Pointer Defect Detection Based on Transfer Learning and Improved Cascade-RCNN

Zhao, Weidong; Huang, Hancheng; Li, Dan; Chen, Feng; Wei, Cheng

doi:10.3390/s20174939

Cited by 18 publications

(11 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The average precision (AP) is used as the evaluation index of each defect detection in this experiment after the model training is completed, and the mean average precision (mAP) is used as the evaluation index of the whole model performance. The definitions of precision (P), AP, and mAP [ 37 ] are shown as follows:

where TP is the number of samples with correct detection, FP is the number of negative samples with detection, and r is the value of recall ( R ). The definition of recall rate is shown in formula ( 10 ), ρ interp( r ) can be expressed as formula ( 11 ) [ 37 ], j is the category index, n j is the total number of categories, and AP j is the average precision of each category:

where FN is the number of samples with error detection and

is the recall rate of

.…”

Section: Steel Defect Detection Methodsmentioning

confidence: 99%

“…e average precision (AP) is used as the evaluation index of each defect detection in this experiment after the model training is completed, and the mean average precision (mAP) is used as the evaluation index of the whole model performance. e definitions of precision (P), AP, and mAP [37] are shown as follows:…”

Section: Experimental Environment and Parameter Settingmentioning

confidence: 99%

See 1 more Smart Citation

A New Steel Defect Detection Algorithm Based on Deep Learning

Zhao

Feng

Huang

et al. 2021

Computational Intelligence and Neuroscience

Self Cite

129

View full text Add to dashboard Cite

In recent years, more and more scholars devoted themselves to the research of the target detection algorithm due to the continuous development of deep learning. Among them, the detection and recognition of small and complex targets are still a problem to be solved. The authors of this article have understood the shortcomings of the deep learning detection algorithm in detecting small and complex defect targets and would like to share a new improved target detection algorithm in steel surface defect detection. The steel surface defects will affect the quality of steel seriously. We find that most of the current detection algorithms for NEU-DET dataset detection accuracy are low, so we choose to verify a steel surface defect detection algorithm based on machine vision on this dataset for the problem of defect detection in steel production. A series of improvement measures are carried out in the traditional Faster R-CNN algorithm, such as reconstructing the network structure of Faster R-CNN. Based on the small features of the target, we train the network with multiscale fusion. For the complex features of the target, we replace part of the conventional convolution network with a deformable convolution network. The experimental results show that the deep learning network model trained by the proposed method has good detection performance, and the mean average precision is 0.752, which is 0.128 higher than the original algorithm. Among them, the average precision of crazing, inclusion, patches, pitted surface, rolled in scale and scratches is 0.501, 0.791, 0.792, 0.874, 0.649, and 0.905, respectively. The detection method is able to identify small target defects on the steel surface effectively, which can provide a reference for the automatic detection of steel defects.

show abstract

where FN is the number of samples with error detection and

is the recall rate of

.…”

Section: Steel Defect Detection Methodsmentioning

confidence: 99%

Section: Experimental Environment and Parameter Settingmentioning

confidence: 99%

A New Steel Defect Detection Algorithm Based on Deep Learning

Zhao

Feng

Huang

et al. 2021

Computational Intelligence and Neuroscience

Self Cite

129

View full text Add to dashboard Cite

show abstract

“…Deep Learning Small Defects Hu [16] 1928 × 1448 3.41 × ○ Zhao [18] 2800 × 300 1.57 ○ ○ Tabernik [14] 1408 × 512 0.11 ○ × Westphal [15] 180 × 180 0.13 ○ × Jiang [19] 512 × 512 2.29 ○ ○…”

Section: Methods Input Image Speed [S]mentioning

confidence: 99%

“…They proposed an algorithm that can detect positive regions, where steel shells are present and applied Gaussian filtering and binarization to the interior of the ellipse to detect the existence of pits. To detect five types of defects that occur in the process of manufacturing, Zhao et al proposed the TICNET model, which improves the existing cascade R-CNN approach [18]. The feature extraction capacity of the model was improved by applying deformable convolution layers instead of convolution layers; this can learn both weights and kernel offsets [19,20].…”

