Xiaofei Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiaofei Wang has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Bing Zhao
Shandong Key Laboratory of Optoelectronic Sensing Technologies, National-Local Joint Engineering Laboratory for Energy and Environment Fiber Smart Sensing Technologies, Laser Institute, Qilu University of Technology (Shandong Academy of Sciences), 3501 Daxue Road, Changqing District, Jinan 250353, China
3 shared publications - Chen Guan
Shandong Key Laboratory of Optoelectronic Sensing Technologies, National-Local Joint Engineering Laboratory for Energy and Environment Fiber Smart Sensing Technologies, Laser Institute, Qilu University of Technology (Shandong Academy of Sciences), 3501 Daxue Road, Changqing District, Jinan 250353, China
3 shared publications - Zhongqing Jia
Shandong Key Laboratory of Optoelectronic Sensing Technologies, National-Local Joint Engineering Laboratory for Energy and Environment Fiber Smart Sensing Technologies, Laser Institute, Qilu University of Technology (Shandong Academy of Sciences), 3501 Daxue Road, Changqing District, Jinan 250353, China
3 shared publications - Xiaolong Ma
Qilu University of Technology (Shandong Academy of Sciences), Laser Institute, Shandong Academy of Scienses, China-Belarus Belt and Road Joint Laboratory on Intelligent Perception in Extreme Environments, Shandong Key Laboratory of Optoelectronic Sensing Technologies, National-Local joint Engineering Laboratory for Energy and Environment Fiber Smart Sensing Technologies, 3501 Daxue Road, Changqing District, Jinan 250353, China
2 shared publications - Huaxing Yu
Shandong Key Laboratory of Optoelectronic Sensing Technologies, National-Local Joint Engineering Laboratory for Energy and Environment Fiber Smart Sensing Technologies, Laser Institute, Qilu University of Technology (Shandong Academy of Sciences), 3501 Daxue Road, Changqing District, Jinan 250353, China
1 shared publication - Ruizhan Zhai
Qilu University of Technology (Shandong Academy of Sciences), Laser Institute, Shandong Academy of Scienses, China-Belarus Belt and Road Joint Laboratory on Intelligent Perception in Extreme Environments, Shandong Key Laboratory of Optoelectronic Sensing Technologies, National-Local joint Engineering Laboratory for Energy and Environment Fiber Smart Sensing Technologies, 3501 Daxue Road, Changqing District, Jinan 250353, China
1 shared publication
Latest Publications
- Open Access
Stabilizing Defect Visibility Under Overexposure in Fringe-Based Imaging via γ Nonlinearity Analysis
Phase-shifting fringe projection (PSFP) is widely used in industrial inspection and three-dimensional measurement, where nonlinearity of the projector–camera system is traditionally treated as a phase-error source to be calibrated or compensated. In this work, nonlinearity is reinterpreted from an imaging perspective and shown to act as a statistical distortion mechanism that reshapes modulation stability, overexposure behavior, and defect saliency in fringe-based imaging. Building on the intrinsic DC–AC decomposition of phase-shifting demodulation, we analyze how nonlinearity interacts with fringe modulation and frequency-selective transfer. An analytical model reveals that nonlinearity simultaneously suppresses the fringe fundamental and introduces harmonic leakage, leading to systematic compression of mean modulation contrast in high-brightness regions. As a result, correction does not necessarily enhance mean-based defect contrast and may even reduce it, contrary to common intuition. We further demonstrate that the primary benefit of correction lies in statistical stabilization rather than contrast amplification. By introducing modulation-domain saliency formulations and a frequency-domain harmonic energy ratio, a physical link is established between nonlinearity, overexposure, and defect separability. Controlled experiments on highly reflective sheet-metal specimens confirm that while mean-contrast- and SNR-based saliency metrics often decrease after correction, separability-based metrics consistently improve due to reduced nonlinear- and saturation-induced variance. Cross-channel and cross-condition analyses further show that modulation and reflectance images respond differently to correction, yet metric-level separability exhibits consistent improvement across channels. These results clarify the true role of correction in fringe-based inspection and provide theoretical insight and practical guidance for robust defect imaging under nonlinear and near-overexposure conditions.Open AccessStabilizing Defect Visibility Under Overexposure in Fringe-Based Imaging via γ Nonlinearity Analysis
