Fabric defect detection based on separate convolutional UNet

Cheng, Le; Yi, Jizheng; Chen, Aibin; Zhang, Yi

doi:10.1007/s11042-022-13568-7

Cited by 31 publications

(15 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we evaluate the segmentation performance of our proposed method for real-time hair defect detection with thorough ablation studies in segmentation accuracy and speed. Four widely-used segmentation models, i.e., Unet [6], SegNet [35], SCUNet [36], and FSDNet [37], for defect detection, are introduced for comparison in this paper. To validate the validity of our proposed LFE module, we also apply it to two common base networks (i.e., VGG16 and Mo-bileNetv1).…”

Section: Experimental Results and Analysismentioning

confidence: 99%

“…In this subsection, two standard networks that are commonly used for semantic segmentation, that is, UNet [6] and Seg-Net [35], and two recent published defect detection networks, i.e., SCUNet [36] and FSDNet [37], are introduced for comparison.…”

Section: Segmentation Comparison Resultsmentioning

confidence: 99%

“…In section 1, we have discussed the significance of real-time performance in industrial defect detection, highlighting its Unet [6] SegNet [35] Ground truth DLERS(Ours) Input SCUNet [36] FSDNet [37] Fig. 3 Visualization of hair extraction using different segmentation networks.…”

Section: Real-time Performance Analysismentioning

confidence: 99%

See 2 more Smart Citations

Deep LBP-Enriched Real-time Segmentation for Hair Defect Detection

Wang

et al. 2023

Preprint

View full text Add to dashboard Cite

Hair defects are common in the industrial production of medical syringes, posing a significant risk to product quality and efficacy. Detecting these defects in real-time is crucial for ensuring high-quality production.However, existing Deep semantic segmentation (DSS) methods, which generally have numerous network parameters,face significant challenges in real-time hair defect detection due to hair's unique characteristics, including its irregular and thin structure. Moreover, potential hair overlapping with the syringe further complicates the detection process. In this case, conventional DSS methods are hard to explore the accurate low-level visuospatial information that is critical for detecting hair defects. Considering the wide applicability and effectiveness of the handcrafted features, such as Local Binary Pattern (LBP) and Sobel operators, in defect detection, we argue that these features designed by skillful experts may encode rich prior knowledge about defects and may improve the performance of DSS models for hair defects on syringes.Inspired by this idea, this study proposes a Deep LBP-Enriched Real-time Segmentation (DLERS) method for hair defects detection, which maintains a lightweight network structure and leverages the LBP encoding mechanism to facilitate the effective transfer of domain prior knowledge.Besides, to alleviate the influence of the hair-like noise and fragmentary edges, we propose employing a joint loss function that combines the Dice loss, BCE loss, and Edge loss to train our network. To evaluate the performance of DLERS, we conduct experiments on one real-world syringe dataset.The competitive results (e.g., 85.36% MIoU and 149.1 FPS) prove the effectiveness of our method.

show abstract

Section: Experimental Results and Analysismentioning

confidence: 99%

Section: Segmentation Comparison Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Deep LBP-Enriched Real-time Segmentation for Hair Defect Detection

Wang

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In this section, we first show the performance of the SeNet and compare it with four state-of-the-art segmentation methods. The compared methods include the U-Net [ 36 ], SN [ 6 ], SCUNet [ 37 ], and FSDNet [ 38 ]. Secondly, we explore the number of samples needed for training the network.…”

Section: Methodsmentioning

confidence: 99%

“…SN [ 6 ], which enlightens us to propose SeNet according to the characteristics of the scale. SCUNet [ 37 ], a U-Net like segmentation network with depthwise convolution, which slashes the complexity and the size of U-Net sharply. FDSNet [ 38 ], which is a novel segmentation network based on a two-stage defect detection framework.…”

Section: Methodsmentioning

confidence: 99%

A robust defect detection method for syringe scale without positive samples

Wang

et al. 2022

Vis Comput

View full text Add to dashboard Cite

With the worldwide spread of the COVID-19 pandemic, the demand for medical syringes has increased dramatically. Scale defect, one of the most common defects on syringes, has become a major barrier to boosting syringe production. Existing methods for scale defect detection suffer from large volumes of data requirements and the inability to handle diverse and uncertain defects. In this paper, we propose a robust scale defects detection method with only negative samples and favorable detection performance to solve this problem. Different from conventional methods that work in a batch-mode defects detection manner, we propose to locate the defects on syringes with a two-stage framework, which consists of two components, that is, the scale extraction network and the scale defect discriminator. Concretely, the SeNet is first built to utilize the convolutional neural network to extract the main structure of the scale. After that, the scale defect discriminator is designed to detect and label the scale defects. To evaluate the performance of our method, we conduct experiments on one real-world syringe dataset. The competitive results, that is, 99.7% on F1, prove the effectiveness of our method.

show abstract