Off-angle iris recognition using bi-orthogonal wavelet network system

被引：9

作者：

Abhyankar, A ^{[1
]}

Hornak, L ^{[1
]}

Schuckers, S ^{[1
]}

机构：

[1] Clarkson Univ, Dept Elect & Comp Engn, Potsdam, NY 13676 USA

来源：

FOURTH IEEE WORKSHOP ON AUTOMATIC IDENTIFICATION ADVANCED TECHNOLOGIES, PROCEEDINGS | 2005年

关键词：

D O I：

10.1109/AUTOID.2005.37

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

One important category of non-ideal conditions for iris recognition is off-angle iris images. Practically it is very difficult for images to be captured with no offset. It then becomes necessary to account for off angle information in order to maintain robust performance. A bi-orthogonal wavelet based iris recognition system, previously designed at our lab, is modified and demonstrated to perform off-angle iris recognition. Bi-orthogonal wavelet network (BWN) are developed and trained for each class. The non-ideal factors are adjusted by repositioning the BWN. To test, synthetic iris images are generated by using affine and geometric transforms of 0 degrees, 10 degrees and 20 degrees experimentally collected images from 101 subjects. This approach is shown to perform better than a transformation based iris recognition approach. Iris images off-angle by up to 42 degrees are successfully recognized.

引用

页码：239 / 244

页数：6

共 18 条

[11]

LeCun Y., 1988, P 1988 CONN MOD SUMM, P21, DOI DOI 10.3168/JDS.S0022-0302(88)79586-7

[12]

Limaye BV, 1996, FUNCTIONAL ANAL

[13]

Ma L., 2002, IRIS RECOGNITION USI

[14]

NOH S, 2002, 2002 INT TECHN C CIR

[15]

PRINCIPE J, 2000, P IEEE SPEC ISS ENG

[16]

SZU H, OPTICAL ENG, V31, P1907

[17]

Wildes R. P., 1994, Proceedings of the Second IEEE Workshop on Applications of Computer Vision (Cat. No.94TH06742), P121, DOI 10.1109/ACV.1994.341298

[18] Iris recognition: An emerging biometric technology [J].

Wildes, RP .

PROCEEDINGS OF THE IEEE, 1997, 85 (09) :1348-1363

← 1 2 →