Fingerprint image enhancement: algorithm and performance evaluation
ABSTRACT In order to ensure that the performance of an automatic
fingerprint identification/verification system will be robust with
respect to the quality of input fingerprint images, it is essential to
incorporate a fingerprint enhancement algorithm in the minutiae
extraction module. We present a fast fingerprint enhancement algorithm,
which can adaptively improve the clarity of ridge and valley structures
of input fingerprint images based on the estimated local ridge
orientation and frequency. We have evaluated the performance of the
image enhancement algorithm using the goodness index of the extracted
minutiae and the accuracy of an online fingerprint verification system.
Experimental results show that incorporating the enhancement algorithm
improves both the goodness index and the verification accuracy
- SourceAvailable from: Guangwei Gao[Show abstract] [Hide abstract]
ABSTRACT: 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.Neurocomputing 01/2014; 135:180–191. · 1.63 Impact Factor
- [Show abstract] [Hide abstract]
ABSTRACT: In this study, a high accuracy fingerprint classification method is proposed to enhance the performance in terms of efficiency for fingerprint recognition system. The recognition system has been considered as a reliable mechanism for criminal identification and forensic for its invariance property, yet the huge database is the key issue to make the system obtuse. In former works, the pre-classifying manner is an effective way to speed up the process, yet the accuracy of the classification dominates the further recognition rate and processing speed. In this paper, a rule-based fingerprint classification method is proposed, wherein the two features, including the types of singular points and the number of each type of point are adopted to distinguish different fingerprints. Moreover, when fingerprints are indistinguishable, the proposed Center-to-Delta Flow (CDF) and Balance Arm Flow (BAF) are catered for further classification. As documented in the experimental results, a good accuracy rate can be achieved, which endorses the effectiveness of the fingerprint classification scheme for the further fingerprint recognition system.Expert Systems with Applications: An International Journal. 02/2014; 41(2):752-764.
- [Show abstract] [Hide abstract]
ABSTRACT: The paper studies a 3D fingerprint reconstruction technique based on multi-view touchless fingerprint images. This technique offers a solution for 3D fingerprint image generation and application when only multi-view 2D images are available. However, the difficulties and stresses of 3D fingerprint reconstruction are the establishment of feature correspondences based on 2D touchless fingerprint images and the estimation of the finger shape model. In this paper, several popular used features, such as scale invariant feature transformation (SIFT) feature, ridge feature and minutiae, are employed for correspondences establishment. To extract these fingerprint features accurately, an improved fingerprint enhancement method has been proposed by polishing orientation and ridge frequency maps according to the characteristics of 2D touchless fingerprint images. Therefore, correspondences can be established by adopting hierarchical fingerprint matching approaches. Through an analysis of 440 3D point cloud finger data (220 fingers, 2 pictures each) collected by a 3D scanning technique, i.e., the structured light illumination (SLI) method, the finger shape model is estimated. It is found that the binary quadratic function is more suitable for the finger shape model than the other mixed model tested in this paper. In our experiments, the reconstruction accuracy is illustrated by constructing a cylinder. Furthermore, results obtained from different fingerprint feature correspondences are analyzed and compared to show which features are more suitable for 3D fingerprint images generation.Pattern Recognition. 01/2014; 47(1):178-193.
P erformance Ev aluation
Lin Hong?YifeiWan? andAnilJain
Michigan StateUniv ersity
A criticalstep inautomatic?ngerprint matchingistoautomatical ly andreliablyextract
minutiaefromtheinput?ngerprintimages?However?the performanceof aminutiaeex?
andfurrowstructures of input?ngerprint imagesbasedontheestimate dlo cal ridgeorienta?
usingthegoodnessindexoftheextr actedminutiae andtheaccuracyofanonline?ngerprint
Fingerprintidenti?cationis oneofthemostimportantbiometrictec hnologieswhichhas
drawnasubstantialamountofattentionrecently ????????A?ngerprintisthepattern of
ridges andfurrowsonthe surfaceofa?ngertip?Eachindividualhasunique?ngerprints?
Theuniqueness ofa?ngerprintisexclusiv elydeterminedbythelocal ridgecharacteristics
Ridge Bifurcation Ridge Ending
Figure??Examplesof minutiae??a?aminutiaecanbecharacterizedbyitsp ositionand its
orientation??b?minutiaeov erlaidon a?ngerprint image?
andtheir relationships????????Atotalofonehundredand?fty di?erentlocalridgechar?
qualityof ?ngerprints andarerarelyobservedin?ngerprints?Thetwomostprominentridge
characteristics? calledminutiae? are?i?ridge endingand?ii? ridge bifurc ation?Aridge end?
ingisde?nedasthepointwherearidge endsabruptly?Aridgebifurcationis de?nedasthe
containsabout??????minutiae? Examplesofminutiaearesho wnin Figure??
