On matching latent fingerprints

Abstract

Latent fingerprint identification is of critical importance to law enforcement agencies in forensics application. While tremendous progress has been made in the field of automatic fingerprint matching, latent fingerprint matching continues to be a difficult problem because the challenges involved in latent print matching are quite different from plain or rolled fingerprint matching. Poor quality of friction ridge impressions, small finger area and large non-linear distortion are some of the main difficulties in latent fingerprint matching. We propose a system for matching latent images to rolled fingerprints that takes into account the specific characteristics of the latent matching problem. In addition to minutiae, additional features like orientation field and quality map are also used in our system. Experimental results on the NIST SD27 latent database indicate that the introduction of orientation field and quality map to minutiae-based matching leads to good recognition performance despite the inherently difficult nature of the problem. We achieve the rank-20 accuracy of 93.4% in retrieving 258 latents from a background database of 2,258 rolled fingerprints.

Full text

Page 1

On Matching Latent Fingerprints
Anil K. Jain, Jianjiang Feng, Abhishek Nagar
Department of Computer Science and Engineering
Michigan State University
East Lansing, MI-48824, U.S.A.
jain,jfeng,nagarabh@msu.edu
Karthik Nandakumar
Institute for Infocomm Research
A*STAR, Fusionopolis, Singapore
knandakumar@i2r.a-star.edu.sg
Abstract
Latent fingerprint identification is of critical importance
to law enforcement agencies in forensics application. While
tremendousprogresshasbeenmadeinthefieldofautomatic
fingerprint matching, latent fingerprint matching continues
to be a difficult problem because the challenges involved in
latent print matching are quite different from plain or rolled
fingerprint matching. Poor quality of friction ridge impres-
sions, small finger area and large non-linear distortion are
some of the main difficulties in latent fingerprint matching.
We propose a system for matching latent images to rolled
fingerprints that takes into account the specific character-
istics of the latent matching problem. In addition to minu-
tiae, additional features like orientation field and quality
map are also used in our system. Experimental results on
the NIST SD27 latent database indicate that the introduc-
tion of orientation field and quality map to minutiae-based
matchingleadstogoodrecognitionperformancedespitethe
inherently difficult nature of the problem. We achieve the
rank-20 accuracy of 93.4% in retrieving 258 latents from a
background database of 2,258 rolled fingerprints.
1. Introduction
Fingerprint images can be broadly classified into three
categories, namely, (i) rolled/full, (ii) plain/flat and (iii) la-
tent [10,12,14] (see Figure 1). Rolled fingerprint images
are obtained by rolling a finger from one side to the other
(“nail-to-nail”) in order to capture all the ridge-details of a
finger. Plain impressions are those in which the finger is
pressed down on a flat surface but not rolled. While plain
impressionscoverasmallerareathanrolledprints, theytyp-
ically do not have the distortion introduced during rolling.
Rolled and plain impressions are obtained either by scan-
ning the inked impression on paper or by using live-scan
1This research was supported by ARO grant W911NF-06-1-0418 and
NIJ grant 2007-RG-CX-K183.
devices. Since rolled and plain fingerprints are acquired in
an attended mode, they are typically of good quality and
are rich in information content. In contrast, latent finger-
prints are lifted from surfaces of objects that are inadver-
tently touched or handled by a person through a variety of
means ranging from simply photographing the print to more
complex dusting or chemical processing [9, 13]. It is the
matching of a latent fingerprint against a database of rolled
prints or latent prints (reference prints) that is of utmost im-
portance in forensics to apprehend a criminal.
(a)(b)(c)
Figure 1. Three types of fingerprint images. (a) Rolled fingerprint,
(b) Plain fingerprint and (c) Latent fingerprint.
Latent fingerprints obtained from crime scenes have
served as crucial evidence in forensic identification for
more than a century. However, there have been instances
where mistakes in latent fingerprint identification have led
to wrongful convictions. One of the most high profile cases
in which such a mistake was made is the case of Brandon
Mayfield who was wrongly apprehended in the Madrid train
bombing incident after a latent fingerprint obtained from
the bombing site was incorrectly matched with his finger-
print in the FBI database [5].
similar cases has been brought to light by the Innocence
project [1]. These incidents and findings have undermined
the importance of latent fingerprints as forensic evidence in
courts of law. This is evident from recent ruling of a Bal-
timore court [6] which excluded fingerprints as evidence in
a murder trial because the prosecutor was not able to jus-
tify the procedure followed in latent fingerprint matching as
An extensive account of

