A5003049136- Biometric Identification and Security
- Advanced Image and Video Retrieval Techniques
- Advanced Image Fusion Techniques
- Advanced Image Processing Techniques
- Face recognition and analysis
- Image Retrieval and Classification Techniques
- Industrial Vision Systems and Defect Detection
- Human Pose and Action Recognition
- Digital Imaging for Blood Diseases
- Advanced Neural Network Applications
- AI in cancer detection
- Anomaly Detection Techniques and Applications
- Remote-Sensing Image Classification
- COVID-19 diagnosis using AI
- Forensic Fingerprint Detection Methods
- Medical Imaging and Analysis
- Advanced Computational Techniques and Applications
- Medical Imaging Techniques and Applications
- Robotics and Sensor-Based Localization
- Remote Sensing and Land Use
- Face and Expression Recognition
- Power Systems and Technologies
- Engineering Applied Research
- Gait Recognition and Analysis
- Advanced X-ray and CT Imaging
Northwestern Polytechnical University
2021-2024
Yangtze River Delta Physics Research Center (China)
2024
Zhejiang University of Technology
2022
National Chung Cheng University
2021
Guangdong Polytechnic Normal University
2020-2021
University of Strathclyde
2018-2020
Ben-Gurion University of the Negev
2020
This paper reviews the second challenge on spectral reconstruction from RGB images, i.e., recovery of whole- scene hyperspectral (HS) information a 3-channel image. As in previous challenge, two tracks were provided: (i) "Clean" track where HS images are estimated noise-free RGBs, themselves calculated numerically using ground-truth and supplied sensitivity functions (ii) "Real World" track, simulating capture by an uncalibrated unknown camera, recovered noisy JPEG-compressed images. A new,...
To suppress the spread of COVID-19, accurate diagnosis at an early stage is crucial, chest screening with radiography imaging plays important role in addition to real-time reverse transcriptase polymerase chain reaction (RT-PCR) swab test. Due limited data, existing models suffer from incapable feature extraction and poor network convergence optimization. Accordingly, a multi-stage residual network, MSRCovXNet, proposed for effective detection COVID-19 x-ray (CXR) images. As shallow yet...
The pandemic of COVID-19 has become a global crisis in public health, which led to massive number deaths and severe economic degradation. To suppress the spread COVID-19, accurate diagnosis at an early stage is crucial. As popularly used real-time reverse transcriptase polymerase chain reaction (RT-PCR) swab test can be lengthy inaccurate, chest screening with radiography imaging still preferred. However, due limited image data difficulty early-stage diagnosis, existing models suffer from...
Purpose: Treatment delivery verification (DV) is important in the field of intensity modulated radiation therapy (IMRT). While IMRT and image guided (IGRT), allow us to create more conformal plans enables use tighter margins, an erroneously executed plan can have detrimental effects on treatment outcome. The purpose this study develop a DV technique verify TomoTherapy's multileaf collimator (MLC) using onboard mega-voltage CT detectors. Methods: proposed method uses temporal changes MVCT...
An oriented bounding box (OBB) is preferable over a horizontal (HBB) in accurate object detection. Most of existing works utilize two-stage detector for locating the HBB and OBB, respectively, which have suffered from misaligned proposals interference complex backgrounds. To tackle these issues, region interest transformer attention models were proposed, yet they are extremely computationally intensive. this end, we propose semi-anchor-free (SAFDet) detection aerial images, where...
Detecting oriented small objects is a critical task in remote sensing, but the development of high-performance deep learning-based detectors hindered by need for large-scale and well-annotated datasets. The high cost creating these datasets, due to dense numerous distribution objects, significantly limits application such detectors. To address this problem, we propose single-point-based annotation approach (SPA) based on graph cut method. In framework, user annotations act as origin positive...
Band selection has become a significant issue for the efficiency of hyperspectral image (HSI) processing. Although many unsupervised band (UBS) approaches have been developed in last decades, flexible and robust method is still lacking. The lack proper understanding HSI data structure resulted inconsistency outcome UBS. Besides, most UBS methods are either relying on complicated measurements or rather noise sensitive, which hinder determined subset. In this article, an adaptive...
Graph Convolution Network (GCN)-based networks for human action recognition, accepting 3D skeleton sequence as input, have gained much attention and good performances recently. In this paper, joint information enhanced with rich higher-order features/attributes is proposed to lift up their recognition performances. All joints in a spatio-temporal are described terms of set 3-component vectors by referring 3 neighbors the domain. The referred physically connected spatial or corresponded...
Most of the existing hand data collection procedures rely on complex and bulky image acquisition systems, in fact, directly acquired by systems do not have a realistic context, neural network models trained from these perform well real-world situations, especially when people are wearing gloves scenes with changing illumination. However, to improve consistency traditional fusion methods sacrifice authenticity background supervised limited system which cannot generate high quality image....
research-article Share on SF-DPN: A Dual Path Network for Authenticity Detection of the Signed Fingermark Legal Documents Authors: Zhenyu Fang College Computer Science and Technology, Zhejiang University China ChinaSearch about this author , Yongliang Zhang Xiaoguang Qiu Hangzhou Commnet Co., Ltd., Yingkun Xu Zhan Shi Authors Info & Claims ICCAI '22: Proceedings 8th International Conference Computing Artificial IntelligenceMarch 2022 Pages...