Improving Borderline Adulthood Facial Age Estimation through Ensemble Learning
This work addresses a specific weakness in facial age estimation algorithms for borderline cases, which is important for applications like age verification but is incremental in nature.
The paper tackled the challenge of accurately estimating facial age for borderline adulthood subjects (16-17 years old) by developing an ensemble technique combined with a fine-tuned deep learning model, achieving 68% accuracy, which is four times better than the baseline DEX model for that age range.
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 have been employed to measure the mean absolute error (MAE) ranging 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. 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.