An Adaptive Image Segmentation Network for Surface Defect Detection

Liu, Taiheng; He, Zhaoshui; Lin, Zhijie; Cao, Guangzhong; Su, Wenqing; Xie, Shengli

doi:10.1109/tnnls.2022.3230426

Cited by 31 publications

(4 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Defect segmentation [19,20] provides intricate insights into defect attributes, size, shape, and precise extent via pixel-level outlining. It is effective for capturing irregular or non-uniform defects that lack predefined shapes.…”

Section: Defect Segmentationmentioning

confidence: 99%

An Attention-Augmented Convolutional Neural Network With Focal Loss for Mixed-Type Wafer Defect Classification

Batool,

Shapiai,

Mostafa

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Silicon wafer defect classification is crucial in improving fabrication and chip production. While deep learning methods have been successful in single-defect wafer classification, the increasing complexity of the fabrication process has introduced the challenge of multiple defects on wafers, which requires more robust feature learning and classification techniques. Attention mechanisms have been used to enhance feature learning for multiple wafer defects. However, they have limited use in a few mixed-type defect categories, and their performance declines as the number of mixed patterns increases. This work proposes an attention-augmented convolutional neural networks (A2CNN) model for enhanced discriminative feature learning of complex defects. The A2CNN model emphasizes the features in the channel and spatial dimensions. Additionally, the model adopts the focal loss function to reduce misclassification and a global average pooling layer to enhance the network's generalization by reducing overfitting. The A2CNN model is evaluated on the MixedWM38 wafer defect dataset using 10-fold cross-validation. It achieves impressive results, with accuracy, precision, recall, and F1-score reported as 98.66%, 99.0%, 98.55%, and 98.82% respectively. Compared to existing works, the A2CNN model performs better by effectively learning valuable information for complex mixed-type wafer defects.

show abstract

Section: Defect Segmentationmentioning

confidence: 99%

An Attention-Augmented Convolutional Neural Network With Focal Loss for Mixed-Type Wafer Defect Classification

Batool,

Shapiai,

Mostafa

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…However, the size of the convolutional kernel in the above method limits the model's ability to perceive the receptive field. To broaden the receptive field, dilation convolutions with multiple dilation rates are used in [4,5] to gain global contextual knowledge without enlarging the amount of model parameters. Nevertheless, these methods are unable to achieve good results for long stripe defects in SOFC surface defect images.…”

Section: Introductionmentioning

confidence: 99%

Cascaded mixed pyramid pooling for surface defect segmentation in solid oxide fuel cell

Wang,

Fu,

et al. 2024

Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024)

View full text Add to dashboard Cite

To address the issues of defect leakage and mis-segmentation in the surface defect segmentation of solid oxide fuel cells, we propose a cascaded mixed pyramid pooling segmentation method. In the encoding part, attention-based depth-wise separable convolution is implemented to replace the traditional convolution. This reduces the computational complexity and achieves hierarchical feature extraction. Secondly, cascaded sampling is applied to the last three layers of the encoder to promote multi-level feature fusion, and mixed pyramid pooling consisting of atrous convolution and strip pooling is adopted to achieve feature extraction for long-range band defects. Lastly, an adaptive loss function is constructed to supervise the training process, balancing the relative importance among the losses and improving the learning of defect features by the network. The experiments demonstrate that the proposed method improves segmentation accuracy, as evidenced by better results in mean absolute error, F1 score, intersection over union, and Pratt's figure of merit.

show abstract

“…Li Z et al [ 11 ] proposed a two-stage industrial defect detection framework based on Improved-YOLOv5 and Optimation-Inception—resnetv2, which completes the localization and classification tasks through two specific models. Liu T et al [ 12 ] proposed an adaptive image segmentation network (AIS-Net) for the pixel-level segmentation of surface defects. In order to achieve the balance between accuracy and speed, Shi X et al [ 13 ] proposed an improved network based on Faster R-CNN for the detection of steel surface defects.…”

Section: Introductionmentioning

confidence: 99%

Strip Surface Defect Detection Algorithm Based on YOLOv5

et al. 2023

View full text Add to dashboard Cite

In order to improve the detection accuracy of the surface defect detection of industrial hot rolled strip steel, the advanced technology of deep learning is applied to the surface defect detection of strip steel. In this paper, we propose a framework for strip surface defect detection based on a convolutional neural network (CNN). In particular, we propose a novel multi-scale feature fusion module (ATPF) for integrating multi-scale features and adaptively assigning weights to each feature. This module can extract semantic information at different scales more fully. At the same time, based on this module, we build a deep learning network, CG-Net, that is suitable for strip surface defect detection. The test results showed that it achieved an average accuracy of 75.9 percent (mAP50) in 6.5 giga floating-point operation (GFLOPs) and 105 frames per second (FPS). The detection accuracy improved by 6.3% over the baseline YOLOv5s. Compared with YOLOv5s, the reference quantity and calculation amount were reduced by 67% and 59.5%, respectively. At the same time, we also verify that our model exhibits good generalization performance on the NEU-CLS dataset.

show abstract

An Adaptive Image Segmentation Network for Surface Defect Detection

Cited by 31 publications

References 46 publications

An Attention-Augmented Convolutional Neural Network With Focal Loss for Mixed-Type Wafer Defect Classification

An Attention-Augmented Convolutional Neural Network With Focal Loss for Mixed-Type Wafer Defect Classification

Cascaded mixed pyramid pooling for surface defect segmentation in solid oxide fuel cell

Strip Surface Defect Detection Algorithm Based on YOLOv5

Contact Info

Product

Resources

About