Fast Landmark Localization with 3D Component Reconstruction and CNN for Cross-Pose Recognition

TL;DR

This paper introduces two novel cross-pose face recognition methods: one using 3D facial component reconstruction and the other employing a CNN, both evaluated extensively against state-of-the-art techniques.

Contribution

It proposes a 3D component-based face recognition approach and a revised VGG CNN, with a hierarchical landmark detection method, advancing cross-pose face recognition techniques.

Findings

3D component reconstruction improves recognition accuracy.

CNN-based approach performs well as classifier and feature extractor.

Fast landmark localization enhances overall recognition efficiency.

Abstract

Two approaches are proposed for cross-pose face recognition, one is based on the 3D reconstruction of facial components and the other is based on the deep Convolutional Neural Network (CNN). Unlike most 3D approaches that consider holistic faces, the proposed approach considers 3D facial components. It segments a 2D gallery face into components, reconstructs the 3D surface for each component, and recognizes a probe face by component features. The segmentation is based on the landmarks located by a hierarchical algorithm that combines the Faster R-CNN for face detection and the Reduced Tree Structured Model for landmark localization. The core part of the CNN-based approach is a revised VGG network. We study the performances with different settings on the training set, including the synthesized data from 3D reconstruction, the real-life data from an in-the-wild database, and both types of data combined. We investigate the performances of the network when it is employed as a classifier or designed as a feature extractor. The two recognition approaches and the fast landmark localization are evaluated in extensive experiments, and compared to stateof-the-art methods to demonstrate their efficacy.