A Survey on Heterogeneous Face Recognition: Sketch, Infra-red, 3D and Low-resolution

TL;DR

This survey reviews recent advances in heterogeneous face recognition across various modalities, highlighting new features, models, datasets, and benchmarks, and discusses future research directions.

Contribution

It provides a comprehensive overview of techniques, datasets, and benchmarks in HFR, and evaluates the current state and future prospects of the field.

Findings

Extensive review of invariant features and cross-modality models

Compilation of datasets and benchmarks used in HFR research

Discussion of promising future research directions

Abstract

Heterogeneous face recognition (HFR) refers to matching face imagery across different domains. It has received much interest from the research community as a result of its profound implications in law enforcement. A wide variety of new invariant features, cross-modality matching models and heterogeneous datasets being established in recent years. This survey provides a comprehensive review of established techniques and recent developments in HFR. Moreover, we offer a detailed account of datasets and benchmarks commonly used for evaluation. We finish by assessing the state of the field and discussing promising directions for future research.