Phase-shifting fringe projection (PSFP) is widely used in industrial inspection and three-dimensional measurement, where nonlinearity of the projector–camera system is traditionally treated as a phase-error source to be calibrated or compensated. In this work, nonlinearity is reinterpreted from an imaging perspective and shown to act as a statistical distortion mechanism that reshapes modulation stability, overexposure behavior, and defect saliency in fringe-based imaging. Building on the intrinsic DC–AC decomposition of phase-shifting demodulation, we analyze how nonlinearity interacts with fringe modulation and frequency-selective transfer. An analytical model reveals that nonlinearity simultaneously suppresses the fringe fundamental and introduces harmonic leakage, leading to systematic compression of mean modulation contrast in high-brightness regions. As a result, correction does not necessarily enhance mean-based defect contrast and may even reduce it, contrary to common intuition. We further demonstrate that the primary benefit of correction lies in statistical stabilization rather than contrast amplification. By introducing modulation-domain saliency formulations and a frequency-domain harmonic energy ratio, a physical link is established between nonlinearity, overexposure, and defect separability. Controlled experiments on highly reflective sheet-metal specimens confirm that while mean-contrast- and SNR-based saliency metrics often decrease after correction, separability-based metrics consistently improve due to reduced nonlinear- and saturation-induced variance. Cross-channel and cross-condition analyses further show that modulation and reflectance images respond differently to correction, yet metric-level separability exhibits consistent improvement across channels. These results clarify the true role of correction in fringe-based inspection and provide theoretical insight and practical guidance for robust defect imaging under nonlinear and near-overexposure conditions. - Open Access
A Co-Designed Framework Combining Dome-Aperture Imaging and Generative AI for Defect Detection on Non-Planar Metal Surfaces
Automated visual inspection of safety-critical metal assemblies such as automotive door lock strikes remains challenging due to their complex three-dimensional geometry, highly reflective surfaces, and scarcity of defect samples. While 3D sensing technologies are often constrained by cost and speed, traditional 2D optical methods struggle with severe imaging artifacts and poor generalization under few-shot conditions. This work constructs a complete system integrating defect imaging, generation, and detection. It proposes an integrated framework through the co-design of an image acquisition system and deep generative models to holistically enhance defect perception capability. First, we develop an imaging system using dome illumination and a small-aperture lens to acquire high-quality images of non-planar metal surfaces. Subsequently, we introduce a dual-stage generation strategy: stage one employs an improved FastGAN with Dynamic Multi-Granularity Fusion Skip-Layer Excitation (DMGF-SLE) and perceptual loss to efficiently generate high-quality local defect patches; stage two utilizes Poisson image editing and an optimized loss function to seamlessly fuse defect patches into specified locations of normal images. This strategy avoids modeling the complete complex background, concentrating computational resources on creating realistic defects. Experiments on a dedicated dataset demonstrate that our method can efficiently generate realistic defect samples under few-shot conditions, achieving 11–24% improvement in Fréchet Inception Distance (FID) scores over baseline models. The generated synthetic data significantly enhances downstream detection performance, increasing YOLOv8’s mAP@50:95 from 50.4% to 60.5%. Beyond proposing individual technical improvements, this research provides a complete, synergistic, and deployable system solution—from physical imaging to algorithmic generation—delivering a computationally efficient and practically viable technical pathway for defect detection in highly reflective, non-planar metal components.
