Back to Search
Start Over
Stacking PCANet +: An Overly Simplified ConvNets Baseline for Face Recognition.
- Source :
- IEEE Signal Processing Letters; Nov2017, Vol. 24 Issue 11, p1581-1585, 5p
- Publication Year :
- 2017
-
Abstract
- The principal component analysis network (PCANet) is asserted as a parsimonious stacking-based convolutional neural networks (CNNs) instance for generic object recognition including face. However, to be regarded a CNN resemblance, PCANet lacks a nonlinearity in between two successive convolutional layers. The multilayer PCANet (by neglecting the nonlinearity pre-requisite) is also deemed far-fetched for the network depth beyond two, due to feature dimensionality explosion. We thus devise a PCANet alternative, dubbed PCANet+ in this letter, to untangle these constraints. To be more precise, conforming to the CNN essentials, PCANet+ conveys a mean-pooling unit manipulating each feature map. On top of that, we streamline the PCANet topology to permit a deep construction with an expanded PCA filter ensemble. We scrutinize the PCANet+ performance using face recognition technology and other two faces in the wild datasets, namely, labeled faces in the wild and YouTube faces. The experimental results reveal that the PCANet+ descriptor prevails over its predecessor and other stacking-based descriptors in face identification and verification, serving a baseline for ConvNets. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 10709908
- Volume :
- 24
- Issue :
- 11
- Database :
- Complementary Index
- Journal :
- IEEE Signal Processing Letters
- Publication Type :
- Academic Journal
- Accession number :
- 125755062
- Full Text :
- https://doi.org/10.1109/LSP.2017.2749763