Partial Least Squares for Face Hashing

Abstract : Face identification is an important research topic due to areas such as its application to surveillance, forensics and human-computer interaction. In the past few years, a myriad of methods for face identification has been proposed in the literature, with just a few among them focusing on scalability. In this work, we propose a simple but efficient approach for scalable face identification based on partial least squares (PLS) and random independent hash functions inspired by locality-sensitive hashing (LSH), resulting in the PLS for hashing (PLSH) approach. The original PLSH approach is further extended using feature selection to reduce the computational cost to evaluate the PLS-based hash functions, resulting in the state-of-the-art extended PLSH approach (ePLSH). The proposed approach is evaluated in the dataset FERET and in the dataset FRGCv1. The results show significant reduction in the number of subjects evaluated in the face identification (reduced to 0.3% of the gallery), providing averaged speedups up to 233 times compared to evaluating all subjects in the face gallery and 58 times compared to previous works in the literature.
Liste complète des métadonnées

Cited literature [21 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01399660
Contributor : Guillaume Gravier <>
Submitted on : Sunday, November 20, 2016 - 1:29:50 PM
Last modification on : Thursday, February 7, 2019 - 2:55:21 PM
Document(s) archivé(s) le : Monday, March 27, 2017 - 9:30:45 AM

File

main.pdf
Files produced by the author(s)

Identifiers

Citation

Cassio Dos Santos, Ewa Kijak, Guillaume Gravier, William Robson Schwartz. Partial Least Squares for Face Hashing. Neurocomputing, Elsevier, 2016, 213, pp.34-47. ⟨http://www.sciencedirect.com/science/journal/09252312/213⟩. ⟨10.1016/j.neucom.2016.02.083⟩. ⟨hal-01399660⟩

Share

Metrics

Record views

1207

Files downloads

235