http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Stacking PCANet +: An Overly Simplified ConvNets Baseline for Face Recognition
Cheng-Yaw Low,Teoh, Andrew Beng-Jin,Kar-Ann Toh IEEE Signal Processing Society 2017 IEEE signal processing letters Vol.24 No.11
<P>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.</P>
Multi-Fold Gabor, PCA, and ICA Filter Convolution Descriptor for Face Recognition
Low, Cheng-Yaw,Teoh, Andrew Beng-Jin,Ng, Cong-Jie IEEE 2019 IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDE Vol.29 No.1
<P>This paper devises a new means of filter diversification, dubbed multi-fold filter convolution ( <TEX>$\mathcal {M}$</TEX>-FFC), for face recognition. On the assumption that <TEX>$\mathcal {M}$</TEX>-FFC receives single-scale Gabor filters of varying orientations as input, these filters are self-cross convolved by <TEX>$\mathcal {M}$</TEX>-fold to instantiate a filter offspring set. The <TEX>$\mathcal {M}$</TEX>-FFC flexibility also permits cross convolution amongst Gabor filters and other filter banks of profoundly dissimilar traits, e.g., principal component analysis (PCA) filters and independent component analysis (ICA) filters. The 2-FFC of Gabor, PCA, and ICA filters thus yields three offspring sets: 1) Gabor filters solely; 2) Gabor-PCA filters; and 3) Gabor-ICA filters, to render the learning-free and the learning-based 2-FFC descriptors. To facilitate a sensible Gabor filter selection for <TEX>$\mathcal {M}$</TEX>-FFC, the 40 multi-scale, multi-orientation Gabor filters are condensed into eight elementary filters. Aside from that, an average histogram pooling operator is employed to leverage the 2-FFC histogram features, prior to the final whitening PCA compression. The empirical results substantiate that the 2-FFC descriptors prevail over, or on par with, other face descriptors on both identification and verification tasks.</P>
Kernel Deep Regression Network for Touch-Stroke Dynamics Authentication
Chang, Inho,Low, Cheng-Yaw,Choi, Seokmin,Teoh, Andrew Beng-Jin IEEE Signal Processing Society 2018 IEEE signal processing letters Vol.25 No.7
<P>Touch-stroke dynamics is an emerging behavioral biometrics justified feasible for mobile identity management. A touch-stroke dynamics authentication system is composed of a hand-engineered feature extractor and a classifier separately. In this letter, we propose a stacking-based deep learning network that performs feature extraction and classification, collectively dubbed Kernel Deep Regression Network (KDRN). The KDRN is built on multiple kernel ridge regressions (KRR) hierarchically, where each is trained analytically and independently. In principal, KDRN does not mean to learn directly from the raw touch-stroke data like other deep learning models, but it relearns from the pre-extracted features to yield a richer and a relatively more discriminative feature set. Subsequent to that, the authentication is carried out by KRR. Overall, KDRN achieves an equal error rate of 0.013% for intrasession authentication, 0.023% for intersession authentication, and 0.121% for interweek authentication on the Touchlaytics dataset.</P>
Orthogonal filter banks with region Log-TiedRank covariance matrices for face recognition
Ng, Cong Jie,Low, Cheng Yaw,Toh, Kar-Ann,Kim, Jaihie,Teoh, Andrew Beng Jin Elsevier 2018 Journal of visual communication and image represen Vol.55 No.-
<P><B>Abstract</B></P> <P>With the capability of fusing varying features from a specific image region, the Region Covariance Matrices (RCM) image descriptor has been evidenced plausible in face recognition. However, a systematic study for RCM, regarding which features to be fused in particular, remains absent. This paper therefore explores several features derived from the orthogonal filter ensembles, i.e., Identity Transform, Discrete Haar Transform, Discrete Cosine Transform, and Karhunen-Loève Transform, for feature encoding in RCM. Aside from that, we also outline a RCM variant, dubbed Region Log-TiedRank Covariance Matrices (RLTCM) in this paper. The RLTCM descriptor, on average, exhibits dramatic performance gain over RCM as well as state-of-the-art descriptors, especially when probe sets far deviated from the face gallery. Furthermore, we discern that the RLTCM descriptor defined based on Identity Transform, i.e., the simplest form of orthogonal filters, and other learning-free orthogonal filters yield impressive performance on par with the learning-based counterparts.</P>