TU Darmstadt / ULB / TUbiblio

Cross-spectrum thermal to visible face recognition based on cascaded image synthesis

Mallat, Khawla and Damer, Naser and Boutros, Fadi and Kuijper, Arjan and Dugelay, Jean-Luc (2019):
Cross-spectrum thermal to visible face recognition based on cascaded image synthesis.
pp. 1-8, 2019 International Conference on Biometrics (ICB), Crete, Greece, 04.-07. June, 2019, DOI: 10.1109/ICB45273.2019.8987347,
[Conference or Workshop Item]

Abstract

Face synthesis from thermal to visible spectrum is fundamental to perform cross-spectrum face recognition as it simplifies its integration in existing commercial face recognition systems and enables manual face verification. In this paper, a new solution based on cascaded refinement networks is proposed. This method generates visible-like colored images of high visual quality without requiring large amounts of training data. By employing a contextual loss function during training, the proposed network is inherently scale and rotation invariant. We discuss the visual perception of the generated visible-like faces in comparison with recent works. We also provide an objective evaluation in terms of cross-spectrum face recognition, where the generated faces were compared against a gallery in visible spectrum using two state-of-the-art deep learning based face recognition systems. When compared to the recently published TV-GAN solution, the performance of the face recognition systems, OpenFace and LightCNN, was improved by a 42.48% (i.e. from 10.76% to 15.37%) and a 71.43% (i.e. from 33.606% to 57.612%), respectively.

Item Type: Conference or Workshop Item
Erschienen: 2019
Creators: Mallat, Khawla and Damer, Naser and Boutros, Fadi and Kuijper, Arjan and Dugelay, Jean-Luc
Title: Cross-spectrum thermal to visible face recognition based on cascaded image synthesis
Language: English
Abstract:

Face synthesis from thermal to visible spectrum is fundamental to perform cross-spectrum face recognition as it simplifies its integration in existing commercial face recognition systems and enables manual face verification. In this paper, a new solution based on cascaded refinement networks is proposed. This method generates visible-like colored images of high visual quality without requiring large amounts of training data. By employing a contextual loss function during training, the proposed network is inherently scale and rotation invariant. We discuss the visual perception of the generated visible-like faces in comparison with recent works. We also provide an objective evaluation in terms of cross-spectrum face recognition, where the generated faces were compared against a gallery in visible spectrum using two state-of-the-art deep learning based face recognition systems. When compared to the recently published TV-GAN solution, the performance of the face recognition systems, OpenFace and LightCNN, was improved by a 42.48% (i.e. from 10.76% to 15.37%) and a 71.43% (i.e. from 33.606% to 57.612%), respectively.

Uncontrolled Keywords: Biometrics Biometric identification systems Face recognition
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
20 Department of Computer Science > Mathematical and Applied Visual Computing
Event Title: 2019 International Conference on Biometrics (ICB)
Event Location: Crete, Greece
Event Dates: 04.-07. June, 2019
Date Deposited: 17 Apr 2020 10:16
DOI: 10.1109/ICB45273.2019.8987347
Official URL: https://ieeexplore.ieee.org/document/8987347
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details