Liming Chen

Liming Chen

Auto-generated profile, based on publicly available information

Liming Chen

Fitow (Tianjin) Detection Technology Co Ltd, Tianjin 300387, P. R. China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 May 2024 in Journal of Visual Communication and Image Representation
Verified
Journal Article
Closed access
SYShuai Yang
Shuai Yang
ZWZibei Wang
Zibei Wang
GWGuangao Wang
Guangao Wang
YKYongzhen Ke
Yongzhen Ke
FQFan Qin
Fan Qin
LCLiming Chen
Liming Chen

8 May 2026 in Measurement Science and Technology
Verified
Journal Article
Closed access
MWMinxue Wang
Minxue Wang
MCMenghang Chen
Menghang Chen
LCLiming Chen
Liming Chen
AZAng Zhang
Ang Zhang
XLXu Li
Xu Li
XZXiaodong Zhang
Xiaodong Zhang
Industrial laser profile sensor requires linear motion module to acquire three-dimensional data. Accurate calibration of their relative pose is crucial for applications such as 3D contour scanning of mechanical parts, point cloud registration, defect detection, and precision measurement. This paper presents a novel motion vector calibration method that is applicable to arbitrary mounting orientations for an industrial translational laser profile sensor system, offering high accuracy and efficiency. An innovative calibration device, featuring multiple planar surfaces at distinct poses, was designed and manufactured. The relative pose between the laser profile sensor and the calibration device was calibrated from a single measurement using a proposed four-feature-point algorithm without any secondary camera. Subsequently, with the linear motion module moving to capture a sequence of profiles, a hybrid global–local nonlinear optimization method was employed to calibrate the motion vector between the sensor and the module. Experimental validation demonstrated that this method achieves an overall measurement accuracy of less than 0.030 mm and a repeatability within 0.005 mm over a 100 mm travel range, confirming its feasibility and stability for high-precision industrial applications.

1 July 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
KTKai Tian
Kai Tian
DMDehao Meng
Dehao Meng
WKWang Kai
Wang Kai
YKYongzhen Ke
Yongzhen Ke
SYShuai Yang
Shuai Yang
XZXiaodong Zhang
Xiaodong Zhang
Automatic surface defect rating is vital for industrial quality control but faces challenges in handling diverse defect scales and learning ordinal relationships with ambiguous boundaries. To address the inherent contradiction between scale and ordinality processing, we propose CFG-Net (Coarse-to-Fine Grouping Network), which adopts a "divide-and-conquer" strategy to decouple multi-scale rating tasks. CFG-Net uses a dual-stream grouping-gating module with lossless pixel unshuffle for initial-scale grouping and localization. Defects are dynamically dispatched to specialized branches: a low-level branch using anchor difference to amplify weak anomaly signals, and a high-level branch using deformable convolutions to fit irregular contours. Features are integrated via an adaptive ordinal fusion module guided by gating probabilities. Furthermore, we introduce a Multi-Margin N-Pair (MMNP) contrastive loss to construct an ordinal manifold space that strictly aligns with defect severity levels. Experimental results on real-world industrial datasets show that CFG-Net effectively resolves mixed-scale conflicts, achieving 97.2% group classification accuracy and 65.7% fine-grained rating accuracy. With a Mean Absolute Error (MAE) of 0.45 and Mean Squared Error (MSE) of 0.58, the proposed architecture demonstrates high precision and engineering robustness for complex, multi-scale defect rating tasks.

17 June 2026 in International Journal of Software Engineering and Knowledge Engineering
Verified
Journal Article
Closed access
YHYongkun Han
Yongkun Han
WKWang Kai
Wang Kai
LCLiming Chen
Liming Chen
YKYongzhen Ke
Yongzhen Ke
SYShuai Yang
Shuai Yang
KTKai Tian
Kai Tian