DeepAI AI Chat
Log In Sign Up

Targeting Ultimate Accuracy: Face Recognition via Deep Embedding

by   Jingtuo Liu, et al.

Face Recognition has been studied for many decades. As opposed to traditional hand-crafted features such as LBP and HOG, much more sophisticated features can be learned automatically by deep learning methods in a data-driven way. In this paper, we propose a two-stage approach that combines a multi-patch deep CNN and deep metric learning, which extracts low dimensional but very discriminative features for face verification and recognition. Experiments show that this method outperforms other state-of-the-art methods on LFW dataset, achieving 99.77 other two more practical protocols. This paper also discusses the importance of data size and the number of patches, showing a clear path to practical high-performance face recognition systems in real world.


page 3

page 4


Face Recognition: From Traditional to Deep Learning Methods

Starting in the seventies, face recognition has become one of the most r...

ScaleFace: Uncertainty-aware Deep Metric Learning

The performance of modern deep learning-based systems dramatically depen...

Discriminant Patch Representation for RGB-D Face Recognition Using Convolutional Neural Networks

This paper focuses on designing data-driven models to learn a discrimina...

Triplet Similarity Embedding for Face Verification

In this work, we present an unconstrained face verification algorithm an...

Are Adaptive Face Recognition Systems still Necessary? Experiments on the APE Dataset

In the last five years, deep learning methods, in particular CNN, have a...

Data-specific Adaptive Threshold for Face Recognition and Authentication

Many face recognition systems boost the performance using deep learning ...

Face Identification with Second-Order Pooling

Automatic face recognition has received significant performance improvem...