Two-stage local and global fingerprint matching technique for automated fingerprint verification/identification

• US 6,778,685 B1
• Filed: 07/06/2000
• Issued: 08/17/2004
• Est. Priority Date: 07/08/1999
• Status: Expired due to Term

• Current Assignee: Centre For Signal Processing of The Nanyang Technology
• Original Assignee: Nanyang Technological University
• Inventors: Jiang, Xudong, Ser, Wee, Yau, Wei Yun
• Primary Examiner(s): Ahmed, Samir
• Assistant Examiner(s): LE, BRIAN Q
• Application Number:
  US09/611,951
• Time in Patent Office: 1,503 Days
• Field of Search: 382/124, 382/115, 382/116, 382/312, 382/315, 382/125, 340/5.53, 340/5.83, 396/15, 283/68, 283/78, D14/384
• US Class Current: 382/124
• CPC Class Codes: G06V 40/1365 Matching; Classification

Abstract

A method for determining a degree of match between a search fingerprint and a reference fingerprint comprises the following steps:

a) Extracting at least one first search feature from a first region of said search fingerprint thereby forming a local search feature vector,

b) Extracting at least one second search feature from a second region of said search fingerprint thereby forming a global search feature vector, whereby said second region comprises said first region,

c) Determining a first similarity degree by comparing said local search feature vector with a local reference feature vector,

d) Determining a second similarity degree by comparing said global search feature vector with a global reference feature vector of said reference fingerprint and using said first similarity degree,

e) Determining said degree of match from said second similarity degree.

Claims

1. A method for determining a degree of match between a search fingerprint and a reference fingerprint comprising the following steps:

extracting at least one first search feature from a first region of said search fingerprint thereby forming a local search feature vector,

extracting at least one second search feature from a second region of said search fingerprint thereby forming a global search feature vector, wherein said second region comprises said first region,

determining a first similarity degree by comparing said local search feature vector with a local reference feature vector of said reference fingerprint,

determining a second similarity degree by comparing said global search feature vector with a global reference feature vector of said reference fingerprint and using said first similarity degree;

determining said degree of match from said second similarity degree, wherein said feature vectors describe minutiae of said fingerprints or a relation between minutiae of said fingerprints; and

further comprising the steps of

determining said first similarity degree for all minutiae in said first region,

determining a best match local structure pair of minutiae by using said first similarity degrees,

aligning all minutiae in said second region based on said best match local structure pair, thereby forming said global search feature vector; and

wherein said first similarity degree cl(k1, k2) is determined using the following formula;

$\mathrm{c1}<br><br>\left(\mathrm{k1},\mathrm{k2}\right)=\{\begin{array}{cc}\frac{\mathrm{b1}-W\times <br><br><br><br>{\mathrm{FL}}_{\mathrm{k1}}^S-{\mathrm{FL}}_{\mathrm{k2}}^R<br><br>}{\mathrm{b1}},& \mathrm{if}<br><br>\text{\hspace{1em}<br><br>}<br><br>W\times <br><br><br><br>{\mathrm{FL}}_{\mathrm{k1}}^S-{\mathrm{FL}}_{\mathrm{k2}}^R<br><br><<br><br>\mathrm{b1}\\ 0,& \mathrm{Others}\end{array}$

wherein

bl is a freely selectable local threshold,

W is a freely selectable weight vector that specifies the weight associated with each component of said feature vector,

FL_k1^S is a local search feature vector of minutia k1,

FL_k2^R is a local reference feature vector of minutia k2.

2. A method according to claim 1, wherein said features are independent from rotation and/or translation of the fingerprints compared with a given coordinate system.

3. A method according to claim 1 or 2 wherein

said first region comprises a given first amount of neighbor minutiae,

said second region comprises a given second amount of neighbor minutiae,

said second amount is larger than said first amount.

4. A method according to claim 1, wherein said second similarity degree cg(k1, k2) is determined using the following formula:

$\mathrm{cg}<br><br>\left(\mathrm{k1},\mathrm{k2}\right)=\{\begin{array}{cc}\mathrm{c1}<br><br>\left(\mathrm{k1},\mathrm{k2}\right),& \mathrm{if}<br><br>\text{\hspace{1em}<br><br>}<br><br><br><br>{\mathrm{FG}}_{\mathrm{k1b}}^S-{\mathrm{FG}}_{\mathrm{k2b}}^R<br><br><<br><br>\mathrm{bg}\\ 0,& \mathrm{Others}\end{array},$

wherein

bg is a freely selectable global threshold vector,

FG_k1b^S is a global search feature vector of minutia k1,

FG_k2b^R is a global reference feature vector of minutia k2.

5. A method according to claim 4, wherein said degree of match is determined using the following formula:

$m<br><br>\text{\hspace{1em}<br><br>}<br><br>s=\frac{\sum <br><br>\mathrm{cg}<br><br>\left(\mathrm{k1},\mathrm{k2}\right)}{\max <br><br>\left(\mathrm{N1},\mathrm{N2}\right)},$

wherein N1 and N2 are the numbers of minutiae in a common region of said search fingerprint and said reference fingerprint, and ms is said degree of match.