Abstract
Limited processing power, hand pose variations, complicated backgrounds and changing illumination are some of the inherent problems in mobile palmprint recognition. In this paper, a hand-shaped guide window is proposed for fast processing of image acquisition, valley point detection and verification to deal with such problems. Also, an improved version of the Competitive Code is proposed in order to cope with the variation in mobile images, and two practical verification scenarios are suggested to further improve the verification performance. A palmprint database was established using mobile phones for experiments, and an equal error rate (EER) of 2.88% was achieved by using the conventional 1-to-1 matching strategy. By applying the suggested practical scenarios, the verification accuracy was improved to achieve an EER of 0.97%.
| Original language | English |
|---|---|
| Article number | 7298090 |
| Pages (from-to) | 311-319 |
| Number of pages | 9 |
| Journal | IEEE Transactions on Consumer Electronics |
| Volume | 61 |
| Issue number | 3 |
| DOIs | |
| Publication status | Published - 2015 Aug 1 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Media Technology
- Electrical and Electronic Engineering
Cite this
}
An empirical study of palmprint recognition for mobile phones. / Kim, Jin Su; Li, Gen; Son, Byungjun; Kim, Jaihie.
In: IEEE Transactions on Consumer Electronics, Vol. 61, No. 3, 7298090, 01.08.2015, p. 311-319.Research output: Contribution to journal › Article
TY - JOUR
T1 - An empirical study of palmprint recognition for mobile phones
AU - Kim, Jin Su
AU - Li, Gen
AU - Son, Byungjun
AU - Kim, Jaihie
PY - 2015/8/1
Y1 - 2015/8/1
N2 - Limited processing power, hand pose variations, complicated backgrounds and changing illumination are some of the inherent problems in mobile palmprint recognition. In this paper, a hand-shaped guide window is proposed for fast processing of image acquisition, valley point detection and verification to deal with such problems. Also, an improved version of the Competitive Code is proposed in order to cope with the variation in mobile images, and two practical verification scenarios are suggested to further improve the verification performance. A palmprint database was established using mobile phones for experiments, and an equal error rate (EER) of 2.88% was achieved by using the conventional 1-to-1 matching strategy. By applying the suggested practical scenarios, the verification accuracy was improved to achieve an EER of 0.97%.
AB - Limited processing power, hand pose variations, complicated backgrounds and changing illumination are some of the inherent problems in mobile palmprint recognition. In this paper, a hand-shaped guide window is proposed for fast processing of image acquisition, valley point detection and verification to deal with such problems. Also, an improved version of the Competitive Code is proposed in order to cope with the variation in mobile images, and two practical verification scenarios are suggested to further improve the verification performance. A palmprint database was established using mobile phones for experiments, and an equal error rate (EER) of 2.88% was achieved by using the conventional 1-to-1 matching strategy. By applying the suggested practical scenarios, the verification accuracy was improved to achieve an EER of 0.97%.
UR - http://www.scopus.com/inward/record.url?scp=84945135268&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84945135268&partnerID=8YFLogxK
U2 - 10.1109/TCE.2015.7298090
DO - 10.1109/TCE.2015.7298090
M3 - Article
AN - SCOPUS:84945135268
VL - 61
SP - 311
EP - 319
JO - IEEE Transactions on Consumer Electronics
JF - IEEE Transactions on Consumer Electronics
SN - 0098-3063
IS - 3
M1 - 7298090
ER -