Distance and Edge Transform for Skeleton Extraction

Tang, Xiaojun; Zheng, Rui; Wang, Yinghao

doi:10.1109/iccvw54120.2021.00242

Cited by 4 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, the Fl score of Deep-Fig. 19 Shape skeleton extraction using CNN-based methods: FHN (Jiang et al, 2019), U-Net (Panichev et al, 2019), DISCO (Song et al, 2021), SDE (Tang et al, 2021), and SkeletonNetV2 (Nathan and Kansal, 2021) Flux (Wang et al, 2019) method improved from 0.732 to 0.752 on the SK1491 dataset (Table 6). This is because, comparing to the original GTs in the SK1491, our GTs are more consistent and possess better completeness in representing objects' geometrical features (see Fig.…”

Section: Skeleton Detectors In Imagesmentioning

confidence: 99%

Skeleton Ground Truth Extraction: Methodology, Annotation Tool and Benchmarks

Yang,

Indurkhya,

See

et al. 2023

Int J Comput Vis

View full text Add to dashboard Cite

Skeleton Ground Truth (GT) is critical to the success of supervised skeleton extraction methods, especially with the popularity of deep learning techniques. Furthermore, we see skeleton GTs used not only for training skeleton detectors with Convolutional Neural Networks (CNN), but also for evaluating skeleton-related pruning and matching algorithms. However, most existing shape and image datasets suffer from the lack of skeleton GT and inconsistency of GT standards. As a result, it is difficult to evaluate and reproduce CNN-based skeleton detectors and algorithms on a fair basis. In this paper, we present a heuristic strategy for object skeleton GT extraction in binary shapes and natural images. Our strategy is built on an extended theory of diagnosticity hypothesis, which enables encoding human-in-the-loop GT extraction based on clues from the target’s context, simplicity, and completeness. Using this strategy, we developed a tool, SkeView, to generate skeleton GT of 17 existing shape and image datasets. The GTs are then structurally evaluated with representative methods to build viable baselines for fair comparisons. Experiments demonstrate that GTs generated by our strategy yield promising quality with respect to standard consistency, and also provide a balance between simplicity and completeness.

show abstract

Section: Skeleton Detectors In Imagesmentioning

confidence: 99%

Skeleton Ground Truth Extraction: Methodology, Annotation Tool and Benchmarks

Yang,

Indurkhya,

See

et al. 2023

Int J Comput Vis

View full text Add to dashboard Cite

show abstract

“…Following the post-processing phase, the average thickness of the RNFL was determined using the Python environment and the Euclidean distance transform (EDT) [17,18] approach.…”

Section: Average Thickness Estimationmentioning

confidence: 99%

Correction of Retinal Nerve Fiber Layer Thickness Measurement on Spectral-Domain Optical Coherence Tomographic Images Using U-net Architecture

Hejazi

Razaghi

Fard

2023

JOVR

View full text Add to dashboard Cite

Purpose: In this study, an algorithm based on deep learning was presented to reduce the retinal nerve fiber layer (RNFL) segmentation errors in spectral domain optical coherence tomography (SD-OCT) scans using ophthalmologists’ manual segmentation as a reference standard. Methods: In this study, we developed an image segmentation network based on deep learning to automatically identify the RNFL thickness from B-scans obtained with SD-OCT. The scans were collected from Farabi Eye Hospital (500 B-scans were used for training, while 50 were used for testing). To remove the speckle noise from the images, preprocessing was applied before training, and postprocessing was performed to fill any discontinuities that might exist. Afterward, output masks were analyzed for their average thickness. Finally, the calculation of mean absolute error between predicted and ground truth RNFL thickness was performed. Results: Based on the testing database, SD-OCT segmentation had an average dice similarity coefficient of 0.91, and thickness estimation had a mean absolute error of 2.23 ± 2.1 μm. As compared to conventional OCT software algorithms, deep learning predictions were better correlated with the best available estimate during the test period (r2 = 0.99 vs r2 = 0.88, respectively; P < 0.001). Conclusion: Our experimental results demonstrate effective and precise segmentation of the RNFL layer with the coefficient of 0.91 and reliable thickness prediction with MAE 2.23 ± 2.1 μm in SD-OCT B-scans. Performance is comparable with human annotation of the RNFL layer and other algorithms according to the correlation coefficient of 0.99 and 0.88, respectively, while artifacts and errors are evident.

show abstract

Learning a complex network representation for shape classification

Ribas,

Bruno

2024

Pattern Recognition

View full text Add to dashboard Cite

Distance and Edge Transform for Skeleton Extraction

Cited by 4 publications

References 18 publications

Skeleton Ground Truth Extraction: Methodology, Annotation Tool and Benchmarks

Skeleton Ground Truth Extraction: Methodology, Annotation Tool and Benchmarks

Correction of Retinal Nerve Fiber Layer Thickness Measurement on Spectral-Domain Optical Coherence Tomographic Images Using U-net Architecture

Learning a complex network representation for shape classification

Contact Info

Product

Resources

About