Automatic Identification of Corrosion in Marine Vessels Using Decision-Tree Imaging Hierarchies

Chliveros, Georgios; Kontomaris, Stylianos V.; Letsios, Apostolos

doi:10.3390/eng4030118

Cited by 3 publications

(8 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to explore performance characteristics of the selected methods, we use the corrosion images dataset for marine vessels in dry-dock conditions [12,16]. The dataset incorporates several artifacts due to environmental conditions (e.g.…”

Section: Datamentioning

confidence: 99%

“…Since the predicted leaf node contains only pixel indices, the prediction methodology preserves the and reconstructs the predicted frame based on said cluster indices. The handling of eigenvectors e i and information entropy H i are further described in [12].…”

Section: Proposed Eigen Module (Yolo-eigen)mentioning

confidence: 99%

“…Corrosion as isolated area units on a vessel surface is difficult to both detect and predict in RGB images, with a diverse geometrical shape, which makes it difficult to postulate prior knowledge on the basis of a generalised morphology in terms of image processing. Recent advances in deep learning models [5,6] have examined the applicability and potential of machine vision for the inspection of large structures [7][8][9][10] and segmentation of corrosion in marine vessels [3,[11][12][13].…”

Section: Introductionmentioning

confidence: 99%

“…Respectively, said deep-learning models seem to exhibit a decreased recognition accuracy when in the training images appears increased crack-like texture, and/or locally dispersed illumination due to crack depth. This surface texture produces high 'colour' similarity between groups of pixels that results in reduced precision and accuracy [4,11,12]. A possible solution is to fine tune the neural network during its training phase in order to enhance specificity, although this leads to decreased method generalisation.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Vessel Surface Corrosion Segmentation Approach Using a Decision-Tree Module for YOLO Trained Models

Chliveros,

Tzanetatos,

Kontomaris

2024

Preprint

View full text Add to dashboard Cite

In this paper we propose a module that uses features learned by a deep convolutional neural network to infer areas of corrosion and segment pixels to corrosion areas of inspection interest. Our segmentation module is based on eigen tree decomposition and information based decision criteria. To interrogate performance we use several state-of-the-art deep learning architectures and compare to our approach. The results indicate that our method produces better results in terms of accuracy and precision, whilst maintaining good (f-score) significance over the entire dataset.

show abstract

Section: Datamentioning

confidence: 99%

Section: Proposed Eigen Module (Yolo-eigen)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Vessel Surface Corrosion Segmentation Approach Using a Decision-Tree Module for YOLO Trained Models

Chliveros,

Tzanetatos,

Kontomaris

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…This is mainly due to the diverse geometrical shape, which makes it difficult to postulate prior knowledge on the basis of a generalised morphology. Recent advances in deep learning models [16,17] have examined the applicability and potential of machine vision for the inspection of large structures [18][19][20] and segmentation of corrosion in marine vessels [2,11,[21][22][23].…”

Section: Introductionmentioning

confidence: 99%

A Deep Learning Image Corrosion Classification Method for Marine Vessels Using an Eigen Tree Hierarchy Module

Chliveros,

Tzanetatos,

Kontomaris

2024

Coatings

Self Cite

View full text Add to dashboard Cite

This paper involves the automation of a visual characterisation technique for corrosion in marine vessels, as it appears in the hull preventive coatings of marine vessels and their surfaces. We propose a module that maximizes the utilisation of features learned by a deep convolutional neural network to identify areas of corrosion and segment pixels in regions of inspection interest for corrosion detection. Our segmentation module is based on Eigen tree decomposition and information-based decision criteria in order to produce specific corroded spots—regions of interest. To assess performance and compare it with our method, we utilize several state-of-the-art deep learning architectures.The results indicate that our method achieves higher accuracy and precision while maintaining the significance score across the entire dataset. To the best of our knowledge, this is the first Eigen tree-based module in the literature in the context of trained neural network predictors for classifying corrosion in marine vessel images.

show abstract

Blast Furnace Hanging Diagnosis Model Based On ReliefF-Decision Tree

Li,

Meng,

Liu

et al. 2024

ISIJ Int.

View full text Add to dashboard Cite

Blast furnace hanging is an abnormal furnace condition with the highest frequency.The judgment of hanging mainly relies on manual analysis, but this approach has strong subjectivity and time lag. In order to solve the above problems, this paper proposes a ReliefF -Decision Tree based anomaly diagnosis model to identify the hanging. Firstly, 10 relevant parameters are extracted based on expert experience, and each characteristic parameter is weighted using ReliefF algorithm after preprocessing. Secondly, the calculated weights of the characteristic parameters are sorted from the largest to the smallest, and the seven most effective characteristic parameter sets are selected as the decision nodes of the decision tree, which is constructed according to the expert rules of hanging diagnosis to complete the training and testing of the classifier. Simulation results show that the accuracy of the ReliefF -Decision Tree model reaches 96.5%, and the recognition rate of the two anomalies of "burden stop" and "sudden rise of differential pressure" exceeds 80%, which is 83.1% and 87.5%, respectively, indicating that the performance of the model is good. Finally, the expert diagnosis system is built, which effectively improves the diagnosis efficiency of hanging.

show abstract

Automatic Identification of Corrosion in Marine Vessels Using Decision-Tree Imaging Hierarchies

Cited by 3 publications

References 34 publications

Vessel Surface Corrosion Segmentation Approach Using a Decision-Tree Module for YOLO Trained Models

Vessel Surface Corrosion Segmentation Approach Using a Decision-Tree Module for YOLO Trained Models

A Deep Learning Image Corrosion Classification Method for Marine Vessels Using an Eigen Tree Hierarchy Module

Blast Furnace Hanging Diagnosis Model Based On ReliefF-Decision Tree

Contact Info

Product

Resources

About