文章基本信息

标题：A NEW TECHNIQUE FOR ESTIMATING AND ENHANCING ORIENTATION FIELD OF FINGERPRINT IMAGE
本地全文：下载
作者：ALAA AHMED ABBOOD ; GHAZALI SULONG ; AHMED MAJID TAHA 等
期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2018
卷号：96
期号：7
出版社：Journal of Theoretical and Applied
摘要：The direction of fingerprint patterns normally changes from one block to another, which makes it necessary to have information about neighbouring blocks to obtain the original shape of the fingerprint patterns. This paper introduced a novel approach for orientation field calculation using an innovative filter formed as Epicycloid window shape. In which estimates the orientation fields of each block in the main space of work, to create true-angle orientation fields. The calculation procedure of the proposed method is executed by first dividing the image into blocks of pixels with size (16x16). Then, Epicycloid shape filter with k=4 is located surrounding the target block to extract some information from its 8 neighbours. Finally, calculate the local gradient for each target block which is values later used to estimate the gradient angle θ for that block. The obtained patterns then grouped together to form four distinct homogenous regions using a region growing technique. The current method was evaluated using the NIST-14 database and showed reliable results on different quality images.
关键词：Fingerprint Image Enhancement; Orientation Field Estimations; Epicycloid Window Shape Filter; Region-Growing Technique; Feature Extraction