.png){kind=icon}
.png){kind=icon}
Return
Stacking PCANet plus : An Overly Simplified ConvNets Baseline for Face Recognition
.png){kind=icon}
PRE
AI
DOI：10.1109/LSP.2017.2749763.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Keywords:
Face recognition
principal component analysis (PCA) filters
PCA network (PCANet)
stacking-based convolutional neural network (CNN)
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
9.6
Papers:
1.1W
Citations:
1.7W