Page 2

being sufficiently error free. It is clear that more research
is needed to advance the state of the art in latent fingerprint
matching.
The manual latent identification process can be divided
into four steps, namely, (i) analysis, (ii) comparison, (iii)
evaluation and (iv) verification. This process is commonly
referred to as the ACE-V procedure in latent fingerprint lit-
erature [8].
• Analysis refers to assessing the latent fingerprint to de-
termine whether sufficient ridge information is present
in the image to be processed and to mark the features
along with the associated quality information. The la-
tent print analysis is usually performed manually by a
human expert (without access to a reference print).
• Comparison refers to the stage where an examiner
compares a latent image to a reference print to as-
certain their similarities or dissimilarities. Fingerprint
features at all three levels (Level-1, Level-2 and Level-
3) are compared at this stage.
• Evaluation stage refers to classifying the fingerprint
pair as individualization (identification or match), ex-
clusion (non-match) or inconclusive.
• Verification is the process of re-examination of a fin-
gerprint pair independently by another examiner in or-
der to verify the results of the first examiner.
It is often argued that matching a latent fingerprint to a
rolled print is more of an “art” than “science” [15,16] be-
cause the matching is based on subjective appraisal of the
two fingerprints in question by a human examiner. More-
over, the decisions made by latent examiners are required to
be “crisp”, i.e., an examiner is expected to provide only one
of the three decisions, viz., individualization (identification
or match), exclusion (non-match) and inconclusive [9,13].
This precludes a latent examiner to prepare a well struc-
tured and quantitative latent examination report which can
be studied to estimate the chances of making an error in a
particular case. Often latent examiners have a huge backlog
of cases and are usually under time pressure to match latent
fingerprints, particularly in high profile cases. Therefore,
it is very important that the cases sent to latent examiners
be efficiently selected by an automatic fingerprint match-
ing system so that the latent examiners can spend adequate
amount of time in matching them.
In order to deal with matching efficiency, the concept
of “Lights-Out System” for latent matching has been intro-
duced [10]. A Lights-Out System is characterized by a fully
automatic (no human intervention) identification process.
Such a system should automatically extract features from
query fingerprints (latent) and match them with a gallery
database (rolled or latent) to obtain a set of possible “hits”
with high confidence so that no human intervention is re-
quired. But due to the limitations of the available algo-
rithms, only “Semi Lights-Out Systems” are currently fea-
sible especially for latent prints. In a Semi-Lights-Out Sys-
tem some human intervention is allowed during feature ex-
traction from a latent, e.g. orienting the fingerprint, mark-
ing the region of interest, etc. It further outputs a list of
candidates that need to be examined by a latent examiner to
accept or reject a fingerprint pair as a match.
Although tremendous progress has been made in im-
proving the speed and accuracy of automated fingerprint
identification systems (AFIS), most of these systems work
well only in scenarios where the matching is performed
between rolled or plain fingerprint images.
of Fingerprint Vendor Technology Evaluation (FpVTE)
[18] showed that the most accurate commercial fingerprint
matchers achieved an impressive rank-one identification
rate of more than 99.4% on a database of 10,000 plain fin-
gerprint images (see results of Medium Scale Test on page
56 in [18]). On the other hand, the accuracy of latent to
rolled print match continues to be quite low. The NIST
latent fingerprint testing workshop reported that the rank-
one accuracy of an automatic latent matcher can be as low
as 54% on a large database of more than 40 million sub-
jects [10]. Currently, NIST is conducting a multi-phase
project on Evaluation of Latent Fingerprint Technologies
(ELFT) [4]; phase-I results [7] showed that the best identi-
fication accuracy obtained is 80% in identifying 100 latent
images among a set of 10,000 rolled prints. This accuracy
is still significantly lower than the accuracy of rolled print
to rolled print matching on a similar size database.
The difficulty in latent matching is mainly due to three
reasons: (i) poor quality of latent prints in terms of the clar-
ity of ridge information, (ii) small area of latent prints as
compared to rolled prints and (iii) large non-linear distor-
tion due to pressure variations. Figure 1 shows a latent from
the NIST SD27 along with its corresponding rolled print.
In Figure 1(c), the ridge information near the center of the
image is obscured by the presence of background noise, ex-
traneous markings and other spurious friction ridges sur-
rounding it. Further, while a typical rolled fingerprint has
more than 60 minutiae, a typical latent fingerprint may have
only 15 usable minutiae [10]. Thus, latent fingerprint iden-
tification is a difficult and important problem which needs
significant attention.
In this paper we present an algorithm for matching a la-
tent print to a rolled print that achieves accuracy as high as
93.4% at rank 20 while matching 258 latent images against
a background of 2,258 rolled prints. We use 258 latent fin-
gerprint images from the NIST SD27 as query fingerprints.
The background database consists of a total of 2,258 rolled
print images from SD27 (258 images) and SD4 (2,000 im-
ages, one per finger). We use minutiae, orientation field and
The results

