background regions from the grapevine images in the improvement classification using DL models. The Xception model is trained with a normal dataset and its segmented version. The Local Interpretable Model-Agnostic Explanations (LIME), Grad-CAM, and Grad-CAM++ approaches are used to visualize the segmentation impact in classification decisions. F1-score of 0.92 and 0.94 were achieved, respectively, for segmented-dataset and normal-dataset trained models. Despite the model trained with the segmented-dataset to achieve a worse performance, the Explainable Artificial Intelligence (XAI) approaches showed that it looks into more reliable regions when making decisions.

2022

GRAPEVINE VARIETIES IDENTIFICATION USING VISION TRANSFORMERS

Autores
Carneiro, GA; Padua, L; Peres, E; Morais, R; Sousa, JJ; Cunha, A;

Publicação
2022 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2022)

Abstract
The grape variety plays an important role in the wine production chain, thus identifying it is crucial for production control. Ampelographers, professionals who identify grape varieties through plant visual analysis, are scarce, and molecular markers are expansive to identify grape varieties on a large scale. In this context, Deep Learning models become an effective way to handle ampelographers scarcity. In this work, we explore the benefit of using deep learning vision transformers architecture relative to conventional CNN to identify 12 grapevine varieties using leaf-centred RGB images acquired in the field. We train an Xception model as a baseline and four different configurations of the ViT_B model. The best model achieved 0.96 of F1-score, outperforming the state-of-the-art convolutional-based model in the used dataset.

2023

AUTOMATIC IDENTIFICATION OF PUBLIC LIGHTING FAILURES IN SATELLITE IMAGES: A CASE STUDY IN SEVILLE, SPAIN

Autores
Teixeira, AC; Batista, L; Carneiro, G; Cunha, A; Sousa, JJ;

Publicação
IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM

Abstract
Public lighting is crucial for maintaining the safety and well-being of communities. Current inspection methods involve examining the luminaires during the day, but this approach has drawbacks, including energy consumption, delay in detecting issues, and high costs and time investment. Utilising deep learning based automatic detection is an advanced method that can be used for identifying and locating issues in this field. This study aims to use deep learning to automatically detect burnt-out street lights, using Seville (Spain) as a case study. The study uses high-resolution night time imagery from the JL1-3B satellite to create a dataset called NLight, which is then divided into three subsets: NL1, NL2, and NT. The NL1 and NL2 datasets are used to train and evaluate YOLOv5 and YOLOv7 segmentation models for instance segmentation of streets. And then, distance outliers were detected to find the lights off. Finally, the NT dataset is used to evaluate the effectiveness of the proposed methodology. The study finds that YOLOv5 achieved a mask mAP of 57.7%, and the proposed methodology had a precision of 30.8% and a recall of 28.3%. The main goal of this work is accomplished, but there is still space for future work to improve the methodology.

  • 1
  • 2