An Efficient Network for Surface Defect Detection

Lin, Zesheng; Ye, Hongxia; Zhan, Bin; Huang, Xiaofeng

doi:10.3390/app10176085

Cited by 35 publications

(14 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DRAEM is trained only on anomaly-free training samples using the same parameters as in previous experiments. The standard evaluation protocol on this dataset [19,32,15,6] is used -the challenge is to classify whether the image contains the anomaly; localization accuracy is not measured, since the anomalies are only coarsely labeled.…”

Section: Comparison With Supervised Methodsmentioning

confidence: 99%

See 1 more Smart Citation

DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection

Zavrtanik¹,

Kristan²,

Skočaj³

2021

Preprint

View full text Add to dashboard Cite

Visual surface anomaly detection aims to detect local image regions that significantly deviate from normal appearance. Recent surface anomaly detection methods rely on generative models to accurately reconstruct the normal areas and to fail on anomalies. These methods are trained only on anomaly-free images, and often require hand-crafted post-processing steps to localize the anomalies, which prohibits optimizing the feature extraction for maximal detection capability. In addition to reconstructive approach, we cast surface anomaly detection primarily as a discriminative problem and propose a discriminatively trained reconstruction anomaly embedding model (DRAEM). The proposed method learns a joint representation of an anomalous image and its anomaly-free reconstruction, while simultaneously learning a decision boundary between normal and anomalous examples. The method enables direct anomaly localization without the need for additional complicated post-processing of the network output and can be trained using simple and general anomaly simulations. On the challenging MVTec anomaly detection dataset, DRAEM outperforms the current state-of-theart unsupervised methods by a large margin and even delivers detection performance close to the fully-supervised methods on the widely used DAGM surface-defect detection dataset, while substantially outperforming them in localization accuracy.

show abstract

Section: Comparison With Supervised Methodsmentioning

confidence: 99%

“…CADN [32] ---89.1 Rački et al [19] 99.6 99.9 99.5 -Lin et al [15] 99.0 99.4 99.9 -Božič et al [6] 100 100 100 100…”

Section: Comparison With Supervised Methodsmentioning

confidence: 99%

DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection

Zavrtanik¹,

Kristan²,

Skočaj³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In recent years, the development of deep learning technology led to its application in surface defect detection with good results in terms of classification accuracy. Lin et al [4] constructed a multi-scale cascaded CNN based on MobileNetV2, with a reduced number of parameters thanks to the use of a lightweight backbone. Xiao et al [5] proposed a method for surface defect detection based on Mask R-CNN and image pyramid.…”

Section: Related Workmentioning

confidence: 99%

Surface Defect Detection in Sanitary Ceramics Based on Lightweight Object Detection Network

Hang

Sun

Yu³

et al. 2022

IEEE Open J. Ind. Electron. Soc.

View full text Add to dashboard Cite

Sanitary ceramic products, such as toilet and wash basin, are widely used in our daily life. Sanitary ceramics are expected to have some excellent physical properties, such as corrosion resistance, easy cleaning, and low water absorption. However, surface defects in sanitary ceramics are inevitable due to complex production processes and changing production environment. Therefore, surface defect detection must be performed in the manufacturing process of sanitary ceramics. There are many types of surface defects in sanitary ceramics, and different types of defects have large differences in characteristics and scales. Traditional detection methods with artificially designed features and classifiers are difficult to apply in this context. In addition, there are few studies on surface defect detection methods of sanitary ceramics based on deep neural networks. In this article, a lightweight real-time defect detection network based on the lightweight backbone MobileNetV3 is presented. The proposed network achieves multi-scale detection of surface defects in sanitary ceramics with a multi-layer feature pyramid. Combining region proposal network and anchor-free method, realtime defect detection is achieved. Finally, a detection head with channel attention structure and a low-level mixed feature classification strategy is used to perform defect classification with higher accuracy. Experimental results show that the proposed approach achieves at least 22.9% detection speed improvement and 35.0% average precision improvement while reducing memory consumption by at least 8.4% compared with the classic onestage SSD, YOLO V3 and two-stage Faster R-CNN methods.

show abstract

“…MobileNets are built on a simplified design that uses depthwise separable convolutions to construct low weight deep neural networks instead of regular convolutions, except for the first layer, which is a complete convolution [21]. MobileNet is simpler than VGG-16 and ResNet-50 [8,20,21]. MobileNet-V2 expands on the principles of MobileNet-V1 by employing depthwise separable convolution as efficient building pieces.…”

Section: Mobilenet Modelmentioning

confidence: 99%

Effectiveness of Learning Systems from Common Image File Types to Detect Osteosarcoma Based on Convolutional Neural Networks (CNNs) Models

et al. 2021

View full text Add to dashboard Cite

Osteosarcoma is a rare bone cancer which is more common in children than in adults and has a high chance of metastasizing to the patient’s lungs. Due to initiated cases, it is difficult to diagnose and hard to detect the nodule in a lung at the early state. Convolutional Neural Networks (CNNs) are effectively applied for early state detection by considering CT-scanned images. Transferring patients from small hospitals to the cancer specialized hospital, Lerdsin Hospital, poses difficulties in information sharing because of the privacy and safety regulations. CD-ROM media was allowed for transferring patients’ data to Lerdsin Hospital. Digital Imaging and Communications in Medicine (DICOM) files cannot be stored on a CD-ROM. DICOM must be converted into other common image formats, such as BMP, JPG and PNG formats. Quality of images can affect the accuracy of the CNN models. In this research, the effect of different image formats is studied and experimented. Three popular medical CNN models, VGG-16, ResNet-50 and MobileNet-V2, are considered and used for osteosarcoma detection. The positive and negative class images are corrected from Lerdsin Hospital, and 80% of all images are used as a training dataset, while the rest are used to validate the trained models. Limited training images are simulated by reducing images in the training dataset. Each model is trained and validated by three different image formats, resulting in 54 testing cases. F1-Score and accuracy are calculated and compared for the models’ performance. VGG-16 is the most robust of all the formats. PNG format is the most preferred image format, followed by BMP and JPG formats, respectively.

show abstract

An Efficient Network for Surface Defect Detection

Cited by 35 publications

References 28 publications

DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection

DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detection

Surface Defect Detection in Sanitary Ceramics Based on Lightweight Object Detection Network

Effectiveness of Learning Systems from Common Image File Types to Detect Osteosarcoma Based on Convolutional Neural Networks (CNNs) Models

Contact Info

Product

Resources

About