A Defect Inspection for Explosive Cartridge Using an Improved Visual Attention and Image-Weighted Eigenvalue

Liang, Xu; Xu, Haibo; Li, Xiuxi; Pan, Ming

doi:10.1109/tim.2019.2912237

Cited by 15 publications

(4 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, the primary application of our MINet is strip steel surface defect detection. Moreover, as a preprocessing method, SOD-based defect detection [1], [2] has also been successfully employed in various industrial tasks, such as defect classification [43] and defect inspection [44]. Therefore, our MINet can also be applied to the aforementioned industrial tasks.…”

Section: Practical Implications and Challengesmentioning

confidence: 99%

Two-Stage Edge Reuse Network for Salient Object Detection of Strip Steel Surface Defects

Han

2022

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

The automated surface defect detection is a fundamental task in industrial production, and the existing saliencybased works overcome the challenging scenes and give promising detection results. However, the cutting-edge efforts often suffer from large parameter size, heavy computational cost, and slow inference speed, which heavily limits the practical applications. To this end, we devise a multi-scale interactive (MI) module, which employs depthwise convolution (DWConv) and pointwise convolution (PWConv) to independently extract and interactively fuse features of different scales, respectively. Particularly, the MI module can provide satisfactory characterization for defect regions with fewer parameters. Embarking on this module, we propose a lightweight Multi-scale Interactive Network (MINet) to conduct real-time salient object detection of strip steel surface defects. Comprehensive experimental results on SD-Saliency-900 dataset, which contains three kinds of strip steel surface defect detection images (i.e., inclusion, patches, and scratches), demonstrate that the proposed MINet presents comparable detection accuracy with the state-of-the-art methods while running at a GPU speed of 721FPS and a CPU speed of 6.3FPS for 368×368 images with only 0.28M parameters. The code is available at https://github.com/Kunye-Shen/MINet.

show abstract

Section: Practical Implications and Challengesmentioning

confidence: 99%

Two-Stage Edge Reuse Network for Salient Object Detection of Strip Steel Surface Defects

Han

2022

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

show abstract

“…Preprocessing filters noise and differentiates various areas in input images acquired by a camera in an industrial setting. The Otsu threshold algorithm is a kind of common segmentation technique in image processing [60] and widely used in character classification [61,62]. It is applied during image binarization.…”

Section: ) Image Preprocessingmentioning

confidence: 99%

A Hybrid Character Recognition Approach Using Fuzzy Logic and Stroke Bayesian Program Learning With Naïve Bayes in Industrial Environments

Liang

Wang

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Automated character recognition is critical for reading and tracking data in a variety of fields. It is particularly challenging in industrial settings since information may be printed on the surface of various materials with complex and uneven shapes, causing overlapping, obstructing, and distorting characters. We propose a hybrid character recognition approach using fuzzy logic and stroke Bayesian program learning with naï ve Bayes. During character segmentation, touching characters are separated using support vector machines and a three-feature fuzzy segmentation strategy that uses particle swarm optimization. This approach includes a new methodology for stroke presentation and extraction using a prebuilt primitive-stroke library containing prior knowledge. During character recognition, a conceptual character model is constructed using stroke Bayesian program learning. Monte Carlo Markov chain sampling is used to produce a fitting model for each character. This model predicts character classification by calculating the probability that a target sample belongs to a training set. To this end, naï ve Bayes effectively discerns extremely similar characters. We evaluate our method experimentally using a database of industrial images and the NIST dataset. Our method outperforms existing state-of-the art methods.

show abstract

“…Wu et al [16] propose a high-sensitivity magnetic flux leakage method based on magnetic induction head for the detection of tiny cracks in bearing rings. Xu et al [17] propose a new multidefect detection method based on a combination of an improved visual attention model and image partitioning-weighted eigenvalue for surface defects of explosive cartridge in the automatic sorting process that are of small area, irregular shape, and random distribution. Kong et al [18] propose a unified framework for detecting defects in planar industrial products or planar surfaces of nonplanar products based on a template-matching strategy.…”

Section: Introductionmentioning

confidence: 99%

Bearing Defect Detection with Unsupervised Neural Networks

Zuo

Danchao³

et al. 2021

Shock and Vibration

View full text Add to dashboard Cite

Bearings always suffer from surface defects, such as scratches, black spots, and pits. Those surface defects have great effects on the quality and service life of bearings. Therefore, the defect detection of the bearing has always been the focus of the bearing quality control. Deep learning has been successfully applied to the objection detection due to its excellent performance. However, it is difficult to realize automatic detection of bearing surface defects based on data-driven-based deep learning due to few samples data of bearing defects on the actual production line. Sample preprocessing algorithm based on normalized sample symmetry of bearing is adopted to greatly increase the number of samples. Two different convolutional neural networks, supervised networks and unsupervised networks, are tested separately for the bearing defect detection. The first experiment adopts the supervised networks, and ResNet neural networks are selected as the supervised networks in this experiment. The experiment result shows that the AUC of the model is 0.8567, which is low for the actual use. Also, the positive and negative samples should be labelled manually. To improve the AUC of the model and the flexibility of the samples labelling, a new unsupervised neural network based on autoencoder networks is proposed. Gradients of the unlabeled data are used as labels, and autoencoder networks are created with U-net to predict the output. In the second experiment, positive samples of the supervised experiment are used as the training set. The experiment of the unsupervised neural networks shows that the AUC of the model is 0.9721. In this experiment, the AUC is higher than the first experiment, but the positive samples must be selected. To overcome this shortage, the dataset of the third experiment is the same as the supervised experiment, where all the positive and negative samples are mixed together, which means that there is no need to label the samples. This experiment shows that the AUC of the model is 0.9623. Although the AUC is slightly lower than that of the second experiment, the AUC is high enough for actual use. The experiment results demonstrate the feasibility and superiority of the proposed unsupervised networks.

show abstract

A Defect Inspection for Explosive Cartridge Using an Improved Visual Attention and Image-Weighted Eigenvalue

Cited by 15 publications

References 38 publications

Two-Stage Edge Reuse Network for Salient Object Detection of Strip Steel Surface Defects

Two-Stage Edge Reuse Network for Salient Object Detection of Strip Steel Surface Defects

A Hybrid Character Recognition Approach Using Fuzzy Logic and Stroke Bayesian Program Learning With Naïve Bayes in Industrial Environments

Bearing Defect Detection with Unsupervised Neural Networks

Contact Info

Product

Resources

About