Open AccessA Co-Designed Framework Combining Dome-Aperture Imaging and Generative AI for Defect Detection on Non-Planar Metal Surfaces
Automated visual inspection of safety-critical metal assemblies such as automotive door lock strikes remains challenging due to their complex three-dimensional geometry, highly reflective surfaces, and scarcity of defect samples. While 3D sensing technologies are often constrained by cost and speed, traditional 2D optical methods struggle with severe imaging artifacts and poor generalization under few-shot conditions. This work constructs a complete system integrating defect imaging, generation, and detection. It proposes an integrated framework through the co-design of an image acquisition system and deep generative models to holistically enhance defect perception capability. First, we develop an imaging system using dome illumination and a small-aperture lens to acquire high-quality images of non-planar metal surfaces. Subsequently, we introduce a dual-stage generation strategy: stage one employs an improved FastGAN with Dynamic Multi-Granularity Fusion Skip-Layer Excitation (DMGF-SLE) and perceptual loss to efficiently generate high-quality local defect patches; stage two utilizes Poisson image editing and an optimized loss function to seamlessly fuse defect patches into specified locations of normal images. This strategy avoids modeling the complete complex background, concentrating computational resources on creating realistic defects. Experiments on a dedicated dataset demonstrate that our method can efficiently generate realistic defect samples under few-shot conditions, achieving 11–24% improvement in Fréchet Inception Distance (FID) scores over baseline models. The generated synthetic data significantly enhances downstream detection performance, increasing YOLOv8’s mAP@50:95 from 50.4% to 60.5%. Beyond proposing individual technical improvements, this research provides a complete, synergistic, and deployable system solution—from physical imaging to algorithmic generation—delivering a computationally efficient and practically viable technical pathway for defect detection in highly reflective, non-planar metal components.
- Open Access
A Multi-Parameter Inspection Platform for Transparent Packaging Containers: System Design for Stress, Dimensional, and Defect Detection
With increasing quality demands in pharmaceutical and cosmetic packaging, this work presents a unified inspection platform for transparent ampoules that synergistically integrates stress measurement, dimensional measurement, and surface defect detection. Key innovations include an integrated system architecture, a shared-resource task scheduling mechanism, and an optimized deployment strategy tailored for production-like conditions. Non-contact residual stress measurement is achieved using the photoelastic method, while telecentric imaging combined with subpixel contour extraction enables accurate dimensional assessment. A YOLOv8-based deep learning model efficiently identifies multiple surface defect types, enhancing detection performance without increasing hardware complexity. Experimental validation under laboratory conditions simulating production lines demonstrates a stress measurement error of ±3 nm, dimensional accuracy of ±0.2 mm, and defect detection mAP@0.5 of 90.3%. The platform meets industrial inspection requirements and shows strong scalability and engineering potential. Future work will focus on real-time operation and exploring stress–defect coupling for intelligent quality prediction.
Open AccessA Multi-Parameter Inspection Platform for Transparent Packaging Containers: System Design for Stress, Dimensional, and Defect Detection
With increasing quality demands in pharmaceutical and cosmetic packaging, this work presents a unified inspection platform for transparent ampoules that synergistically integrates stress measurement, dimensional measurement, and surface defect detection. Key innovations include an integrated system architecture, a shared-resource task scheduling mechanism, and an optimized deployment strategy tailored for production-like conditions. Non-contact residual stress measurement is achieved using the photoelastic method, while telecentric imaging combined with subpixel contour extraction enables accurate dimensional assessment. A YOLOv8-based deep learning model efficiently identifies multiple surface defect types, enhancing detection performance without increasing hardware complexity. Experimental validation under laboratory conditions simulating production lines demonstrates a stress measurement error of ±3 nm, dimensional accuracy of ±0.2 mm, and defect detection mAP@0.5 of 90.3%. The platform meets industrial inspection requirements and shows strong scalability and engineering potential. Future work will focus on real-time operation and exploring stress–defect coupling for intelligent quality prediction.