Journal
IEEE TRANSACTIONS ON IMAGE PROCESSING
Volume 29, Issue -, Pages 3270-3281Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2019.2958404
Keywords
Deep convolutional neural network (DCNN); Gabor face representations; Gabor DCNN (GDCNN) ensemble; face recognition (FR); confidence based majority voting
Funding
- Hankuk University of Foreign Studies Research Fund
- National Research Foundation of Korea (NRF) - Ministry of Education [2018R1D1A1A09082615]
- Marine Industry Technology Development Project, named the Development of Artificial Intelligence based Satellite Image Restoration and Prediction Technology [20190228]
- National Research Foundation of Korea [2018R1D1A1A09082615] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)
Ask authors/readers for more resources
Most DCNN-based FR approaches typically employ grayscale or RGB color images as input representations of DCNN architectures. However, other effective face representation methods have been developed and incorporated into current practical FR systems. In light of this fact, the focus of our study is to employ Gabor face representations in the design of DCNN-based FR frameworks to improve FR performance. To this end, we develop a novel Gabor DCNN (GDCNN) ensemble method that effectively applies different and multiple Gabor face representations as inputs during the training and testing phases of a DCNN for FR applications. The proposed GDCNN ensemble method primarily consists of two parts: 1) GDCNN ensemble construction and 2) GDCNN ensemble combination. The goal of the former part is to build an ensemble of GDCNN members (i.e., base models), each learned with a particular type of Gabor face representation. The objective of the latter part is to adaptively combine multiple FR outputs of individual GDCNN members. We perform extensive experiments to evaluate our proposed method on four public face databases (DBs) using the associated standard evaluation protocols. Experimental results demonstrate that our approach exhibits significantly better FR performance than typical DCNN-based approaches that rely only on grayscale or color face images as input representations. In addition, the feasibility of our proposed GDCNN ensemble has been successfully demonstrated by making comparisons with other state-of-the-art DCNN-based FR methods.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available