Utilizing CNNs and transfer learning of pre-trained models for age range classification from unconstrained face images

Abstract Automatic age classification from real-world and wild face images is a challenging task and has an increasing importance due to its wide range of applications in current and future lifestyles. As a result of increasing age specific human-computer interactions, it is expected that computerized systems should be capable of estimating the age from face images and respond accordingly. Over the past decade, many research studies have been conducted on automatic age classification from face images. However, the performance of the developed age classification systems suffered due to the absence of large, comprehensive benchmarks. In this work, we propose and show that pre-trained CNNs which were trained on large benchmarks for different purposes can be retrained and fine-tuned for age range classification from unconstrained face images. Also, we propose to reduce the dimension of the output of the last convolutional layer in pre-trained CNNs to improve the performance of the designed CNNs architectures. The experimental results show significant improvements in exact and 1-off accuracies on the Adience benchmark.