Accurate Facial Parts Localization and Deep Learning for 3D Facial Expression Recognition

TL;DR

This paper presents a novel 3D facial expression recognition system that accurately extracts facial parts from textured 3D scans and fuses deep features from both texture and depth maps, achieving state-of-the-art results.

Contribution

It introduces a new 4-stage facial parts extraction process and deep feature fusion approach for improved 3D facial expression recognition.

Findings

Effective fusion of texture and depth cues improves accuracy

Achieves state-of-the-art results on BU-3DFE database

Demonstrates robustness of facial parts-based approach

Abstract

Meaningful facial parts can convey key cues for both facial action unit detection and expression prediction. Textured 3D face scan can provide both detailed 3D geometric shape and 2D texture appearance cues of the face which are beneficial for Facial Expression Recognition (FER). However, accurate facial parts extraction as well as their fusion are challenging tasks. In this paper, a novel system for 3D FER is designed based on accurate facial parts extraction and deep feature fusion of facial parts. In particular, each textured 3D face scan is firstly represented as a 2D texture map and a depth map with one-to-one dense correspondence. Then, the facial parts of both texture map and depth map are extracted using a novel 4-stage process consists of facial landmark localization, facial rotation correction, facial resizing, facial parts bounding box extraction and post-processing procedures. Finally, deep fusion Convolutional Neural Networks (CNNs) features of all facial parts are learned from both texture maps and depth maps, respectively and nonlinear SVMs are used for expression prediction. Experiments are conducted on the BU-3DFE database, demonstrating the effectiveness of combing different facial parts, texture and depth cues and reporting the state-of-the-art results in comparison with all existing methods under the same setting.