Multi‐step radiographic image enhancement conforming to weld defect segmentation

Dang, Changying; Gao, Jianmin; Zhao, Wang; Chen, Fumin; Xiao, Yulin

doi:10.1049/iet-ipr.2014.0716

Cited by 29 publications

(5 citation statements)

References 15 publications

(18 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study uses four performance metrics: F1, Positive Predictive Value (PPV), Sensitivity, and Relative Segmentation Accuracy (RSA) [21]. Accuracy was not used in this study because it was judged not suitable for measuring performance for segmentation.…”

Section: Methodsmentioning

confidence: 99%

Malaria parasite segmentation using U-Net: Comparative study of loss functions

Abraham¹

2019

CST

View full text Add to dashboard Cite

The convolutional neural network is commonly used for classification. However, convolutional networks can also be used for semantic segmentation using the fully convolutional network approach. U-Net is one example of a fully convolutional network architecture capable of producing accurate segmentation on biomedical images. This paper proposes to use U-Net for Plasmodium segmentation on thin blood smear images. The evaluation shows that U-Net can accurately perform Plasmodium segmentation on thin blood smear images, besides this study also compares the three loss functions, namely mean-squared error, binary cross-entropy, and Huber loss. The results show that Huber loss has the best testing metrics: 0.9297, 0.9715, 0.8957, 0.9096 for F1 score, positive predictive value (PPV), sensitivity (SE), and relative segmentation accuracy (RSA), respectively.

show abstract

Section: Methodsmentioning

confidence: 99%

Malaria parasite segmentation using U-Net: Comparative study of loss functions

Abraham¹

2019

CST

View full text Add to dashboard Cite

show abstract

“…However, manual threshold values are to be finetuned for different images, and it is not suitable for all types of images. Multi Step Radiographic enhancement proposed in [3] also aimed at segmenting the defective welds through image processing. Their image processing algorithm involved the key components including linear weighting process that combines a CLAHE enhanced image with the normal image to improve the image contrast.…”

Section: Related Workmentioning

confidence: 99%

Slag and Porosity Defective Region Identification in Welding Images Using Computer Vision Techniques

Rajalakshmi,

Sivasankaran,

Shinow

et al. 2023

DDF

View full text Add to dashboard Cite

The process of welding is prone to many defects and these defects can cause the formation of many defective regions. It is necessary to identify the regions of defects as these may cause problems and breakages. In this work, we have proposed a method to detect and identify the defects that are commonly seen in seam welds. Manually identifying the detects is not only error prone and time consuming, most of the defects are not visible to the human eyes. In recent days, X-ray images of weld seam are used for this purpose. In this paper we have applied computer vision techniques and proposed an image processing pipeline to generate a binary segmentation of the image to identify the regions of slag and porosity defect seen in weld seams. From the experimental results on the publicly available dataset, GDX-ray images, it could be observed that, there is a significant improvement in detecting various defects with the proposed approach.

show abstract

“…In the fuzzy set theory, image I can be defined as [15]