# Image Segmentation on GHIS

Source: [Image Segmentation on GHIS](<https://www.sota2.com/research/sota/image-segmentation-on-ghis>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:40:50.480Z

Evaluation of Image Segmentation performance on the GHIS dataset, reporting metrics such as Dice, IoU, Precision, and Recall.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Image Segmentation |
| Dataset (including any stated split) | GHIS |
| Metric | Dice |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Dice](<https://www.sota2.com/research/sota/image-segmentation-on-ghis.md?metric=Dice>): Higher is better; unit: PERCENT.

- [IoU](<https://www.sota2.com/research/sota/image-segmentation-on-ghis.md?metric=IoU>): Higher is better; unit: PERCENT.

- [Precision](<https://www.sota2.com/research/sota/image-segmentation-on-ghis.md?metric=Precision>): Higher is better; unit: PERCENT.

- [Recall](<https://www.sota2.com/research/sota/image-segmentation-on-ghis.md?metric=Recall>): Higher is better; unit: PERCENT.

- [Specificity](<https://www.sota2.com/research/sota/image-segmentation-on-ghis.md?metric=Specificity>): Higher is better; unit: PERCENT.

- [RVD](<https://www.sota2.com/research/sota/image-segmentation-on-ghis.md?metric=RVD>): Lower is better; unit: SCALAR.

- [Accuracy](<https://www.sota2.com/research/sota/image-segmentation-on-ghis.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Dice | Result date | Report paper |
| --- | --- | --- | --- |
| HCRF | 46.29 | Not recorded | 68fa688b1e209131cea1cd53 |
| DenseCRF | 45.78 | Not recorded | 68fa688b1e209131cea1cd53 |
| U-Net | 45.57 | Not recorded | 68fa688b1e209131cea1cd53 |
| Watershed | 26.13 | Not recorded | 68fa688b1e209131cea1cd53 |
| Otsu thresholding | 25.34 | Not recorded | 68fa688b1e209131cea1cd53 |
| k-means | 25.34 | Not recorded | 68fa688b1e209131cea1cd53 |
| MRF | 23.96 | Not recorded | 68fa688b1e209131cea1cd53 |
| SegNet | 20.08 | Not recorded | 68fa688b1e209131cea1cd53 |

### HCRF

Dice: 46.29. Result ID: 698d76de8b517eb43321b1a9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa688b1e209131cea1cd53.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa688b1e209131cea1cd53.md>)

[Implementation](<http://dx.doi.org/10.17632/thgf23xgy7.2>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DenseCRF

Dice: 45.78. Result ID: 698d76de8b517eb43321b1aa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa688b1e209131cea1cd53.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa63541e209131ce9fe382.md>)

[Implementation](<http://liangchiehchen.com/projects/DeepLab.html>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### U-Net

Dice: 45.57. Result ID: 698d76de8b517eb43321b1ab.

[Reporting paper](<https://www.sota2.com/research/paper/68fa688b1e209131cea1cd53.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa61e11e209131ce9f653d.md>)

[Implementation](<http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Watershed

Dice: 26.13. Result ID: 698d76de8b517eb43321b1ae.

[Reporting paper](<https://www.sota2.com/research/paper/68fa688b1e209131cea1cd53.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Otsu thresholding

Dice: 25.34. Result ID: 698d76de8b517eb43321b1ad.

[Reporting paper](<https://www.sota2.com/research/paper/68fa688b1e209131cea1cd53.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### k-means

Dice: 25.34. Result ID: 698d76de8b517eb43321b1af.

[Reporting paper](<https://www.sota2.com/research/paper/68fa688b1e209131cea1cd53.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MRF

Dice: 23.96. Result ID: 698d76de8b517eb43321b1b0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa688b1e209131cea1cd53.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SegNet

Dice: 20.08. Result ID: 698d76de8b517eb43321b1ac.

[Reporting paper](<https://www.sota2.com/research/paper/68fa688b1e209131cea1cd53.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa62d51e209131ce9fb761.md>)

[Implementation](<http://mi.eng.cam.ac.uk/projects/segnet/>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.