A Parallel Deep Learning Approach for Age Invariant Face Recognition system

Age robust face recognition is a challenging technology to implement in various applications. One of its most critical features is the ability to identify the different facial features due to the varying shapes and textures of the human body. All these variations result in poor recognition performance. Soft computing methodologies have helped it to achieve better recognition results. Deep learning has been regarded as a promising technique in terms of face recognition. However, despite the advancements in this field, many challenges still remain. This paper presents an age-invariant face identification system that uses high-dimensional binary pattern features and a parallel deep convolutional neural network. We performed experiments on two standard datasets, namely the FGNET and the CACD. Our method outperforms the existing techniques and provides a high degree of recognition accuracy.