Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleMarch 2024
Residual shape adaptive dense-nested Unet: Redesign the long lateral skip connections for metal surface tiny defect inspection
Highlights- A pixel-based defect inspection method, called Residual Shape Adaptive Dense-nested Unet, is proposed to obtain the exact shape and location of the defect.
- The Dense-Nested Unet is designed to improve the inspection of tiny defects, ...
The state-of-the-art metal surface defect inspection methods have two problems: (1) they are sensitive to tiny defects because of their extreme small sizes, and (2) they cannot accurately locate the random appeared defects whose semantic ...
- research-articleDecember 2023
Cross-domain object detection by local to global object-aware feature alignment
Neural Computing and Applications (NCAA), Volume 36, Issue 7Mar 2024, Pages 3631–3644https://doi.org/10.1007/s00521-023-09248-8AbstractCross-domain object detection has attracted more and more attention recently. It reduces the gap between the two domains, where the source domain is labeled and the target domain is label-agnostic. The feature alignment is a fundamental step for ...
- research-articleSeptember 2023
Part-to-Surface Mesh Segmentation for Mechanical Models Based on Multi-Stage Clustering
AbstractIn this paper, we propose a part-to-surface mesh segmentation method for engineering models characterized by a multi-stage clustering of surface patches generated by the Variational Shape Approximation (VSA) method. Initially, border ...
Highlights- An effective mesh segmentation that achieves both part- and surface-level partitioning is proposed for mechanical models.
- research-articleMay 2023
Task-balanced distillation for object detection
- Ruining Tang,
- Zhenyu Liu,
- Yangguang Li,
- Yiguo Song,
- Hui Liu,
- Qide Wang,
- Jing Shao,
- Guifang Duan,
- Jianrong Tan
Highlights- A novel HD component is proposed to assist the generation of harmonious predictions for the student.
Mainstream object detectors are commonly constituted of two sub-tasks, including classification and regression tasks, implemented by two parallel heads. This classic design paradigm inevitably leads to inconsistent spatial ...
- research-articleApril 2023
GradCa: Generalizing to unseen domains via gradient calibration
Neurocomputing (NEUROC), Volume 529, Issue CApr 2023, Pages 1–10https://doi.org/10.1016/j.neucom.2023.01.042AbstractIn domain generalization (DG) problem, we hope to train a robust model from multiple source domains and generalize it to unseen domains. However, the trained model can not perform well in the unseen domain since the domain-invariant ...
-
- research-articleMarch 2023
Hierarchical multi-scale network for cross-scale visual defect detection
Journal of Intelligent Manufacturing (SPJIM), Volume 35, Issue 3Mar 2024, Pages 1141–1157https://doi.org/10.1007/s10845-023-02097-1AbstractNowadays, an increasing number of researchers apply deep-learning-based object detection methods to implement visual defect detection in industrial manufacturing. However, large-scale variation in visual defect detection impedes the improvement of ...
- research-articleSeptember 2022
Few-shot defect recognition of metal surfaces via attention-embedding and self-supervised learning
Journal of Intelligent Manufacturing (SPJIM), Volume 34, Issue 8Dec 2023, Pages 3507–3521https://doi.org/10.1007/s10845-022-02022-yAbstractVision-based defect recognition in the metal industry is an important and challenging task. Many mainstream methods based on supervised learning need a large amount of annotated defect data. However, the data acquisition in industrial scenarios is ...
- research-articleNovember 2021
Precise hand–eye calibration method based on spatial distance and epipolar constraints
Robotics and Autonomous Systems (ROAS), Volume 145, Issue CNov 2021https://doi.org/10.1016/j.robot.2021.103868AbstractIn this paper, a new hand–eye calibration method based on spatial distance and epipolar constraints is proposed to obtain the transformation X between the end effector (hand) of the robotic arm and the camera (eye) fixed on the end ...
Highlights- 3D constraint is applied to optimize hand-eye parameters.
- The epipolar ...
- research-articleAugust 2021
Accurate on-line support vector regression incorporated with compensated prior knowledge
Neural Computing and Applications (NCAA), Volume 33, Issue 15Aug 2021, Pages 9005–9023https://doi.org/10.1007/s00521-020-05664-2AbstractWhen the training data required by the data-driven model is insufficient or difficult to cover the sample space completely, incorporating the prior knowledge and prior knowledge compensation module into the support vector regression (PESVR) can ...
- research-articleSeptember 2020
A real-time and precise ellipse detector via edge screening and aggregation
Machine Vision and Applications (MVAA), Volume 31, Issue 7-8Oct 2020https://doi.org/10.1007/s00138-020-01113-1AbstractA fast and precise method for ellipse detection is proposed in this paper. The method aims at clearly removing the lines and curves which are not ellipse edges to improve the ellipse fitting. In arc extraction, the arcs are divided into four ...
