Facial Landmarks Localization using Cascaded Neural Networks

TL;DR

This paper introduces a cascaded deep learning approach for facial landmarks localization, improving accuracy especially in challenging conditions by refining heatmap estimates through successive neural network stages.

Contribution

It presents a novel cascaded neural network architecture that refines facial landmark localization via heatmap estimation and regression, outperforming existing methods.

Findings

Outperforms state-of-the-art schemes in challenging conditions

Effective heatmap-based encoding of landmarks

Improved localization accuracy through cascaded refinement

Abstract

The accurate localization of facial landmarks is at the core of face analysis tasks, such as face recognition and facial expression analysis, to name a few. In this work, we propose a novel localization approach based on a deep learning architecture that utilizes cascaded subnetworks with convolutional neural network units. The cascaded units of the first subnetwork estimate heatmap-based encodings of the landmarks locations, while the cascaded units of the second subnetwork receive as input the output of the corresponding heatmap estimation units, and refine them through regression. The proposed scheme is experimentally shown to compare favorably with contemporary state-of-the-art schemes, especially when applied to images depicting challenging localization conditions.