Publications
2023
Carofilis-Vasco, Andrés; Chaves, Deisy; Martínez-Mendoza, Alicia; Fidalgo, Eduardo; González-Castro, Víctor; Alegre, Enrique
Impact of facial occlusions in age estimation algorithms for forensic applications Artículo de revista
En: Actas de las VIII Jornadas Nacionales de Investigación en Ciberseguridad: Vigo, 21 a 23 de junio de 2023, pp. 497–498, 2023, (Publisher: Universidade de Vigo).
Resumen | Enlaces | BibTeX | Etiquetas: Age Estimation, CSEM, deep learning, facial occlusion
@article{carofilis-vasco_impact_2023,
title = {Impact of facial occlusions in age estimation algorithms for forensic applications},
author = {Andrés Carofilis-Vasco and Deisy Chaves and Alicia Martínez-Mendoza and Eduardo Fidalgo and Víctor González-Castro and Enrique Alegre},
url = {https://buleria.unileon.es/handle/10612/20673},
year = {2023},
date = {2023-01-01},
journal = {Actas de las VIII Jornadas Nacionales de Investigación en Ciberseguridad: Vigo, 21 a 23 de junio de 2023},
pages = {497–498},
abstract = {This study examines age estimation in Child Sexual Exploitation Materials (CSEM) using deep learning. It evaluates six age estimators on facial images with and without occlusion, focusing on how facial occlusion impacts accuracy. Results show that eye occlusion significantly affects age prediction, especially for minors and older adults. The study offers insights for age estimation in forensic applications related to CSEM.},
note = {Publisher: Universidade de Vigo},
keywords = {Age Estimation, CSEM, deep learning, facial occlusion},
pubstate = {published},
tppubtype = {article}
}
2022
Jeuland, Elouan Derenee; Ferreras, Aitor Del Río; Chaves, Deisy; Fidalgo, Eduardo; González-Castro, Víctor; Alegre, Enrique
Assessment of age estimation methods for forensic applications using non-occluded and synthetic occluded facial images Artículo de revista
En: XLIII Jornadas de Automática, pp. 972–979, 2022, (Publisher: Universidade da Coruña. Servizo de Publicacións).
Resumen | Enlaces | BibTeX | Etiquetas: Age Estimation, CSEM, deep learning, facial occlusion
@article{jeuland_assessment_2022,
title = {Assessment of age estimation methods for forensic applications using non-occluded and synthetic occluded facial images},
author = {Elouan Derenee Jeuland and Aitor Del Río Ferreras and Deisy Chaves and Eduardo Fidalgo and Víctor González-Castro and Enrique Alegre},
url = {https://ruc.udc.es/dspace/handle/2183/31412},
year = {2022},
date = {2022-01-01},
journal = {XLIII Jornadas de Automática},
pages = {972–979},
abstract = {This paper evaluates the performance of six deep-learning-based age estimators for forensic applications, particularly in identifying minors and offenders in Child Sexual Exploitation Materials (CSEM). While deep learning is the state-of-the-art for age estimation, it struggles with minors and older adults due to dataset imbalances. Additionally, offenders often use facial occlusion to obscure identities, further impacting estimator accuracy. The study assesses models on non-occluded and synthetically occluded datasets, revealing that eye occlusion has a greater effect than mouth occlusion. Minors and elderly individuals are the most affected by occlusion, making this research a valuable benchmark for forensic victim profiling.},
note = {Publisher: Universidade da Coruña. Servizo de Publicacións},
keywords = {Age Estimation, CSEM, deep learning, facial occlusion},
pubstate = {published},
tppubtype = {article}
}
2020
Chaves, Deisy; Fidalgo, Eduardo; Alegre, Enrique; Jañez-Martino, Francisco; Biswas, Rubel
Improving age estimation in minors with occluded faces to fight against child sexual exploitation Artículo de revista
En: Proceedings of the 15th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, vol. 1, no 978-989-758-402-2, 2020.
