Active Testing for Face Detection and Localization

TL;DR

This paper introduces an active testing method for face detection that employs a hierarchical model and mutual information heuristic to significantly reduce computation while maintaining detection accuracy.

Contribution

The paper presents a novel search technique that improves face localization efficiency using hierarchical modeling and information gain heuristics.

Findings

Exponential reduction in computation compared to sliding window methods.

Maintains similar face detection performance levels.

Efficient face localization in images.

Abstract

We provide a novel search technique, which uses a hierarchical model and a mutual information gain heuristic to efficiently prune the search space when localizing faces in images. We show exponential gains in computation over traditional sliding window approaches, while keeping similar performance levels.