Machine vision systems based on deep learning play an important role in the industrial Internet of things (IIoT) and Industry 4.0 applications, especially for product quality monitoring. Fabric defect detection is an important task in the industrial production of textiles and is crucial for product quality assurance. In actual production, the detection of many small and weak target defects remains challenging. Furthermore, industrial production requires high production rates and small model sizes in practice. This study proposes a lightweight segmentation system that meets real-time industrial production requirements. Herein, first, the defect sample image was repaired based on the image repair mechanism of the generative adversarial network model. Then, the difference between the defect sample and the repaired sample was obtained and subsequent processing, such as denoising and enhancement, was done. Finally, the defect areas were segmented. Our model was specifically designed for the segmentation of weak and small defects. This was achieved through adversarial training, optimization of an objective function, and image processing. Experimental comparisons show that the intersection over union of the three different datasets is 77.84%, 77.85%, and 73.6% and that our model is superior to the conventional semantic segmentation model. Furthermore, our model has good image restoration quality with a low mean absolute error and high structural similarity index. Additionally, our model is lightweight, has good real-time performance, and is suitable for applications in the IIoT and industrial production lines, such as embedded systems.
Automatic and intelligent railway locomotive inspection and maintenance are fundamental issues in high-speed rail applications and intelligent transportation system (ITS). Traditional locomotive equipment inspection is carried out manually on-site by workers, and the task is exhausting, cumbersome, and unsafe. Based on computer vision and machine learning, this paper presents an approach to the automatic detection of the locomotive speed sensor equipment, an important device in locomotives. Challenges to the detection of speed sensor mainly concerns complex background, motion blur, muddy noise, and variable shapes. In this paper, a cascade learning framework is proposed, which includes two learning stages: target localization and speed sensor detection, to reduce the complexity of the research object and solve the imbalance of samples. In the first stage, histogram of oriented gradient feature and support vector machine (HOG-SVM) model is used for multi-scale detection. Then, an improved LeNet-5 model is adopted in the second stage. To solve the problem of the imbalance of positive and negative samples of speed sensor, a combination strategy which draws on four individual classifiers is designed to construct an ensemble of classifier for recognition, and the results of three different algorithms are compared. The experimental results demonstrate that our approach is effective and robust with respect to changes in speed sensor patterns for robust equipment identification. INDEX TERMS Cascade learning, speed sensor detection, imbalanced data, ensemble learning.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.