SlapSegII Analysis: Matching Segmented Fingerprint Images

This report is an extension of the SlapSegII evaluation and will study the affect of slap fingerprint segmentation on matching accuracy. This study will compare matching accuracy of hand marked segmentation data with the automated segmentation algorithms to examine the affect of automated fingerprint segmentation on matcher accuracy. A couple issues this study will attempt to examine are: 1) How detrimental is excluding fingerprint ridge structure (over-segmentation) to matching? 2) How much can fusion of multiple fingers compensate for bad segmentation? The only dataset from SlapSegII with mates available for matching is the 2-inch dataset so the study will look at matching accuracy for single finger, two index fingers and eight fingers (no thumbs).