Difference between revisions of "Publications/yoruk.06.itip"
From LRDE
(Created page with "{{Publication | date = 2006-07-01 | authors = Erdem Yörük, Ender Konukoglu, Bülent Sankur, Jérôme Darbon | title = Shape-based hand recognition | journal = IEEE Transacti...") |
|||
Line 10: | Line 10: | ||
| urllrde = 2006XX-ITIP |
| urllrde = 2006XX-ITIP |
||
| abstract = The problem of person recognition and verification based on their hand images has been addressed. The system is based on the images of the right hands of the subjectscaptured by a flatbed scanner in an unconstrained pose at 45 dpi. In a preprocessing stage of the algorithm, the silhouettes of hand images are registered to a fixed posewhich involves both rotation and translation of the hand and, separately, of the individual fingers. Two feature sets have been comparatively assessed, Hausdorff distance of the hand contours and independent component features of the hand silhouette images. Both the classification and the verification performances are found to be very satisfactory as it was shown that, at least for groups of about five hundred subjects, hand-based recognition is a viable secure access control scheme. |
| abstract = The problem of person recognition and verification based on their hand images has been addressed. The system is based on the images of the right hands of the subjectscaptured by a flatbed scanner in an unconstrained pose at 45 dpi. In a preprocessing stage of the algorithm, the silhouettes of hand images are registered to a fixed posewhich involves both rotation and translation of the hand and, separately, of the individual fingers. Two feature sets have been comparatively assessed, Hausdorff distance of the hand contours and independent component features of the hand silhouette images. Both the classification and the verification performances are found to be very satisfactory as it was shown that, at least for groups of about five hundred subjects, hand-based recognition is a viable secure access control scheme. |
||
+ | | lrdekeywords = Image |
||
| type = article |
| type = article |
||
| id = yoruk.06.itip |
| id = yoruk.06.itip |
||
Line 38: | Line 39: | ||
as it was shown that, at least for groups of about five |
as it was shown that, at least for groups of about five |
||
hundred subjects, hand-based recognition is a viable secure |
hundred subjects, hand-based recognition is a viable secure |
||
− | access control scheme.<nowiki>}</nowiki> |
+ | access control scheme.<nowiki>}</nowiki>, |
+ | lrdekeywords = <nowiki>{</nowiki>Image<nowiki>}</nowiki> |
||
<nowiki>}</nowiki> |
<nowiki>}</nowiki> |
||
Revision as of 18:09, 4 November 2013
- Authors
- Erdem Yörük, Ender Konukoglu, Bülent Sankur, Jérôme Darbon
- Journal
- IEEE Transactions on Image Processing
- Type
- article
- Keywords
- Image
- Date
- 2006-07-01
Abstract
The problem of person recognition and verification based on their hand images has been addressed. The system is based on the images of the right hands of the subjectscaptured by a flatbed scanner in an unconstrained pose at 45 dpi. In a preprocessing stage of the algorithm, the silhouettes of hand images are registered to a fixed posewhich involves both rotation and translation of the hand and, separately, of the individual fingers. Two feature sets have been comparatively assessed, Hausdorff distance of the hand contours and independent component features of the hand silhouette images. Both the classification and the verification performances are found to be very satisfactory as it was shown that, at least for groups of about five hundred subjects, hand-based recognition is a viable secure access control scheme.
Bibtex (lrde.bib)
@Article{ yoruk.06.itip, author = {Erdem Y\"or\"uk and Ender Konukoglu and B\"ulent Sankur and J\'er\^ome Darbon}, title = {Shape-based hand recognition}, journal = {IEEE Transactions on Image Processing}, year = 2006, volume = 15, number = 7, pages = {1803--1815}, month = jul, project = {Image}, abstract = {The problem of person recognition and verification based on their hand images has been addressed. The system is based on the images of the right hands of the subjects, captured by a flatbed scanner in an unconstrained pose at 45 dpi. In a preprocessing stage of the algorithm, the silhouettes of hand images are registered to a fixed pose, which involves both rotation and translation of the hand and, separately, of the individual fingers. Two feature sets have been comparatively assessed, Hausdorff distance of the hand contours and independent component features of the hand silhouette images. Both the classification and the verification performances are found to be very satisfactory as it was shown that, at least for groups of about five hundred subjects, hand-based recognition is a viable secure access control scheme.}, lrdekeywords = {Image} }