Page 3

quality map as the features for matching. For latent prints,
all the features are currently manually marked whereas for
rolled prints features are automatically extracted.
2. Feature Extraction
In our system, three types of features are used: minutiae,
orientation field and quality map. A minutia consists of five
attributes, namely x, y, minutiae direction, type and quality,
where x and y represent the position of the minutiae. The
quality of minutia is defined to have two levels: 0 (unreli-
able) and 1 (reliable). Orientation field and quality map are
obtained by dividing the whole image into blocks of size
16 ∗ 16 pixels and assigning a single orientation and qual-
ity value to each block. We define three quality levels for
a block: background (0), reliable (1), unreliable (2). Both
reliable and unreliable blocks belong to foreground. A reli-
able block has good quality with clear ridge structure such
that all the minutiae present in that block (if any) can be
extracted or marked reliably. An unreliable block is char-
acterized by poor quality where the ridge structure is not
clear and hence some minutiae may be missed. However,
orientation field can be estimated in an unreliable block.
2.1. Latent Fingerprint
Minutiae in latent prints in the SD27 database have been
marked by a team of FBI latent examiners. We have man-
ually classified these minutiae as reliable or unreliable.
Minutiae near singular points and pairs of minutiae that are
spatially close to each other but have nearly opposite di-
rections are categorized as unreliable. Since the chance of
an unreliable minutia being missed by an automatic minu-
tiae extraction algorithm is high, they are marked for spe-
cial treatment in our matching algorithm. In addition to
the minutiae provided in the SD27 database, we also mark
the orientation field of latents. It is first estimated using a
gradient-based algorithm and then modified manually. Due
to the poor quality of latents, this process is quite time-
consuming. The quality map of latents is also manually
marked. Blocks where ridge structure is clear are marked
as reliable blocks whereas blocks where orientation can be
reliably estimated but there may be some missing minutiae
are marked as unreliable blocks. In addition, blocks around
singular points are also classified as unreliable blocks. This
isbecause automatic feature extractionalgorithms for rolled
prints tend to detect many spurious minutiae in such re-
gions. Figure 2 shows the different types of features marked
in a latent image.
2.2. Rolled Fingerprint
Rolled fingerprints are automatically processed to obtain
minutiae, orientation map and quality map. Our feature ex-
traction algorithm consists of two modules: preprocessing
(a) (b)
Figure 2. Features in a latent fingerprint. (a) Minutiae (green: re-
liable minutiae, red: unreliable minutiae), (b) orientation field and
quality map (green: reliable blocks, red: unreliable blocks)
and postprocessing. In this work, Neurotechnology Verifin-
ger 4.2 SDK [2] has been used as a preprocessor. Due to the
presence of handwritten characters and strokes on many fin-
gerprints scanned from paper, like the rolled prints in SD4
and SD27, Verifinger produces many false minutiae. There-
fore, a postprocessing algorithm was developed to remove
these unreliable minutiae and ridges. The quality map is
created based on the automatically extracted ridges. We
developed a minutiae validation algorithm to classify each
minutia as spurious, reliable or unreliable. Ridges are also
classified as true ridges or false ridges by a ridge validation
algorithm. The results of the various processing steps are
shown in Figure 3. In the following paragraphs, we will
describe minutia validation, ridge validation, quality map
construction and orientation field estimation.
1. Minutia validation
A minutia is deemed as spurious if it is close to a back-
ground block. A minutia is deemed as unreliable if it
forms an opposite pair with other minutia. An opposite
pair is a pair of minutiae which are close to each other
but have opposite directions. Remaining minutiae are
deemed as reliable.
2. Ridge validation
It consists of the following two steps. In the first step
each ridge is broken into several segments at unreli-
able ridgels (ridgels are defined as adjoining sequences
of six consecutive pixels on a ridge). Reliability of
a ridgel is based on neighboring ridge pixels of the
two endpoints of the ridgel (see Figure 4). A ridgel is
called reliable if: (i) neighboring ridge pixels on both
sides are continuous, or (ii) discontinuity in neighbor-
ing ridge pixels is caused by a reliable minutia (such
as minutia b in Figure 4). In the second step two ridges

