| 摘要 |
A computer implemented method for differentiating between elements of an image and a background includes inputting an image comprising pixels forming a view of the elements and a background (100), providing a model for assigning a probability of belonging to a predefined class to each of the pixels (101), assigning a probability to each of the pixels of belonging to the predefined class (102), labeling each of the pixels according to a corresponding probability and a predefined threshold (103), determining boundaries between groups of like-labeled pixels (104), and outputting a visualization of the boundaries (106). |
