TY - GEN
T1 - The effects of JPEG2000 on ear recognition system
AU - Khalaf, Doaa
AU - Omara, Ibrahim
AU - Hagag, Ahmed
AU - Liu, Shaohui
N1 - Publisher Copyright:
©2018 Association for Computing Machinery.
PY - 2018/5/16
Y1 - 2018/5/16
N2 - Recently, JPEG2000 standard has played a vital role on biometric applications such as face and finger-print biometrics. Ear biometric system is observed as one of the efficient biometric trait. The ear is large and passive trait, making ear image acquisition more easily from a distance and can use in surveillance applications. Therefore, we study the impact of JPEG2000 on ear recognition performance which the ear image may transfer over low quality wireless channels. Local descriptors like POEM, LPQ, LBP, and BSIF are used to represent and extract ear image features. Then, JPEG2000 is exploited to compress the image of ear. Finally, support vector machine is adopted for ear recognition at various compression rates. To evaluate our study, the experimental results are conducted on two public ear databases; USTB and IIT Delhi databases. The results show the superior of LPQ descriptors till compression rate 0.4 bpp.
AB - Recently, JPEG2000 standard has played a vital role on biometric applications such as face and finger-print biometrics. Ear biometric system is observed as one of the efficient biometric trait. The ear is large and passive trait, making ear image acquisition more easily from a distance and can use in surveillance applications. Therefore, we study the impact of JPEG2000 on ear recognition performance which the ear image may transfer over low quality wireless channels. Local descriptors like POEM, LPQ, LBP, and BSIF are used to represent and extract ear image features. Then, JPEG2000 is exploited to compress the image of ear. Finally, support vector machine is adopted for ear recognition at various compression rates. To evaluate our study, the experimental results are conducted on two public ear databases; USTB and IIT Delhi databases. The results show the superior of LPQ descriptors till compression rate 0.4 bpp.
KW - Ear recognition
KW - JPEG2000
KW - Local features
KW - SVM
UR - https://www.scopus.com/pages/publications/85054848204
U2 - 10.1145/3230820.3230831
DO - 10.1145/3230820.3230831
M3 - 会议稿件
AN - SCOPUS:85054848204
SN - 9781450363945
T3 - ACM International Conference Proceeding Series
SP - 13
EP - 17
BT - ICBEA 2018 - Proceedings of 2018 2nd International Conference on Biometric Engineering and Applications
PB - Association for Computing Machinery
T2 - 2nd International Conference on Biometric Engineering and Applications, ICBEA 2018
Y2 - 16 May 2018 through 18 May 2018
ER -