Refereed Publications
- T. Wakahara, Y. Kimura, A. Suzuki, A. Shio, and M. Sano,
“Fingerprint Verification Using Ridge Direction Distribution
and Minutiae Correspondence,” The Transactions of
the IEICE, Vol. J86-D-II, No. 1, pp. 63-71, 2003 (in Japanese).
Abstract - This paper
describes a new technique of fingerprint verification
realizing high-accuracy normalization with respect to
position and rotation as preprocessing and stable minutiae
matching in the subsequent verification stage. The proposed
method consists of three parts; (1) extraction of ridge
direction distribution features and effective adjustments
for position and rotation using feature matching between
input and enrolled fingerprint images, (2) optimal combinatorial
search for one-to-one minutiae correspondence between
input and enrolled minutiae, (3) robust fingerprint verification
using both the ridge direction distribution distance and
the minutiae matching rate. Exhaustive experiments using
a database of 80 people × 4 fingers × 10 samples
demonstrate sufficiently low rates of both FAR (false
acceptance rate) and FRR (false reject rate).
- T. Wakahara, “Shape Matching Using GAT Correlation
against Nonlinear Distortion and its Application to Handwritten
Numeral Recognition,” Proc. of 7th International
Conference on Document Analysis and Recognition (ICDAR’03),
pp. 54-58, Edinburgh, August 2003.
Abstract - This paper
addresses the problem of to what extent linear transformation
can alleviate nonlinear distortion. We investigate a technique
of global affine transformation (GAT) correlation to absorb
linear distortion between gray-scale images. Features
used in GAT correlation are occurrence probabilities of
gray levels or gradients. Experiments using the handwritten
numeral database IPTP CDROM1B show that the entropy of
GAT-superimposed images decreases by around 15%. Furthermore,
gray-level-based GAT correlation improves the recognition
rate from 85.78% to 91.01%, while gradient-based GAT correlation
improves the recognition rate from 91.80% to 94.02%. These
results show that GAT correlation has a marked effect
of improving both shape matching and discrimination abilities
by extracting linear distortion from nonlinear one.
Other Publications
- A. Suzuki, A. Shio, T. Wakahara, M. Sano, and Y. Kimura,
“Development of Fingerprint Verification Technique
Using Ridge Direction Distribution and Minutiae Correspondence,”
IMAGE LAB, Vol. 14, No. 9, pp. 26-30, 2003 (in Japanese).
>PAGE TOP
|
|
|