Automatic ?ngerprint matc hingdep endsonthecomparisonoftheselocalridgec har?
acteristics andtheirrelationshipstomakeapersonal iden ti?cation?????Acriticalstepin
print images?whichisadi?culttask?Theperformanceofaminutiaeextraction algorithm
relies heavilyon the quality of theinput?ngerprintimages? Inanideal?ngerprintimage?
ridgesandfurro wsalternateand?ow ina locally constan tdirection andmin utiae areanoma?
Figure ??Fingerprintimages ofverypoorqualit y?
liesofridges?i?e?ridgeendingsandridgebifurcations?Insuch situations?the ridges canbe
easilydetectedandminutiaecanbe preciselylocatedfrom thebinary ridges? Figure??b?
sho wsanexampleof good quality liv e?scan?ngerprint image?Howev er?in practice?due
tovariationsin impressionconditions?ridgecon?guration?skin conditions ?aberrant forma?
?ngerprintimages?appro ximately???accordingtoourexperience? isofpoorquality?The
cannotbe correctlydetected?Thisleadstofollowingproblems? ?i?asigni?cantnumber of
spuriousminutiaemaybecreated??ii?alargepercentofgenuine min utiaemaybeignored?
and?iii?largeerrors intheirlocalization ?p osition andorien tation?maybein troduced?Ex?
amplesof?ngerprintimages ofverypo orquality? inwhic h ridge structuresare completely
corrupted?are sho wn inFigure ?? Inordertoensurethatthep erformance of themin utiae
Figure??Fingerprintregions??a?well?de?ned region??b?recoverable corrupted region??c?
unreco verable corrupted region?
extractionalgorithmwillbe robustwithresp ect tothequalit yofinputdigital?ngerprint
images?anenhancemen talgorithmwhichcanimprovethe clarityoftheridgestructuresis
visualcluessuchas localridgeorientation?ridgecontinuity?ridge tendency? etc?? aslong
astheridge andfurrowstructuresare notcorruptedcompletely?Itis possibleto develop
anenhancementalgorithmthatexploits thesevisual cluestoimprovetheclarit y ofridge
structures incorrupted?ngerprintimages?Generally? foragiv endigital?ngerprintimage?
theregion ofinterest canbedivided intothefollowingthreecategories?Figure???
?Well?de?nedregion? whereridgesandfurrows areclearlydi?erentiatedfrom onean?
other suchthataminutiaeextractionalgorithmis abletooperatereasonably?
?Recover ablecorruptedregion? whereridgesand furrowsarecorruptedbya smallamount
ofcreases? smudges?etc?But?theyarestillvisibleandtheneighboringregionspro vide
su?cientinformation aboutthe trueridgeandfurrowstructures?
?Unrecoverablec orruptedregion?where ridgesandfurrows arecorruptedbysucha
sev ereamount ofnoise anddistortion thatno ridgesandfurrowsarevisibleandthe
neighboringregionsdonotpro videsu?cientinformationaboutthe trueridgeand
furrow structures either?
Werefertothe?rsttwocategoriesofregions asrecoverable and thelast categoryasunrecov?
erable?Thegoal ofan enhancement algorithmistoimpr ovetheclarityofridgestructur esof
?ngerprintimages inreco verableregionsand toremo vetheunrecoverableregions?Sincethe
ofinput ?ngerprintimagestofacilitatetheextractionofridgesandminutiae?a?ngerprin t
enhancementalgorithm should notresultin anyspurious ridgestructures?Thisisveryim?
portantb ecausespuriousridgestructure maychange theindividualityofinput?ngerprints?
Fingerprin t enhancementcanbeconducted on either?i?binaryridgeimagesor?ii?gray?
levelimages?Abinaryridgeimageisanimagewhereall the ridgepixelsareassignedav alue
?and non?ridgepixelsare assignedavalue ??Thebinary imagecanbeobtained by applying
aridgeextractionalgorithmonagra y?level?ngerprint image???? Sinceridges andfurrows
ina?ngerprintimagealternate andrunparallelto eachotherinalo calneighborho od?a
numberofsimpleheuristics canbeused todi?erentiate thespuriousridgecon?gurations
from thetrue ridgecon?gurationsina binaryridge image???? Howev er? afterapplying
aridgeextractionalgorithmon the originalgra y?levelimages?informationaboutthetrue
ridgestructuresisoftenlost dependingonthe performance oftheridgeextractionalgorithm?
Therefore?enhancementofbinary ridgeimageshasits inherent limitations?
Ina gray?level ?ngerprintimage?ridgesandfurrows ina local neighb orhood forma