Since we know that we can calculate f-score using percision and recall very easily in classificaiton task.
When it comes to edge detection, how can we measure f-score? Can you explain?
You can read this classical paper: (TPAMI'04)Learning to detect natural image boundaries using local brightness, color, and texture cues
This paper defines current metrics for edge detection.
Since we know that we can calculate f-score using percision and recall very easily in classificaiton task. When it comes to edge detection, how can we measure f-score? Can you explain?
Thanks,