FINGERPRINT RECOGNITION IN LOW-QUALITY IMAGES

被引：76

作者：

COETZEE, L

BOTHA, EC

机构：

[1] Department of Electrical and Electronic Engineering, University of Pretoria, Pretoria

来源：

PATTERN RECOGNITION | 1993年 / 26卷 / 10期

关键词：

FINGERPRINT RECOGNITION; IMAGE RECOGNITION; ACCESS CONTROL; LOW QUALITY IMAGE RECOGNITION;

D O I：

10.1016/0031-3203(93)90151-L

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Algorithms are identified which are best suited for an automatic fingerprint recognition system operating on low quality images. New preprocessing algorithms for noise removal and binarization are described. Three approaches to classification are investigated: a correlation classifier, and two feature-based classification schemes. The best results on a database of 80 fingerprints are obtained with spatial-frequency features. Three classifiers (neural net, linear classifier and nearest neighbour) using these features are successful in identifying an independent test set. Details of the results are shown. In conclusion suggestions are made concerning the most suitable algorithms in each of the processing steps.

引用

页码：1441 / 1460

页数：20

共 14 条

[1]

Ballard DH, 1982, COMPUTER VISION

[2]

BARNARD E, 1908, CSE89014 OR GRAD CTR

[3] LINE THINNING BY LINE FOLLOWING [J].

BARUCH, O .

PATTERN RECOGNITION LETTERS, 1988, 8 (04) :271-276

[4] GREY-LEVEL THRESHOLDING OF IMAGES USING A CORRELATION CRITERION [J].

BRINK, AD .

PATTERN RECOGNITION LETTERS, 1989, 9 (05) :335-341

[5]

CH T, 1976, PATTERN RECOGN, V8, P181

[6]

COETZEE L, 1990, 1ST P S AFR WORKSH P, V1, P33

[7]

Duda R. O., 1973, PATTERN CLASSIFICATI, V3

[8]

GLOVER DE, 1988, JUL INT C NEUR NETW, pI569

[9]

GOODMAN JW, 1967, INTRO FOURIER OPTICS

[10] AUTOMATED FINGERPRINT RECOGNITION USING STRUCTURAL MATCHING [J].

HRECHAK, AK ;

MCHUGH, JA .

PATTERN RECOGNITION, 1990, 23 (08) :893-904

← 1 2 →