High Efficient Single-stage Steel Surface Defect Detection

Proceedings of the 2021 International Conference on Multimedia Retrieval

Lin

Kathiresan

2021

Self Cite

Steel surface defect detection represents a challenging task in realworld practical object detection. Based on our observations, there are two critical problems which create this challenge: the tiny size, and vagueness of the defects. To solve these problems, this study a proposes a deep learning-based defect detection system that uses automatic dual transformation in the end-to-end network. First, the original training images in RGB are transformed into the HSV color model to re-arrange the difference in color distribution. Second, the feature maps are upsampled using bilinear interpolation to maintain the smaller resolution. The latest and state-of-the-art object detection model, High-Resolution Network (HRNet) is utilized in this system, with initial transformation performed via data augmentation. Afterward, the output of the backbone stage is applied to the second transformation. According to the experimental results, the proposed approach increases the accuracy of the detection of class 1 Severstal steel surface defects by 3.6% versus the baseline.

Section: Doctoral Consortiummentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

A Beneficial Dual Transformation Approach for Deep Learning Networks Used in Steel Surface Defect Detection

Proceedings of the 2021 International Conference on Multimedia Retrieval

Lin

Kathiresan

2021

Self Cite

“…Such an approach is simple, but it cannot localize defects. To localize various defects in an input image, object detection-based defect inspection systems called defect detectors were developed [3,27,30,36,56]. Such approaches can predict defect locations in the form of bounding boxes, along with the defect class labels and the confidence scores of different defect classes.…”

Section: Introductionmentioning

confidence: 99%

“…There are two types of object detection-based defect detectors [68]. The first is the one-stage method [3,6,11,20,22,41,48,49,58,64,65,67], which simultaneously detects and localizes defects. This method achieves a fast inference speed at the cost of lower precision.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

FDD: The Data Pipeline for Steel Defect Detectors

Liu²,

Hsu³

et al. 2022

Preprint

Self Cite

Surface defects are a common issue that affects product quality in the industrial manufacturing process. Many companies put a lot of effort into developing automated inspection systems to handle this issue. In this work, we propose a novel deep learning-based surface defect inspection system called the forceful steel defect detector (FDD), especially for steel surface defect detection. Our model adopts the state-of-the-art cascade R-CNN as the baseline architecture, and improves it with the deformable convolution and the deformable RoI pooling to adapt to the geometric shape of defects. Besides, our model adopts the guided anchoring region proposal to generate bounding boxes with higher accuracies. Moreover, to enrich the point-of-view of input images, we propose the random scaling and the ultimate scaling techniques in the training and inference process, respectively. The experimental studies on the Severstal steel dataset, NEU steel dataset, and DAGM dataset demonstrate that our proposed model effectively improved the detection accuracy in terms of the average recall (AR) and the mean average precision (mAP) compared to state-of-the-art defect detection methods. We expect our innovation to accelerate the automation of the industrial manufacturing process by increasing productivity and by sustaining high product qualities.

FDD: a deep learning–based steel defect detectors

Int J Adv Manuf Technol

Liu

Hsu

et al. 2023

Self Cite

Surface defects are a common issue that affects product quality in the industrial manufacturing process. Many companies put a lot of effort into developing automated inspection systems to handle this issue. In this work, we propose a novel deep learning–based surface defect inspection system called the forceful steel defect detector (FDD), especially for steel surface defect detection. Our model adopts the state-of-the-art cascade R-CNN as the baseline architecture and improves it with the deformable convolution and the deformable RoI pooling to adapt to the geometric shape of defects. Besides, our model adopts the guided anchoring region proposal to generate bounding boxes with higher accuracies. Moreover, to enrich the point of view of input images, we propose the random scaling and the ultimate scaling techniques in the training and inference process, respectively. The experimental studies on the Severstal steel dataset, NEU steel dataset, and DAGM dataset demonstrate that our proposed model effectively improved the detection accuracy in terms of the average recall (AR) and the mean average precision (mAP) compared to state-of-the-art defect detection methods. We expect our innovation to accelerate the automation of industrial manufacturing process by increasing the productivity and by sustaining high product qualities.