中文|CAS

logo
banner

Journals & Publications

Journals Publications Papers

Papers

Improved RGB-D-T based face recognition
Dec 26, 2016Author：
PrintText Size A A

Title: Improved RGB-D-T based face recognition
Authors: Simon, MO; Corneanu, C; Nasrollahi, K; Nikisins, O; Escalera, S; Sun, YL; Li, HQ; Sun, ZA; Moeslund, TB; Greitans, M
Author Full Names: Oliu Simon, Marc; Corneanu, Ciprian; Nasrollahi, Kamal; Nikisins, Olegs; Escalera, Sergio; Sun, Yunlian; Li, Haiqing; Sun, Zhenan; Moeslund, Thomas B.; Greitans, Modris
Source: IET BIOMETRICS, 5 (4):297-304; 10.1049/iet-bmt.2015.0057 DEC 2016
Language: English
Abstract: Reliable facial recognition systems are of crucial importance in various applications from entertainment to security. Thanks to the deep-learning concepts introduced in the field, a significant improvement in the performance of the unimodal facial recognition systems has been observed in the recent years. At the same time a multimodal facial recognition is a promising approach. This study combines the latest successes in both directions by applying deep learning convolutional neural networks (CNN) to the multimodal RGB, depth, and thermal (RGB-D-T) based facial recognition problem outperforming previously published results. Furthermore, a late fusion of the CNN-based recognition block with various hand-crafted features (local binary patterns, histograms of oriented gradients, Haar-like rectangular features, histograms of Gabor ordinal measures) is introduced, demonstrating even better recognition performance on a benchmark RGB-D-T database. The obtained results in this study show that the classical engineered features and CNN-based features can complement each other for recognition purposes.
ISSN: 2047-4938
eISSN: 2047-4946
IDS Number: ED3CO
Unique ID: WOS:000388727100004
*Click Here to View Full Record