Image quality assessment to enhance infrared face recognition

Camilo G.Rodriguez Pulecio, Hernan D. Benitez-Restrepo, Alan C. Bovik

Producción: Capítulo del libro/informe/acta de congresoContribución a la conferenciarevisión exhaustiva

7 Citas (Scopus)

Resumen

Automatic quality evaluation of infrared images has not been researched as extensively as for images of the visible spectrum. Moreover, there is a lack of studies on the influence of degradation of image quality on the performance of computer vision tasks operating on thermal images. Here, we quantify the impact of common image distortions on infrared face recognition, and present a method for aggregating perceptual quality-aware features to improve the identification rates. We use Natural Scene Statistics (NSS) to detect degradation of infrared images, and to adapt the face recognition algorithm to the quality of the test image. The proposed approach applied to a face identification algorithm based on thermal signatures yielded an improvement of rank one recognition rates between 11% and 19%. These results confirm the relevance of image quality assessment for improving biometric identification systems that use thermal images.

Idioma originalInglés
Título de la publicación alojada2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings
EditorialIEEE Computer Society
Páginas805-809
Número de páginas5
ISBN (versión digital)9781509021758
DOI
EstadoPublicada - 02 jul. 2017
Evento24th IEEE International Conference on Image Processing, ICIP 2017 - Beijing, China
Duración: 17 sep. 201720 sep. 2017

Serie de la publicación

NombreProceedings - International Conference on Image Processing, ICIP
Volumen2017-September
ISSN (versión impresa)1522-4880

Conferencia

Conferencia24th IEEE International Conference on Image Processing, ICIP 2017
País/TerritorioChina
CiudadBeijing
Período17/09/1720/09/17

Huella

Profundice en los temas de investigación de 'Image quality assessment to enhance infrared face recognition'. En conjunto forman una huella única.

Citar esto