FACE RECOGNITION: A NOVEL DEEP LEARNING APPROACH

摘要

We propose a novel and robust-deep learning method for face recognition, which uses an effective image representations learned automatically to handle with big data. There are two stages about the deep learning architecture in real-time application. First, on the offline training procedure, we train a stacked denoising autoencoder to learn generic image features from 80 million Tiny images dataset used as auxiliary offline training data. Second, on the supervised object recognition procedure, we construct a five layers as a feature extractor to produce an image representation and an additional classification layer, which we can use to further tune generic image features to adapt to specific objects recognition by online training of corresponding objects. Comparison with the state-of-the-art face recognition methods shows that our deep learning algorithm in face recognition is more accurate and it is a perfect processing tool in big data problem.