Difference between revisions of "Publications/yoruk.04.eusipco"
From LRDE
(Created page with "{{Publication | date = 2004-09-01 | authors = Erdem Yoruk, Ender Konukoglu, Bulent Sankur, Jérôme Darbon | title = Person authentication based on hand shape | booktitle = Pr...") |
|||
Line 8: | Line 8: | ||
| urllrde = 200409-EUSIPCO |
| urllrde = 200409-EUSIPCO |
||
| abstract = The problem of person identification 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. 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, separatelyof the individual fingers. Independent component features of the hand silhouette images are used for recognition. The classification performance is found to be very satisfactory and it was shown that, at least for groups of one hundred subjects, hand-based recognition is a viable secure access control scheme. |
| abstract = The problem of person identification 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. 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, separatelyof the individual fingers. Independent component features of the hand silhouette images are used for recognition. The classification performance is found to be very satisfactory and it was shown that, at least for groups of one hundred subjects, hand-based recognition is a viable secure access control scheme. |
||
+ | | lrdekeywords = Image |
||
| type = inproceedings |
| type = inproceedings |
||
| id = yoruk.04.eusipco |
| id = yoruk.04.eusipco |
||
Line 33: | Line 34: | ||
and it was shown that, at least for groups of one hundred |
and it was shown that, at least for groups of one hundred |
||
subjects, hand-based recognition is a viable secure access |
subjects, hand-based recognition is a viable secure access |
||
− | control scheme.<nowiki>}</nowiki> |
+ | control scheme.<nowiki>}</nowiki>, |
+ | lrdekeywords = <nowiki>{</nowiki>Image<nowiki>}</nowiki> |
||
<nowiki>}</nowiki> |
<nowiki>}</nowiki> |
||
Revision as of 18:09, 4 November 2013
- Authors
- Erdem Yoruk, Ender Konukoglu, Bulent Sankur, Jérôme Darbon
- Where
- Proceedings of 12th European Signal Processing Conference (EUSIPCO)
- Place
- Vienna, Austria
- Type
- inproceedings
- Keywords
- Image
- Date
- 2004-09-01
Abstract
The problem of person identification 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. 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, separatelyof the individual fingers. Independent component features of the hand silhouette images are used for recognition. The classification performance is found to be very satisfactory and it was shown that, at least for groups of one hundred subjects, hand-based recognition is a viable secure access control scheme.
Bibtex (lrde.bib)
@InProceedings{ yoruk.04.eusipco, author = {Erdem Yoruk and Ender Konukoglu and Bulent Sankur and J\'er\^ome Darbon}, title = {Person authentication based on hand shape}, booktitle = {Proceedings of 12th European Signal Processing Conference (EUSIPCO)}, year = 2004, address = {Vienna, Austria}, month = sep, project = {Image}, abstract = {The problem of person identification 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. 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. Independent component features of the hand silhouette images are used for recognition. The classification performance is found to be very satisfactory and it was shown that, at least for groups of one hundred subjects, hand-based recognition is a viable secure access control scheme.}, lrdekeywords = {Image} }