Next Article in Journal
Data-Driven Bias Correction and Defect Diagnosis Model for In-Service Vehicle Acceleration Measurements
Next Article in Special Issue
A Deep-Learning-based 3D Defect Quantitative Inspection System in CC Products Surface
Previous Article in Journal
Real-Time Facial Affective Computing on Mobile Devices
Previous Article in Special Issue
Hand Gesture Recognition Using Compact CNN via Surface Electromyography Signals
Open AccessArticle

Automatic Fabric Defect Detection Using Cascaded Mixed Feature Pyramid with Guided Localization

State Key Laboratory of Precision Measuring Technology & Instruments, Centre of Micro/Nano Manufacturing Technology—MNMT, Tianjin University, Tianjin 300072, China
*
Author to whom correspondence should be addressed.
Sensors 2020, 20(3), 871; https://doi.org/10.3390/s20030871
Received: 17 January 2020 / Revised: 2 February 2020 / Accepted: 4 February 2020 / Published: 6 February 2020
Generic object detection algorithms for natural images have been proven to have excellent performance. In this paper, fabric defect detection on optical image datasets is systematically studied. In contrast to generic datasets, defect images are multi-scale, noise-filled, and blurred. Back-light intensity would also be sensitive for visual perception. Large-scale fabric defect datasets are collected, selected, and employed to fulfill the requirements of detection in industrial practice in order to address these imbalanced issues. An improved two-stage defect detector is constructed for achieving better generalization. Stacked feature pyramid networks are set up to aggregate cross-scale defect patterns on interpolating mixed depth-wise block in stage one. By sharing feature maps, center-ness and shape branches merges cascaded modules with deformable convolution to filter and refine the proposed guided anchors. After balanced sampling, the proposals are down-sampled by position-sensitive pooling for region of interest, in order to characterize interactions among fabric defect images in stage two. The experiments show that the end-to-end architecture improves the occluded defect performance of region-based object detectors as compared with the current detectors. View Full-Text
Keywords: fabric defect; object detection; mixed kernels; cross-scale; cascaded center-ness; deformable localization fabric defect; object detection; mixed kernels; cross-scale; cascaded center-ness; deformable localization
Show Figures

Figure 1

MDPI and ACS Style

Wu, Y.; Zhang, X.; Fang, F. Automatic Fabric Defect Detection Using Cascaded Mixed Feature Pyramid with Guided Localization. Sensors 2020, 20, 871. https://doi.org/10.3390/s20030871

AMA Style

Wu Y, Zhang X, Fang F. Automatic Fabric Defect Detection Using Cascaded Mixed Feature Pyramid with Guided Localization. Sensors. 2020; 20(3):871. https://doi.org/10.3390/s20030871

Chicago/Turabian Style

Wu, You; Zhang, Xiaodong; Fang, Fengzhou. 2020. "Automatic Fabric Defect Detection Using Cascaded Mixed Feature Pyramid with Guided Localization" Sensors 20, no. 3: 871. https://doi.org/10.3390/s20030871

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop