Cheng-Yaw Low

Cheng-Yaw Low

Department of AI Engineering, Changwon National University, Changwon, Gyeongnam, Republic of Korea

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 April 2019 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
Cheng-Yaw LowCheng-Yaw Low
Cheng-Yaw Low
JPJaewoo Park
Jaewoo Park
Andrew Teoh Beng JinAndrew Teoh Beng Jin
Andrew Teoh Beng Jin
Stacking-based deep neural network (S-DNN) is aggregated with pluralities of basic learning modules, one after another, to synthesize a deep neural network (DNN) alternative for pattern classification. Contrary to the DNNs trained from end to end by backpropagation (BP), each S-DNN layer, that is, a self-learnable module, is to be trained decisively and independently without BP intervention. In this paper, a ridge regression-based S-DNN, dubbed deep analytic network (DAN), along with its kernelization (K-DAN), are devised for multilayer feature relearning from the pre-extracted baseline features and the structured features. Our theoretical formulation demonstrates that DAN/K-DAN relearn by perturbing the intra/interclass variations, apart from diminishing the prediction errors. We scrutinize the DAN/K-DAN performance for pattern classification on datasets of varying domains--faces, handwritten digits, generic objects, to name a few. Unlike the typical BP-optimized DNNs to be trained from gigantic datasets by GPU, we reveal that DAN/K-DAN are trainable using only CPU even for small-scale training sets. Our experimental results show that DAN/K-DAN outperform the present S-DNNs and also the BP-trained DNNs, including multiplayer perceptron, deep belief network, etc., without data augmentation applied.

10 October 2017 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
Cheng-Yaw LowCheng-Yaw Low
Cheng-Yaw Low
Andrew Teoh Beng JinAndrew Teoh Beng Jin
Andrew Teoh Beng Jin
CNCong-Jie Ng
Cong-Jie Ng
This paper devises a new means of filter diversification, dubbed multi-fold filter convolution (M-FFC), for face recognition. On the assumption that M-FFC receives single-scale Gabor filters of varying orientations as input, these filters are self-cross convolved by M-fold to instantiate a filter offspring set. The M-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 M-FFC, the 40 multi-scale, multi-orientation Gabor filters are condensed into 8 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.

5 August 2020 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
Yoon Gyo JungYoon Gyo Jung
Yoon Gyo Jung
Cheng-Yaw LowCheng-Yaw Low
Cheng-Yaw Low
JPJaewoo Park
Jaewoo Park
Andrew Teoh Beng JinAndrew Teoh Beng Jin
Andrew Teoh Beng Jin
Periocular biometric covering the immediate vicinity of human eye is a synergistic alternative to face particularly when the face is masked or occluded. Most present work for periocular recognition in the wild are mainly convolutional neural networks learned based on cross-entropy loss. However, periocular images only capture the least salient face features, and thus suffering from severe intra-class compactness and inter-class dispersion issues for discriminative deep feature learning. Recently, label smoothing regularization (LSR) is discerned capable of diminishing the intra-class variation by minimizing the Kullback-Liebler divergence of a uniform distribution and a network prediction distribution. In this paper, we extend LSR to that of Generalized LSR (GLSR) by learning a pre-task network prediction, in place of the predefined uniform distribution. Extensive experiments on four periocular in the wild datasets disclose that the GSLR-trained networks prevail over the LSR-based counterpart and other most recent the state of the arts. This is supported by our empirical analyses that the embedding periocular features rendered by GLSR results in better class-wise cluster separation than the conventional LSR.

21 January 2021 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
Cheng-Yaw LowCheng-Yaw Low
Cheng-Yaw Low
Andrew Teoh Beng JinAndrew Teoh Beng Jin
Andrew Teoh Beng Jin
JPJaewoo Park
Jaewoo Park
Realistic low-resolution (LR) face images refer to those captured by the real-world surveillance cameras at extreme standoff distances, thereby LR and poor in quality essentially. Owing to severe scarcity of labeled data, a high-capacity deep convolution neural networks (CNN) is hardly trained to confront the realistic LR face recognition (LRFR) challenge. We introduce in this letter a dual-stream mutual information distillation network (MIND-Net), whereby the non-identity specific mutual information (MI) characterized by generic face features coexistent on realistic and synthetic LR face images are distilled to render a resolution-invariant embedding space for LRFR. For a thorough analysis, we quantify the degree of MI distillation in terms normalized MI index. Our experimental results on the realistic LR face datasets substantiate that the MIND-Net instances assembled from the pre-learned CNNs stand out from the baselines and other state of the arts by a notable margin.

11 July 2024 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Open access
KAKyeongjin Ahn
Kyeongjin Ahn
SLSeungeon Lee
Seungeon Lee
SHSungwon Han
Sungwon Han
Cheng-Yaw LowCheng-Yaw Low
Cheng-Yaw Low
MCMeeyoung Cha
Meeyoung Cha
While advances in deep learning have enabled novel applications in various fields, face recognition in open-set scenarios remains a complex task, owing to the challenges posed by the extensive volume of low-quality face images. We introduce a new approach for recognizing faces in unconstrained open-set settings by leveraging uncertainty-aware embeddings through contrastive learning. Our model, called UCFace, effectively regulates the contribution of each face image based on the face uncertainty derived from image quality as an inverse proxy. Face embeddings are reinterpreted as a probabilistic distribution within the embedding space, where the degree of sharpness (i.e., distribution concentration) reflects the underlying uncertainty and probability density is used as a similarity metric to facilitate contrastive learning. Experiments on a wide range of face datasets, including those with high, mixed, and real-world low-resolution face images, demonstrate that UCFace enhances open-set face recognition performance by integrating the aspect of uncertainty.

11 June 2018 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
ICInho Chang
Inho Chang
Cheng-Yaw LowCheng-Yaw Low
Cheng-Yaw Low
SCSeokmin Choi
Seokmin Choi
Andrew Teoh Beng JinAndrew Teoh Beng Jin
Andrew Teoh Beng Jin
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.