Fabric Defect Detection Using YOLOv2 and YOLO v3 Tiny

Sujee, R.; Shanthosh, D.; Sudharsun, L.

doi:10.1007/978-3-030-63467-4_15

Cited by 9 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result, one-stage algorithms usually run faster. The one-stage algorithm includes SSD [12], YOLO [13], YOLOv2 [14], YOLOv3, RetinaNet [15], etc. In a real-world application, the requirement of defect inspection is highly real-time and accurate.…”

Section: Introductionmentioning

confidence: 99%

A Two-model Automatic Towel Defect Detection Method Based On YOLOv5

Ding¹,

Zhou²,

Du³

et al. 2022

Proceedings of International Exchange and Innovation Conference on Engineering &Amp; Sciences (IEICES)

View full text Add to dashboard Cite

For replacing error-prone, costly, incongruous, and time-consuming human operators in the textile industry, an automatic and precise fabric flaw inspection system is vital. Textile blemish detection plays an essential effect in the production of textiles in the textile industry. Researchers have proposed many algorithms for fabric defect detection. However, several important issues, including inference time consumption, data imbalance, and algorithm complexity, still need to be dealt with for application in textile industry production. This paper proposes a two-model automatic towel defect detection method based on YOLOv5 to detect the defects of towels, effectively improving the detection efficiency and significantly reducing the cost. Moreover, this method has achieved the detection speed of 10 pictures per second in the actual production.

show abstract

Section: Introductionmentioning

confidence: 99%

A Two-model Automatic Towel Defect Detection Method Based On YOLOv5

Ding¹,

Zhou²,

Du³

et al. 2022

Proceedings of International Exchange and Innovation Conference on Engineering &Amp; Sciences (IEICES)

View full text Add to dashboard Cite

show abstract

“…3 Some researchers regard the defect detection problem as a target detection problem. [4][5][6][7] Among them, methods based on YOLO are popular in various papers and competitions recently. YOLO-based networks are end-to-end lightweight networks that are easy to deploy in industrial scenarios.…”

mentioning

confidence: 99%

Unsupervised defect segmentation on denim fabric via local patch prediction and residual fusion

Zhou

Pan

et al. 2023

Textile Research Journal

View full text Add to dashboard Cite

Deep learning-based defect inspection has gained popularity in recent years. The dataset requirements for the supervised learning-based method are currently high, but the types of defects are numerous and difficult to gather. This work proposes a local image reconstruction-based unsupervised fabric defect segmentation method to address this problem. Cyclic structures make up the normal portion of the fabric image, whereas the defects are anomalous and minor in comparison. As a result, the defect will be recreated as a normal texture utilizing the information from its surrounding areas, and the defect information will be preserved in the residual image. By masking the same area with various shapes, different reconstruction outcomes and residual images can be achieved. The signal of the defect will be amplified and the noise will be decreased due to the random distribution when the generated residual pictures are fused, which can effectively identify the defect from the noise and lower the false detection rate. On the denim fabric dataset, the proposed unsupervised method can achieve high precision fabric defect segmentation, with the defect detection rate and detection precision reaching at least 85% and 89%, respectively, with high efficiency (approximately 60 m/min inspection speed), outperforming other fabric defect segmentation methods.

show abstract