Cross-level multi-modal features learning with transformer for rgb-d object recognition

Y Zhang, M Yin, H Wang, C Hua - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Object recognition, one of the main goals of robot vision, is a vital prerequisite for service
robots to perform domestic tasks. Thanks to the rich sense of information provided by RGB-D …

An efficient fuzzy inference system based approximated anisotropic diffusion for image de-noising

N Thakur, NU Khan, SD Sharma - Cluster Computing, 2022 - Springer
Fuzzy system is proven to be one of the well-effective approximation tool in soft computing
techniques. The image de-noising in modern multimedia system is strongly demanded issue …

Dual Discriminative Low-Rank Projection Learning for Robust Image Classification

T Su, D Feng, M Wang, M Chen - IEEE Transactions on Circuits …, 2023 - ieeexplore.ieee.org
Numerous methods have exploited projection learning to extract low-dimensional features
for image classification. Some projection learning methods integrate low-rank matrix …

Multi-Resolution Discrete Cosine Transform Fusion Technique Face Recognition Model

BM AlFawwaz, A AL-Shatnawi, F Al-Saqqar, M Nusir - Data, 2022 - mdpi.com
This work presents a Multi-Resolution Discrete Cosine Transform (MDCT) fusion technique
Fusion Feature-Level Face Recognition Model (FFLFRM) comprising face detection, feature …

Novel Algorithm for Baseline Detection of Offline Arabic Handwritten Text Recognition

AMA Al Masri, MS Hitam… - … in Applied Sciences …, 2024 - semarakilmu.com.my
The baseline detection is one of the challenging tasks in the pre-processing stage of an
online Arabic handwritten text recognition. The challenges include text skewness, touching …

[PDF][PDF] Multi-Resolution Discrete Cosine Transform Fusion Technique Face Recognition Model. Data 2022, 7, 80

BM AlFawwaz, A AL-Shatnawi, F Al-Saqqar, M Nusir - 2022 - academia.edu
This work presents a Multi-Resolution Discrete Cosine Transform (MDCT) fusion technique
Fusion Feature-Level Face Recognition Model (FFLFRM) comprising face detection, feature …