Deep Learning for Biometrics by Bir Bhanu & Ajay Kumar

Author:Bir Bhanu & Ajay Kumar
Language: eng
Format: epub
ISBN: 9783319616575
Publisher: Springer International Publishing

6.4.2 Metrics and Measurements

In order to facilitate holistic statistical analysis and proper assessment of the capabilities of the FCEDNs and the other conventional algorithms on iris segmentation, we have considered a set of evaluation metrics, which cover key segmentation measures such as: true positives (tp), false negatives (fn), and false positive (fp). To this extent, primarily the NICE.I protocol, which is widely accepted for evaluation of iris segmentation accuracy, got adapted. The segmentation error score nice1 calculates the proportion of corresponding disagreeing pixels (by the logical exclusive-or operator) over all the image as follows:

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.