Structure-aware-based crack defect detection for multicrystalline solar cells

Chen, Haiyong; Zhao, Heng; Han, Da; Liu, Weipeng; Chen, Peng; Liu, Kun

doi:10.1016/j.measurement.2019.107170

Cited by 28 publications

(8 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method performs well in micro-crack defect detection task. Chen et al [26] applied 2D Hessian-based enhancement filter to obtain the linear-structure and blob-structure. Then, a novel structure similarity measure (SSM) function is designed by using the identification functions of two structures, which can highlight crack defect (line-structure), and suppress crystal grains (blobstructure) simultaneously.…”

Section: Related Work a Defect Segmentationmentioning

confidence: 99%

SIGAN: A Novel Image Generation Method for Solar Cell Defect Segmentation and Augmentation

Su¹,

Zhou²,

Chen³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Solar cell electroluminescence (EL) defect segmentation is an interesting and challenging topic. Many methods have been proposed for EL defect detection, but these methods are still unsatisfactory due to the diversity of the defect and background. In this paper, we provide a new idea of using generative adversarial network (GAN) for defect segmentation. Firstly, the GAN-based method removes the defect region in the input defective image to get a defect-free image, while keeping the background almost unchanged. Then, the subtracted image is obtained by making difference between the defective input image with the generated defect-free image. Finally, the defect region can be segmented through thresholding the subtracted image. To keep the background unchanged before and after image generation, we propose a novel strong identity GAN (SIGAN), which adopts a novel strong identity loss to constraint the background consistency. The SIGAN can be used not only for defect segmentation, but also small-samples defective dataset augmentation. Moreover, we release a new solar cell EL image dataset named as EL-2019, which includes three types of images: crack, finger interruption and defect-free. Experiments on EL-2019 dataset show that the proposed method achieves 90.34% Fscore, which outperforms many state-of-the-art methods in terms of solar cell defects segmentation results.

show abstract

Section: Related Work a Defect Segmentationmentioning

confidence: 99%

SIGAN: A Novel Image Generation Method for Solar Cell Defect Segmentation and Augmentation

Su¹,

Zhou²,

Chen³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Chen et al [59] The authors presented a structure-aware crack defect detection scheme. It is based on two mathematical models, where the first one models a cracked surface, and the second one models a structured surface of a solar panel.…”

Section: Accuracy Is Not Specifiedmentioning

confidence: 99%

Automated Identification of Wood Veneer Surface Defects Using Faster Region-Based Convolutional Neural Network with Data Augmentation and Transfer Learning

Urbonas¹,

Raudonis²,

Maskeliūnas

et al. 2019

Applied Sciences

113

View full text Add to dashboard Cite

In the lumber and wood processing industry, most visual quality inspections are still done by trained human operators. Visual inspection is a tedious and repetitive task that involves a high likelihood of human error. Currently, new automated solutions with high-resolution cameras and visual inspection algorithms are being tested, but they are not always fast and accurate enough for real-time industrial applications. This paper proposes an automatic visual inspection system for the location and classification of defects on the wood surface. We adopted a faster region-based convolutional neural network (faster R-CNN) for the identification of defects on wood veneer surfaces. Faster R-CNN has been successfully used in medical image processing and object tracking before, but it has not yet been applied for wood panel surface quality assurance. To improve the results, we used pre-trained AlexNet, VGG16, BNInception, and ResNet152 neural network models for transfer learning. The results of the experiments using a synthetically augmented dataset are presented. The best average accuracy of 80.6% was obtained using the pretrained ResNet152 neural network model. By combining all the defect classes, a 96.1% accuracy of finding wood panel surface defects was achieved.

show abstract

“…The Gaussian window is set as 45 according to the experiment. Figure 7c is the response map of the DoG calculated by Equation (8). In the collected image of an aluminum ingot surface, the gray value of the defect area is lower than the texture background in varying degrees, so this paper uses ( , ,7.1) ( , ) ( , ) G x y f x y f x y * − to reduce the influence of the background.…”

Section: Similar Areas Mergementioning

confidence: 99%

“…Both the statistical and structural textures appear as homogeneous ( Figure 1 a,b and Figure 2 a,b) or inhomogeneous ( Figure 1 c,d and Figure 2 c,d). It should be noted that Figure 1 d and Figure 2 b are respectively quoted from Reference [ 7 ] and Reference [ 8 ]. As can been seen, the milling surface we deal with features structured homogeneous or inhomogeneous textures ( Figure 2 a,c,d).…”

Section: Introductionmentioning

confidence: 99%

Mask Gradient Response-Based Threshold Segmentation for Surface Defect Detection of Milled Aluminum Ingot

Liang

Zhou

2020

Sensors

View full text Add to dashboard Cite

The surface quality of aluminum ingot is crucial for subsequent products, so it is necessary to adaptively detect different types of defects in milled aluminum ingots surfaces. In order to quickly apply the calculations to a real production line, a novel two-stage detection approach is proposed. Firstly, we proposed a novel mask gradient response-based threshold segmentation (MGRTS) in which the mask gradient response is the gradient map after the strong gradient has been eliminated by the binary mask, so that the various defects can be effectively extracted from the mask gradient response map by iterative threshold segmentation. In the region of interest (ROI) extraction, we combine the MGRTS and the Difference of Gaussian (DoG) to effectively improve the detection rate. In the aspect of the defect classification, we train the inception-v3 network with a data augmentation technology and the focal loss in order to overcome the class imbalance problem and improve the classification accuracy. The comparative study shows that the proposed method is efficient and robust for detecting various defects on an aluminum ingot surface with complex milling grain. In addition, it has been applied to the actual production line of an aluminum ingot milling machine, which satisfies the requirement of accuracy and real time very well.

show abstract

Structure-aware-based crack defect detection for multicrystalline solar cells

Cited by 28 publications

References 21 publications

SIGAN: A Novel Image Generation Method for Solar Cell Defect Segmentation and Augmentation

SIGAN: A Novel Image Generation Method for Solar Cell Defect Segmentation and Augmentation

Automated Identification of Wood Veneer Surface Defects Using Faster Region-Based Convolutional Neural Network with Data Augmentation and Transfer Learning

Mask Gradient Response-Based Threshold Segmentation for Surface Defect Detection of Milled Aluminum Ingot

Contact Info

Product

Resources

About