- research-articleJune 2020
A fast object registration method for augmented reality assembly with simultaneous determination of multiple 2D-3D correspondences
Robotics and Computer-Integrated Manufacturing (RCIM), Volume 63, Issue CJun 2020https://doi.org/10.1016/j.rcim.2019.101890Highlights- Improve the registration efficiency by keyframe compression.
- Robust object registration with a novel image feature named COLF.
- Parameter configuration and comparison results with conventional methods.
- A system is developed to ...
A fast and robust object registration is one of the fundamental steps of an augmented reality (AR) assembly guidance system. To manage the registration of texture-less objects from monocular images, this paper presents a three-dimensional (3D) ...
- articleOctober 2014
Shape recognition of CAD models via iterative slippage analysis
Computer-Aided Design (CADE), Volume 55October, 2014, Pages 13–25https://doi.org/10.1016/j.cad.2014.04.008A new slippage analysis method for recognizing basic primitive surfaces of CAD models is presented in this paper. Obtaining the exact normal and searching the appropriate local region of each point are found to be the key steps for determining the local ...
- articleOctober 2014
NURBS surface deformation design for complex products by transplanting the surface feature
Engineering with Computers (ENGC), Volume 30, Issue 4October 2014, Pages 599–608https://doi.org/10.1007/s00366-012-0306-6This article addresses the problem of NURBS surface deformation design using surface feature transplantation. To represent the semantic surface feature, a new surface feature representation called normal feature membrane is proposed. In the proposed ...
- articleAugust 2014
Automatic optical phase identification of micro-drill bits based on improved ASM and bag of shape segment in PCB production
Machine Vision and Applications (MVAA), Volume 25, Issue 6August 2014, Pages 1411–1422https://doi.org/10.1007/s00138-014-0627-0This paper addresses the problem of automatic optical phase identification of micro-drill bits for micro-drilling tool inspection in printed circuit board production. To overcome the limitations of conventional active shape model (ASM) on shape modeling ...
- articleMarch 2013
Generalized N-dimensional independent component analysis and its application to multiple feature selection and fusion for image classification
Neurocomputing (NEUROC), Volume 103March, 2013, Pages 186–197https://doi.org/10.1016/j.neucom.2012.09.020We propose a multilinear independent component analysis (ICA) framework called generalized N-dimensional ICA (GND-ICA) by extending the conventional linear ICA based on the multilinear algebra. Unlike the linear ICA that only treats one-dimensional data,...
- research-articleNovember 2012
A Machine Learning-Based Framework for Automatic Visual Inspection of Microdrill Bits in PCB Production
IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews (TSMCPC), Volume 42, Issue 6November 2012, Pages 1679–1689https://doi.org/10.1109/TSMCC.2012.2216260In this paper, an automatic visual inspection scheme with phase identification of microdrill bits in printed circuit board (PCB) production is proposed. Different from conventional methods in which the geometric quantities of microdrill bits are ...
- short-paperNovember 2011
Analysis of cypriot icon faces using ICA-enhanced active shape model representation
MM '11: Proceedings of the 19th ACM international conference on MultimediaNovember 2011, Pages 901–904https://doi.org/10.1145/2072298.2071898Religious iconography is an integral component of the cultural heritage of Cyprus, which was once a part of the great Byzantine empire. On one hand, icons exhibit strict adherence to conventional symbols, poses and apparel. On the other hand, there is a ...
- articleAugust 2010
Automatic optical flank wear measurement of microdrills using level set for cutting plane segmentation
Machine Vision and Applications (MVAA), Volume 21, Issue 5August 2010, Pages 667–676https://doi.org/10.1007/s00138-010-0259-yWe address the problem of automatic optical flank wear measurement for microdrill bits’ inspection. Cutting plane segmentation of microdrill bits is a fundamental step in the measurement. However, in the case of smeared microdrill bits, cutting planes ...
- ArticleNovember 2009
Improved active shape model for automatic optical phase identification of microdrill bits in printed circuit board production
ICIP'09: Proceedings of the 16th IEEE international conference on Image processingNovember 2009, Pages 425–428An improved Active Shape Model (ASM), for automatic optical phase identification of microdrill bits in Printed Circuit Board (PCB) production, is presented. To overcome the limitations of conventional ASM on fitting new instants of microdrill bits, six ...
- ArticleApril 2006
Grid Representation for Efficient Similarity Search in Time Series Databases
ICDEW '06: Proceedings of the 22nd International Conference on Data Engineering WorkshopsApril 2006, Page 123https://doi.org/10.1109/ICDEW.2006.63Widespread interest in time-series similarity search has made more in need of efficient technique, which can reduce dimensionality of the data and then to index it easily using a multidimensional structure. In this paper, we introduce a new technique, ...