Age-API: are landmarks-based features still distinctive for invariant facial age recognition?

Age recognition from faces has attracted potential interest due to its importance in several areas as well as minor-security and online shopping. However, it still has various challenges, especially in an unconstrained environment such as anti-aging treatments, illumination conditions, and filter effects. To deal with these problems, we choose to extract geometric features from face images. Thus, our proposed method consists firstly, of verifying if the acquired image contains a face. Then, the landmarks coordinates are calculated and the image is divided into 4 blocks. In each block, cross-distances are calculated and only max distances are considered to compute ratios. Finally, distances and ratios-max distances are fused to represent the age. In relation with the insufficient data issues and real time responses requirement in the Application Programming Interface (API), we highlight the relative role of using the handcrafted-based features compared to deep learning method for the proposed purpose. On the other hand, imbalanced data and intra-class variability present another famous challenge aiming to decrease the performance results. To overcome these issues, we proposed a multi-level classification strategy. Our developed approach is evaluated using FG-NET and Adience datasets, and the obtained results are effective compared to other recent existing works.