2011
DOI: 10.1016/j.eswa.2011.01.092
|View full text |Cite
|
Sign up to set email alerts
|

Performance evaluation of an automatic inspection system of weld defects in radiographic images based on neuro-classifiers

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
5

Citation Types

1
44
0
2

Year Published

2012
2012
2022
2022

Publication Types

Select...
8
1

Relationship

1
8

Authors

Journals

citations
Cited by 77 publications
(47 citation statements)
references
References 18 publications
1
44
0
2
Order By: Relevance
“…Liao (2008) investigated the imbalanced data problem in the classification of different types of weld flaws. Zapata, Vilar, and Ruiz (2011) described an automatic system to detect, recognize, and classify welding defects in radiographic images using an artificial neuronal network (ANN) and an adaptive-network-based fuzzy inference system. Valavanis and Kosmopoulos (2010) used SVM, ANN and k-nearest neighbor (k-NN) classifiers for the detection and classification of defects in weld radiographs.…”
Section: Introductionmentioning
confidence: 99%
“…Liao (2008) investigated the imbalanced data problem in the classification of different types of weld flaws. Zapata, Vilar, and Ruiz (2011) described an automatic system to detect, recognize, and classify welding defects in radiographic images using an artificial neuronal network (ANN) and an adaptive-network-based fuzzy inference system. Valavanis and Kosmopoulos (2010) used SVM, ANN and k-nearest neighbor (k-NN) classifiers for the detection and classification of defects in weld radiographs.…”
Section: Introductionmentioning
confidence: 99%
“…Centros de pesquisa em diversos países têm focalizado seus esforços na tentativa de encontrar ferramentas computacionais automáticas que possam auxiliar na redução da subjetividade na interpretação radiográfica [3], [4], [5], [6], [7].…”
Section: Introductionunclassified
“…Contudo, geralmente se recorre à extração manual ou semiautomática de regiões da imagem, denominadas regiões de inte-resse (ROI do inglês regions of interest), que no caso da aplicação considerada neste artigo, incluem o cordão de solda e os defeitos a serem analisados [5], [6], [7]. Para melhorar a eficiência dos métodos de detecção de defeitos seria conveniente utilizar métodos para segmentar a região do cordão de solda a ser inspecionado de forma a reduzir o espaço de busca.…”
Section: Introductionunclassified
“…Segmentally extract defected object, then manually select defect characteristics, manual characteristics description computation, statistical method and other shallow network identification method. Due to complicated and uneven background of banknote image, many types of defected object, defected object is tiny, it is very difficult to accurately segment banknote image defect, effectively describe and select manual characteristics, which need very specialized knowledge and not only subject to condition limits [2][3] , but also rely on accurate defect segmentation statistical model or shallow network model. It has high target pertinence and poor adaptability [4] .…”
Section: Introductionmentioning
confidence: 99%