Summary of The Effectiveness Of Edge Detection Evaluation Metrics For Automated Coastline Detection, by Conor O’sullivan et al.
The Effectiveness of Edge Detection Evaluation Metrics for Automated Coastline Detection
by Conor O’Sullivan, Seamus Coveney, Xavier Monteys, Soumyabrata Dev
First submitted to arxiv on: 19 May 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed study investigates the efficiency of four objective evaluation metrics (RMSE, PSNR, SSIM, and FOM) for assessing the performance of edge detection algorithms in automated coastline detection. Typically, visual inspection is used to evaluate the accuracy of detected coastlines, which can be impractical on a large scale. The researchers conducted an experiment using Canny edge detection on 95 satellite images across 49 testing locations, varying the Hysteresis thresholds and comparing metric values with a visual analysis of detected edges. The results show that FOM is the most reliable metric for selecting the best threshold, outperforming RMSE, PSNR, and SSIM. The study also provides insights into why these metrics may not be suitable for evaluating edge detection in general by reformulating them in terms of confusion matrix measures. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary For automated coastline detection, researchers are looking for a way to evaluate how well their algorithms work without having to look at each image individually. They tested four different methods (RMSE, PSNR, SSIM, and FOM) to see which one is best. They used 95 satellite images of coastlines and looked at how well the algorithms worked with different settings. The results showed that one method, FOM, was much better than the others at picking the right settings. This could be important for making accurate maps of coastlines. |
Keywords
» Artificial intelligence » Confusion matrix
