Cascaded Face Alignment via Intimacy Definition Feature

TL;DR

This paper introduces a fast, accurate face alignment method using a novel local feature called intimacy definition feature (IDF), which outperforms existing features in efficiency and accuracy, and significantly reduces memory usage.

Contribution

The paper proposes a new local feature (IDF) for face alignment that is more discriminative, efficient, and compact than existing features, enabling faster and more accurate alignment.

Findings

Achieves state-of-the-art performance on challenging datasets.

About two times speed-up compared to LBF-based algorithms.

Over 20% improvement in alignment accuracy.

Abstract

In this paper, we present a random-forest based fast cascaded regression model for face alignment, via a novel local feature. Our proposed local lightweight feature, namely intimacy definition feature (IDF), is more discriminative than landmark pose-indexed feature, more efficient than histogram of oriented gradients (HOG) feature and scale-invariant feature transform (SIFT) feature, and more compact than the local binary feature (LBF). Experimental results show that our approach achieves state-of-the-art performance when tested on the most challenging datasets. Compared with an LBF-based algorithm, our method can achieve about two times the speed-up and more than 20% improvement, in terms of alignment accuracy measurement, and save an order of magnitude of memory requirement.