Section: Limitations Of Existing Object Detection Modelsmentioning

confidence: 99%

RT-SPeeDet: Real-Time IP–CNN-Based Small Pit Defect Detection for Automatic Film Manufacturing Inspection

Ban

Yoo

2021

Applied Sciences

View full text Add to dashboard Cite

Pits are defects that occur during the film manufacturing process; they appear in the micrometer scale, which makes distinguishing them with the human eye difficult. Existing defect detectors have poor recognition rates for small objects or require a considerable amount of time. To resolve these problems, we propose a real-time small pit defect detector (RT-SPeeDet), a two-stage detection model based on an image processing and convolutional neural network (IP–CNN) approach. The proposed method predicts boundary boxes using a lightweight image-processing algorithm optimized for pit defects, and applies binary classification to the predicted regions; thus, simultaneously simplifying the problem and achieving real-time processing speed, unlike existing detection methods that rely on CNN-based detectors for both boundary box prediction and classification. RT-SPeeDet uses lightweight image processing operations to extract pit defect candidate region image patches from high-resolution images. These patches are then passed through a CNN-based binary classifier to detect small pit defects at a real-time processing speed of less than 0.5 s. In addition, we propose a multiple feature map synthesis method that enhances the features of pit defects, enabling efficient detection of faint pit defects, which are particularly difficult to detect.

show abstract

“…Recently, machine vision has been popularly used in the defect detection of industrial products instead of labor. However, most studies are focused on the detection of products’ external surface [ 4 , 5 , 6 , 7 ], while few are reported on the internal defects of injection-molded parts with DR imaging. Early work in internal defect detection with DR images using machine vision was based on traditional image processing for automated supervision and localization of defects, which mainly relies on manually produced feature extractors, such as area feature extraction, edge detection, threshold segmentation [ 8 ].…”

Section: Introductionmentioning

confidence: 99%

A Lightweight Deep Network for Defect Detection of Insert Molding Based on X-ray Imaging

Wang

Huang

2021

Sensors

View full text Add to dashboard Cite

Aiming at the abnormality detection of industrial insert molding processes, a lightweight but effective deep network is developed based on X-ray images in this study. The captured digital radiography (DR) images are firstly fast guide filtered, and then a multi-task detection dataset is constructed using an overlap slice in order to improve the detection of tiny targets. The proposed network is extended from the one-stage target detection method of yolov5 to be applicable to DR defect detection. We adopt the embedded Ghost module to replace the standard convolution to further lighten the model for industrial implementation, and use the transformer module for spatial multi-headed attentional feature extraction to perform improvement on the network for the DR image defect detection. The performance of the proposed method is evaluated by consistent experiments with peer networks, including the classical two-stage method and the newest yolo series. Our method achieves a mAP of 93.6%, which exceeds the second best by 3%, with robustness sufficient to cope with luminance variations and blurred noise, and is more lightweight. We further conducted ablation experiments based on the proposed method to validate the 32% model size reduction owing to the Ghost module and the detection performance enhancing effect of other key modules. Finally, the usability of the proposed method is discussed, including an analysis of the common causes of the missed shots and suggestions for modification. Our proposed method contributes a good reference solution for the inspection of the insert molding process.

show abstract

Pointer Defect Detection Based on Transfer Learning and Improved Cascade-RCNN

Cited by 18 publications

References 36 publications

A New Steel Defect Detection Algorithm Based on Deep Learning

A New Steel Defect Detection Algorithm Based on Deep Learning

RT-SPeeDet: Real-Time IP–CNN-Based Small Pit Defect Detection for Automatic Film Manufacturing Inspection

A Lightweight Deep Network for Defect Detection of Insert Molding Based on X-ray Imaging

Contact Info

Product

Resources

About