Gerardo Antonio Alvarez Hernandez

Dr. Gerardo Antonio Alvarez Hernandez

Sistema Inteligentes Aplicados, Centro De Innovación Y Desarrollo Tecnológico En Cómputo, Mexico City, Ciudad de México, Mexico
orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2024 in Ciência E Agrotecnologia
Verified
Journal Article
Open access
PDF file
ERErick Rodríguez-Hernández
Erick Rodríguez-Hernández
JOJUAN CARLOS OLGUIN
JUAN CARLOS OLGUIN
GHGerardo Antonio Alvarez Hernandez
Gerardo Antonio Alvarez Hernandez
JVJuan Irving Vasquez
Juan Irving Vasquez
AUAbril Valeria Uriarte-Arcia
Abril Valeria Uriarte-Arcia
HTHind Taud
Hind Taud
The classification of tomato ripening stages involves assigning a tomato to a category based on the visual indicators of its maturity. Indeed, the specific number of categories and their attributes are determined by the agricultural standards of each country, which rely on an empirical understanding of visual characteristics. Conversely, automatic unsupervised classification techniques, such as deep learning-based methods, autonomously learn their characteristics. In this research, a comparison is made between expert-based classification and unsupervised classification, with a particular focus on the analysis of the number of clusters and their respective features. Remarkably, this investigation finds an alignment in the number of clusters identified by both methods. This discovery supports the notion that the expert-based classification system is compatible with automated approaches. The outcomes of this research could aid the agricultural sector in refining automatic classification techniques. Furthermore, this work provides the scientific community with valuable insights into the clustering of images by machine learning methods.

1 August 2026 in IEEE Latin America Transactions
Verified
Journal Article
Closed access
GHGerardo Antonio Alvarez Hernandez
Gerardo Antonio Alvarez Hernandez
JVJuan Irving Vasquez
Juan Irving Vasquez
AUAbril Valeria Uriarte-Arcia
Abril Valeria Uriarte-Arcia
LOLuis Alberto Tovar Ortiz
Luis Alberto Tovar Ortiz

15 June 2025 in Agriculture
Verified
Journal Article
Open access
PDF file
AZAngel Eduardo Zamora-Suárez
Angel Eduardo Zamora-Suárez
GHGerardo Antonio Alvarez Hernandez
Gerardo Antonio Alvarez Hernandez
JVJuan Irving Vasquez
Juan Irving Vasquez
HTHind Taud
Hind Taud
AUAbril Valeria Uriarte-Arcia
Abril Valeria Uriarte-Arcia
EZErik Zamora
Erik Zamora
Accurate labeling is critical for training reliable deep learning models in agricultural applications. However, manual labeling is often error-prone, especially when performed by non-experts, and such errors (modeled as noise) can significantly degrade model performance. This study addresses the problem of correcting labeling errors in object detection datasets without human intervention. We hypothesize that label noise can be reduced by exploiting the feature space representation of the data, enabling automatic refinement through repeated model-based filtering. To test this, we propose a recursive methodology that employs a YOLOv5 detector to iteratively relabel a dataset of Prunaxx and Paipai tomato images captured in greenhouse environments. The correction process involves training the detector, predicting new labels, and replacing existing labelings over multiple iterations. Experimental results show substantial improvements: the mean Average Precision at an IoU threshold of 0.50 (mAP-50) increased from 0.8 to 0.86, the mean Average Precision across IoU thresholds from 0.50 to 0.95 (mAP-50:95) increased from 0.46 to 0.63, and Recall improved from 0.68 to 0.82. These results demonstrate that the model was able to detect more true positives after filtering, while also achieving more accurate bounding box predictions. Although a slight decrease in Precision was observed in later iterations due to false positives, the overall quality of the dataset improved consistently. In conclusion, the proposed filtering method effectively enhances label quality without manual intervention and offers a scalable solution for improving object detection datasets in precision agriculture.