METHOD FOR MEASURING THE BOUNDARY PERFORMANCE OF A SEMANTIC SEGMENTATION NETWORK

摘要

A method for evaluating the boundary performance of a semantic segmentation network in a convolutional neural network. A method for measuring the boundary performance of a semantic segmentation network includes the steps: determining an original boundary mask defining a boundary between different classes of an image; determining a thickened boundary mask dependent on the original boundary mask using morphological operations; determining a true positive rate, a false positive rate and a false negative rate dependent on the original boundary mask and/or the thickened boundary mask; and determining a final boundary metric, indicating the boundary performance, dependent on the determined true positive rate, the determined false positive rate and the determined false negative rate.