A Probabilistic Adaptive Search System for Exploring the Face Space

TL;DR

This paper introduces a probabilistic evolutionary search method for facial composite systems, leveraging Bayesian optimization and skew-normal distributions to efficiently explore the large, unstructured face space for improved face recall assistance.

Contribution

It presents a novel evolutionary approach using skew-normal distributions as an acquisition function, enhancing face space exploration for facial composite systems.

Findings

The method provides more realistic and conservative face suggestions.

It improves search efficiency in large, unstructured face spaces.

The approach is adaptable for real-world facial composite applications.

Abstract

Face recall is a basic human cognitive process performed routinely, e.g., when meeting someone and determining if we have met that person before. Assisting a subject during face recall by suggesting candidate faces can be challenging. One of the reasons is that the search space - the face space - is quite large and lacks structure. A commercial application of face recall is facial composite systems - such as Identikit, PhotoFIT, and CD-FIT - where a witness searches for an image of a face that resembles his memory of a particular offender. The inherent uncertainty and cost in the evaluation of the objective function, the large size and lack of structure of the search space, and the unavailability of the gradient concept makes this problem inappropriate for traditional optimization methods. In this paper we propose a novel evolutionary approach for searching the face space that can be used as a facial composite system. The approach is inspired by methods of Bayesian optimization and differs from other applications in the use of the skew-normal distribution as its acquisition function. This choice of acquisition function provides greater granularity, with regularized, conservative, and realistic results.