Resumen | Enlaces | BibTeX | Etiquetas: Age Estimation, facial occlusion
@article{chaves_improving_2020,
title = {Improving age estimation in minors with occluded faces to fight against child sexual exploitation},
author = {Deisy Chaves and Eduardo Fidalgo and Enrique Alegre and Francisco Jañez-Martino and Rubel Biswas},
url = {https://scholar.google.es/citations?view_op=view_citation&hl=es&user=yATJZvcAAAAJ&cstart=20&pagesize=80&sortby=title&citation_for_view=yATJZvcAAAAJ:35N4QoGY0k4C},
year = {2020},
date = {2020-01-01},
urldate = {2020-01-01},
journal = {Proceedings of the 15th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications},
volume = {1},
number = {978-989-758-402-2},
abstract = {Proceedings of the 15th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications},
keywords = {Age Estimation, facial occlusion},
pubstate = {published},
tppubtype = {article}
}
Chaves, Deisy; Fidalgo, Eduardo; Alegre, Enrique; Jánez-Martino, Francisco; Biswas, Rubel
Improving Age Estimation in Minors and Young Adults with Occluded Faces to Fight Against Child Sexual Exploitation. Proceedings Article
En: VISIGRAPP (5: VISAPP), pp. 721–729, 2020.
Resumen | Enlaces | BibTeX | Etiquetas: Age Estimation, CSEM, Eye Occlusion, Forensic Images, SSR-Net-Model
@inproceedings{chaves_improving_2020-1,
title = {Improving Age Estimation in Minors and Young Adults with Occluded Faces to Fight Against Child Sexual Exploitation.},
author = {Deisy Chaves and Eduardo Fidalgo and Enrique Alegre and Francisco Jánez-Martino and Rubel Biswas},
url = {https://pdfs.semanticscholar.org/b1eb/3264582c54c648cd8329deddf99f64ddb094.pdf},
year = {2020},
date = {2020-01-01},
booktitle = {VISIGRAPP (5: VISAPP)},
pages = {721–729},
abstract = {This study focuses on improving age estimation accuracy in Child Sexual Exploitation Materials, particularly for minors and young adults, using the Soft Stagewise Regression Network (SSR-Net) model. The challenge arises from unbalanced training data and facial occlusion (e.g., covering the eyes to hide victims' identities), which negatively impact the performance of age estimators. The proposed approach combines non-occluded and occluded facial images to create robust SSR-Net models. This strategy significantly enhances the model's performance, reducing the Mean Absolute Error (MAE) from 7.26, 6.81, and 6.5 to 4.07 on the IMBD, MORPH, and Deep EXpectation datasets, respectively.},
keywords = {Age Estimation, CSEM, Eye Occlusion, Forensic Images, SSR-Net-Model},
pubstate = {published},
tppubtype = {inproceedings}
}
0000
Centeno, Iván Paz; Fidalgo, Eduardo; Olivera, Óscar García-Olalla; Alegre, Enrique
DESIGN AND IMPLEMENTATION OF BRPY: A BIORECOGNITION SYSTEM (FACE DETECTION AND RECOGNITION, AGE ESTIMATION AND GENDER ESTIMATION) BASED ON THE FACE. Artículo de revista
En: Power, vol. 5, pp. 2A, 0000.
Resumen | Enlaces | BibTeX | Etiquetas: Age Estimation, Algorithm, BRPY, Detection, Face, Gender Estimation, OpenBR, Python, Recognition
@article{de_paz_centeno_design_nodate,
title = {DESIGN AND IMPLEMENTATION OF BRPY: A BIORECOGNITION SYSTEM (FACE DETECTION AND RECOGNITION, AGE ESTIMATION AND GENDER ESTIMATION) BASED ON THE FACE.},
author = {Iván Paz Centeno and Eduardo Fidalgo and Óscar García-Olalla Olivera and Enrique Alegre},
url = {https://www.ehu.eus/documents/3444171/4484752/108.pdf},
journal = {Power},
volume = {5},
pages = {2A},
abstract = {This document outlines the design and implementation of BRPY, an open-source multi-platform program for real-time face detection, recognition, and age and gender estimation. Developed in Python and C++ using OpenBR and OpenCV, it focuses on using the ODroid U3 platform for execution and details the design of the program interface.},
keywords = {Age Estimation, Algorithm, BRPY, Detection, Face, Gender Estimation, OpenBR, Python, Recognition},
pubstate = {published},
tppubtype = {article}
}