Page 4

(a)(b)
(c)(d)
Figure 3. Images and features of a rolled fingerprint at different
stages of feature extraction algorithm. (a) Gray image, (b) Thin-
ning image, (c) Ridges and minutiae (green: reliable minutiae, red:
unreliable minutiae), (d) Orientation field and quality map (green:
reliable blocks, red: unreliable blocks).
are deemed compatible if there are more than 12 pix-
els on each ridge that are neighbors of each other. The
connected components (ridge groups) are then found
using a depth-first search algorithm. A ridge group is
deemed reliable, if the number of ridge pixels in this
group is greater than a predefined threshold (1,000 in
our experiment). All the ridges in a reliable group are
deemed as reliable. The unreliable ridges are removed
from the image after quality map is created.
3. Quality map construction
After ridge extraction, a block containing any ridge
pixel is labeled as reliable and other blocks as back-
ground blocks. After ridge validation, we set blocks
containing unreliable ridges as background. Finally, a
reliable block whose 8 neighbors are not all reliable
blocks is labeled as an unreliable block.
4. Orientation field estimation
For estimating the orientation field, fingerprint image
is divided into blocks of size 16∗16. For each ridge, its
direction is estimated based on ridge points sampled at
equal intervals (6 pixels). Let dir be the direction at
the ithpoint on the ridge in the (m,n)thblock. We
accumulate the contributions of horizontal and vertical
components of the direction separately in DX(m,n)
Figure 4. Reliability of ridgel. Ridgel 1 is unreliable due to an
unreliable minutia a. Both ridgels 2 and 3 are reliable.
and DY (m,n) as follows:
DX(m,n) = DX(m,n) + cos(2 ∗ dir)
DY (m,n) = DY (m,n) + sin(2 ∗ dir)
After all the ridges have been processed, we compute
the orientation field of a block as atan2(DY,DX)/2
(atan2(x,y) returns a value θ ∈ {−π,π} such that
cos(θ) = x/?x2+ y2and sin(θ) = y/?x2+ y2).
3. Matching
(1)
(2)
Given the features in a latent fingerprint and a rolled fin-
gerprint, the matching algorithm consists of (i) Local minu-
tiae matching - Similarity between each minutia of latent
fingerprint and each minutia of rolled fingerprint is com-
puted. (ii) Global minutiae matching - Using each of the
five most similar minutia pairs as an initial minutia pair, a
greedy matching algorithm is used to find a set of matching
minutia pairs. (iii) Matching score computation - A match-
ing score is computed for each set of matching minutia pairs
and the maximum score is used as the matching score be-
tween the latent and rolled prints.
3.1. Local Minutiae Matching
In this step, the similarity between each minutia of latent
fingerprint and each minutia of rolled fingerprint is com-
puted. Since the basic properties of a minutia, like location,
angle and type, are not very distinctive features, additional
information, which is referred to as descriptor [11], is at-
tached to a minutia to make it distinctive. While the match-
ing algorithm in [11] which utilizes minutiae descriptors
obtained good results on FVC2002 databases, it has to be
adapted to handle latent fingerprints. In this paper, we use
two types of descriptors: orientation-based and neighboring
minutiae-based (See Figure 5). The similarity between two
minutiae is defined as the mean value of the similarity of
two types of descriptors.
1. Orientation-based descriptor

