کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
409984 679112 2014 12 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Integration of multiple orientation and texture information for finger-knuckle-print verification
ترجمه فارسی عنوان
ادغام اطلاعات جهت گیری و بافت چندگانه برای تأیید انگشتان دست و پا
کلمات کلیدی
بیومتریک، انگشت دستکش چاپ گرایش، بافت
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر هوش مصنوعی
چکیده انگلیسی

The Competitive Coding (CompCode) scheme, which extracts and codes the local dominant orientation as features, has been widely used in finger knuckle print (FKP) verification. However, CompCode may lose some valuable information such as multiple orientation and texture of the FKP image. To remedy this drawback, a novel multiple orientation and texture information integration scheme is proposed in this paper. As compared with CompCode, the proposed scheme not only considers more orientations, but also introduces a multilevel image thresholding scheme to perform orientation coding on each Gabor filtering response. For texture features extraction, LBP maps are first obtained by performing Local Binary Pattern (LBP) operator on each Gabor filtering response, and then a similar coding scheme is applied on these LBP maps. Finally, multiple orientation and texture features are integrated via score level fusion to further improve FKP verification accuracy. Extensive experiments conducted on the PolyU FKP database show the effectiveness of the proposed scheme.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Neurocomputing - Volume 135, 5 July 2014, Pages 180–191
نویسندگان
, , , ,