A novel attention aware method is proposed to fuse two image modalities, RGB and depth, for enhanced RGB-D facial recognition . The proposed method first extracts features from both modalities using a convolutional feature extractor . These features are then fused using a two-layer attention mechanism . The training database is preprocessed and augmented through a set of geometric transformations, and the learning process is further aided using transfer learning from a pure 2D image training process . Comparative evaluations demonstrate that the proposed method outperforms other state-of-the-art approaches, including both traditional and deep neural network-based approaches, on the challenging CurtinFaces and IIIT-D RGB-Faces databases, achieving classification accuracies over 98.2% and 99.3% respectively. The proposed attention mechanism is also compared with other attention mechanisms, demonstrating more accurate results, demonstrates more accurate Results . The proposal was published in the Journal of

Links: PDF - Abstract

Code :


Keywords : attention - rgb - proposed - method - learning -

Leave a Reply

Your email address will not be published. Required fields are marked *


Enjoy this blog? Please spread the word :)