A texture-based method for predicting molecular markers and survival outcome in lower grade glioma
Texture-based convolutional neural networks (CNNs) have shown great promise in
predicting various types of cancer, including lower grade glioma (LGG) through radiomics …
predicting various types of cancer, including lower grade glioma (LGG) through radiomics …
Randomized quaternion singular value decomposition for low-rank matrix approximation
Q Liu, S Ling, Z Jia - SIAM Journal on Scientific Computing, 2022 - SIAM
This paper presents a randomized quaternion singular value decomposition (QSVD)
algorithm for low-rank matrix approximation problems, which are widely used in color face …
algorithm for low-rank matrix approximation problems, which are widely used in color face …
Scale fusion light CNN for hyperspectral face recognition with knowledge distillation and attention mechanism
JY Niu, ZH Xie, Y Li, SJ Cheng, JW Fan - Applied Intelligence, 2022 - Springer
Hyperspectral imaging technology, combining traditional imaging and spectroscopy
technologies to simultaneously acquire spatial and spectral information, is deemed to be an …
technologies to simultaneously acquire spatial and spectral information, is deemed to be an …
Structure preserving quaternion biconjugate gradient method
T Li, QW Wang - SIAM Journal on Matrix Analysis and Applications, 2024 - SIAM
This paper considers a novel structure-preserving method for solving non-Hermitian
quaternion linear systems arising from color image deblurred problems. From the quaternion …
quaternion linear systems arising from color image deblurred problems. From the quaternion …
Randomized block Krylov subspace algorithms for low-rank quaternion matrix approximations
A randomized quaternion singular value decomposition algorithm based on block Krylov
iteration (RQSVD-BKI) is presented to solve the low-rank quaternion matrix approximation …
iteration (RQSVD-BKI) is presented to solve the low-rank quaternion matrix approximation …
Quasi non-negative quaternion matrix factorization with application to color face recognition
Y Ke, C Ma, Z Jia, Y Xie, R Liao - Journal of Scientific Computing, 2023 - Springer
To address the non-negativity dropout problem of quaternion models, a novel quasi non-
negative quaternion matrix factorization (QNQMF) model is presented for color image …
negative quaternion matrix factorization (QNQMF) model is presented for color image …
Human ear image recognition method using PCA and Fisherface complementary double feature extraction
Y Wang, K Cheng, S Zhao, E Xu - Journal of Artificial Intelligence …, 2023 - ojs.istp-press.com
Ear recognition is a new kind of biometric identifification technology now. Feature extraction
is a key step in pattern recognition technology, which determines the accuracy of …
is a key step in pattern recognition technology, which determines the accuracy of …
Construction of a smart face recognition model for university libraries based on FaceNet-MMAR algorithm
Y Liu, Y Qu - Plos one, 2024 - journals.plos.org
The continuous development of science and technology has led to the gradual digitization
and intelligence of campus construction. To apply facial recognition technology to construct …
and intelligence of campus construction. To apply facial recognition technology to construct …
Feature autoencoder for detecting adversarial examples
H Ye, X Liu - International Journal of Intelligent Systems, 2022 - Wiley Online Library
Deep neural networks (DNNs) have gained widespread adoption in computer vision.
Unfortunately, state‐of‐the‐art DNNs are vulnerable to adversarial example (AE) attacks …
Unfortunately, state‐of‐the‐art DNNs are vulnerable to adversarial example (AE) attacks …
Data-Driven Bilateral Generalized Two-Dimensional Quaternion Principal Component Analysis with Application to Color Face Recognition
MX Zhao, ZG Jia, DW Gong, Y Zhang - arXiv preprint arXiv:2306.07045, 2023 - arxiv.org
A new data-driven bilateral generalized two-dimensional quaternion principal component
analysis (BiG2DQPCA) is presented to extract the features of matrix samples from both row …
analysis (BiG2DQPCA) is presented to extract the features of matrix samples from both row …