Inproceedings
Improving Borderline Adulthood Facial Age Estimation through Ensemble Learning
Contribution Summary
This paper addresses the challenge of facial age estimation for borderline adulthood cases, where the accuracy of existing algorithms is significantly lower. The authors propose an ensemble learning approach that combines a deep learning model (DS13K) with the Deep Expectation (DEX) model to improve the accuracy of underage estimation. The DS13K model is fine-tuned on the DEX model to achieve an accuracy of 68% for the age group 16-17 years old, which is 4 times better than the DEX accuracy for the same age range. The study also evaluates existing cloud-based facial age prediction services, including Amazon Rekognition, Microsoft Azure Cognitive Services, How-Old.net, and DEX. The results demonstrate the effectiveness of the proposed approach in improving the accuracy of facial age estimation for borderline adulthood cases.
Keywords: Underage Photo Datasets; Deep Learning; Digital Forensics; Child Exploitation Investigation; Facial Recognition; Ensemble Learning; Facial Age Estimation; Borderline Adulthood
Abstract
Achieving high performance for facial age estimation with subjects in the borderline between adulthood and non-adulthood has always been a challenge. Several studies have used different approaches from the age of a baby to an elder adult and different datasets to measure the mean absolute error (MAE) that has been oscillating between 1.47 to 8 years. The weakness of the algorithms specifically in the borderline has been a motivation for this paper. In our approach, we have developed an ensemble technique that improves the accuracy of underage estimation in conjunction with our deep learning model (DS13K) that has been fine-tuned on the Deep Expectation (DEX) model. We have achieved an accuracy of 68% for the age group 16 to 17 years old, which is 4 times better than the DEX accuracy for such age range. And we also present an evaluation of existing cloud-based and offline facial age prediction services such as Amazon Rekognition, Microsoft Azure Cognitive Services, How-Old.net and DEX.
BibTeX
@inproceedings{anda2019borderlineadulthood,
author={Anda, Felix and Lillis, David and Kanta, Aikaterini and Becker, Brett and Bou-Harb, Elias and Le-Khac, Nhien-An and Scanlon, Mark},
title="{Improving Borderline Adulthood Facial Age Estimation through Ensemble Learning}",
booktitle="{The 8th International Workshop on Cyber Crime (IWCC), held at the 14th International Conference on Availability, Reliability and Security (ARES)}",
series = {ARES '19},
year=2019,
month=08,
location={Canterbury, UK},
publisher={ACM},
address = {New York, NY, USA},
abstract="Achieving high performance for facial age estimation with subjects in the borderline between adulthood and non-adulthood has always been a challenge. Several studies have used different approaches from the age of a baby to an elder adult and different datasets to measure the mean absolute error (MAE) that has been oscillating between 1.47 to 8 years. The weakness of the algorithms specifically in the borderline has been a motivation for this paper. In our approach, we have developed an ensemble technique that improves the accuracy of underage estimation in conjunction with our deep learning model (DS13K) that has been fine-tuned on the Deep Expectation (DEX) model. We have achieved an accuracy of 68\% for the age group 16 to 17 years old, which is 4 times better than the DEX accuracy for such age range. And we also present an evaluation of existing cloud-based and offline facial age prediction services such as Amazon Rekognition, Microsoft Azure Cognitive Services, How-Old.net and DEX.",
doi={10.1145/3339252.3341491},
}