Improving the evidential value of low-quality face images with aggregation of deep neural network embeddings

•An effective strategy to improve face recognition of low-quality facial images.•Validation of this strategy under forensically relevant challenging scenarios.•Cleaned versions of the BFW and Adience datasets are provided.•A new verification protocol for the Quis-Campi dataset. In forensic facial co...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Science & justice Ročník 64; číslo 5; s. 509 - 520
Hlavní autoři: Ribeiro, Rafael Oliveira, Neves, João C., Ruifrok, Arnout, de Barros Vidal, Flavio
Médium: Journal Article
Jazyk:angličtina
Vydáno: England Elsevier B.V 01.09.2024
Témata:
Embedding aggregation
Face comparisons
Forensic evaluation
Likelihood ratio
Pathology
Likelihood ratio
Forensic evaluation
Face comparisons
Embedding aggregation
ISSN:1355-0306, 1876-4452, 1876-4452
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:•An effective strategy to improve face recognition of low-quality facial images.•Validation of this strategy under forensically relevant challenging scenarios.•Cleaned versions of the BFW and Adience datasets are provided.•A new verification protocol for the Quis-Campi dataset. In forensic facial comparison, questioned-source images are usually captured in uncontrolled environments, with non-uniform lighting, and from non-cooperative subjects. The poor quality of such material usually compromises their value as evidence in legal proceedings. On the other hand, in forensic casework, multiple images of the person of interest are usually available. In this paper, we propose to aggregate deep neural network embeddings from various images of the same person to improve the performance in forensic comparison of facial images. We observe significant performance improvements, especially for low-quality images. Further improvements are obtained by aggregating embeddings of more images and by applying quality-weighted aggregation. We demonstrate the benefits of this approach in forensic evaluation settings with the development and validation of common-source likelihood ratio systems and report improvements in Cllr both for CCTV images and for social media images.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1355-0306
1876-4452
1876-4452
DOI:10.1016/j.scijus.2024.07.006