Page 5

(a) (b)(c)
Figure 5. Minutia descriptor. (a) Local image, (b) orientation field,
(c) neighboring minutiae.
Figure 6. The configuration of orientation descriptor.
For every minutia, a local coordinate system is defined
with the minutia as the origin and its direction as the
positive x axis. A set of fixed sampling points is de-
fined (See Figure 6) and the local ridge orientation at
these sampling points form the orientation descriptor.
These sampling points are located on 4 circles cen-
tered at the minutia, and distributed equally on each
circle. The radii of circles are 27, 45, 63 and 81 and
the numbers of sampling points on these circles are
10, 16, 22, and 28, respectively. These parameters
have been determined empirically in [17]. The sim-
ilarity of two orientation descriptors is computed as
the mean value of the similarity of all valid sampling
points (a sampling point falling in the background re-
gion is deemed as invalid). The similarity between
the orientations of two sampling points is computed
as sp= exp(−angle/(π/16)), where angle denotes
the angle between two orientations. If the number of
common valid sampling points is less than 25% of the
total number of sampling points, the similarity of two
orientation descriptors is set to 0.
2. Neighboring minutiae-based descriptor
The neighborhood of a minutia is defined to be a cir-
cular region of radius 80 pixels. All minutiae lying
in this neighborhood are called the neighboring minu-
tiae. Let p and q be the two minutiae whose similarity
is to be computed. For each neighboring minutia piof
p, we examine if there is a neighboring minutia of q
whose properties (See Figure 7) are similar to those of
Figure 7. Properties of neighboring minutia pi in the local polar
coordinate system defined by minutia p.
(a)(b)
Figure 8. Comparison of neighboring minutiae based descriptors
for two minutiae (shown in yellow) in (a) and (b). (a) All 4 neigh-
boring minutiae (inside the yellow circle) are matched (shown in
green), (b) only 3 neighboring minutiae are matched but the oth-
ers (shown in blue) are not penalized because they correspond to
unreliable blocks in (a). Unreliable region is shown in red.
pi. If such a minutia exists, piis deemed as a matching
minutia; otherwise piis checked against the following
three criteria: (i) the minutia is unreliable, (ii) it falls
in a background region when mapped to the other fin-
gerprint based on the alignment parameters between
p and q, (iii) it falls in an unreliable block and its di-
rection after being mapped is consistent with the lo-
cal orientation in the other fingerprint. If pibelongs
to any one of the three cases, it will not be penalized;
otherwise, it will be penalized. The above process is
also applied to the neighboring minutiae of q. Then
the similarity of neighboring minutiae-based descrip-
tors is computed as
mp+ 1
mp+ np+ 3×
sm=
mq+ 1
mq+ nq+ 3,
(3)
where mp and mq denote the number of matching
neighboring minutiae of p and q, and npand nqde-
note the number of penalized unmatched neighboring
minutiae of p and q. The example in Figure 8 shows
that the similarity between descriptors of two match-
ing minutiae can be improved by not penalizing the
unmatched minutiae belonging to either of the above
three cases. It should be noted that mpmay be dif-
ferent from mqsince we do not establish a one-to-one
correspondence between minutiae.
3.2. Global Minutiae Matching
Given similarity of all minutia pairs, the one-to-one cor-
respondence between minutiae is established in the global