A5031390008- Manufacturing Process and Optimization
- Advanced Measurement and Metrology Techniques
- Advanced Image Processing Techniques
- Advanced machining processes and optimization
- Industrial Vision Systems and Defect Detection
- Additive Manufacturing and 3D Printing Technologies
- Advanced Neural Network Applications
- Advanced Numerical Analysis Techniques
- Video Surveillance and Tracking Methods
- Advanced Vision and Imaging
- Advanced Image Fusion Techniques
- Image Processing Techniques and Applications
- Image and Signal Denoising Methods
- Optical measurement and interference techniques
- 3D Surveying and Cultural Heritage
- 3D Shape Modeling and Analysis
- Image Enhancement Techniques
- Product Development and Customization
- Remote-Sensing Image Classification
- Ultrasonics and Acoustic Wave Propagation
- Additive Manufacturing Materials and Processes
- Visual Attention and Saliency Detection
- Opinion Dynamics and Social Influence
- Optimization and Packing Problems
- Power System Optimization and Stability
Zhejiang University
2016-2025
Zhejiang University of Technology
2021
York University
2020
University of Saskatchewan
2016
Zhejiang Institute of Mechanical and Electrical Engineering
2012
Hunan University
2008-2010
Zhejiang Energy Research Institute
2008
Shanxi Normal University
2008
Sanming University
2008
Chinese Academy of Sciences
2005
In machine vision-based surface inspection tasks, defects are typically considered as local anomalies in homogeneous background. However, industrial workpieces commonly contain complex structures, including hallow regions, welding joints, or rivet holes. Such obvious structural interference will inevitably cause a cluttered background and mislead the classification results. Moreover, sizes of various might change significantly. Last but not least, it is extremely time-consuming scalable to...
Recently, convolutional neural network (CNN) based models have shown great potential in the task of single image superresolution (SISR). However, many state-of-the-art SISR solutions are reproducing some tricks proven effective other vision tasks, such as pursuing a deeper model. In this paper, we propose new solution (named Multi-Receptive-Field Network - MRFN), which outperforms existing three different aspects. First, from receptive field: novel multi-receptive-field (MRF) module is...
This paper reviews the NTIRE 2020 challenge on real image denoising with focus newly introduced dataset, proposed methods and their results. The is a new version of previous 2019 that was based SIDD benchmark. collected validation testing datasets, hence, named SIDD+. has two tracks for quantitatively evaluating performance in (1) Bayer-pattern rawRGB (2) standard RGB (sRGB) color spaces. Each track ~250 registered participants. A total 22 teams, proposing 24 methods, competed final phase...
Infrared images have a wide range of military and civilian applications, including night vision, surveillance, robotics. However, high-resolution infrared detectors are difficult to fabricate their manufacturing cost is expensive. In this paper, we present cascaded architecture deep neural networks with multiple receptive fields increase the spatial resolution by large scale factor (x8). Instead reconstructing image from its low-resolution version using single complex network, key idea our...
This paper reviews the first challenge on high-dynamic range (HDR) imaging that was part of New Trends in Image Restoration and Enhancement (NTIRE) workshop, held conjunction with CVPR 2021. manuscript focuses newly introduced dataset, proposed methods their results. The aims at estimating a HDR image from one or multiple respective low-dynamic (LDR) observations, which might suffer under-or over-exposed regions different sources noise. is composed by two tracks: In Track 1 only single LDR...
Unanticipated and rapid change in facial expression are micro-expression (ME) that hard to hide after an emotionally charged event. Facial microexpressions transient subtle, making identification challenging. Recognition of MEs very crucial the light personal intention phase identification. Previous studies had challenges recognizing ME due complicated spatiotemporal linkage video data. Using ConvMixer architecture, we Proposed a novel technique for microexpression based on convolutional...
This note presents a generalized sufficient condition which guarantees stability of analog neural networks with time delays. The is derived using Lyapunov functional and the criterion stated as: equilibrium delays globally asymptotically stable if product norm connection matrix maximum neuronal gain less than one.
Fusion of images acquired using different sensors generates a single output with enhanced information for high-level visual perception applications. The transformer architecture has demonstrated its powerful ability to obtain important global contextual dependencies multi-modal image fusion tasks. However, transformer-based methods face many critical issues, such as incurring huge computational burdens, limited learn local features, and the difficulty handling arbitrary sizes. To address...
Three-dimensional geometrical models with incorporated surface temperature data provide important information for various applications such as medical imaging, energy auditing, and intelligent robots. In this paper we present a robust method mobile real-time 3D thermographic reconstruction through depth thermal sensor fusion. A multimodal imaging device consisting of camera RGB-D is calibrated geometrically used capturing. Based on the underlying principle that remains against illumination...