Module 2: BIOMETRICS
found in the Rockwells’ garden in the morning, and that
Module objectives: by the end of the class, the students —-
1. Can identify common biometrics & behaviometrics and site
their advantages and disadvantages
2. Can demonstrate the general process of identification &
verification using biometric data and their applications
3. Can classify fingerprints according to configuration and
match latent prints from fingerprints on file using Galton’s
minutiae
4. Can express in a clear manner the evidentiary value of
fingerprints in the case of People v. Medina, G.R. No. L-38434,
December 23, 1933 and form an opinion regarding the defense
of Medina.
5. Can determine the approximate age of a person using
dentition
6. Can identify names of teeth as well as the positional
descriptions in dentition and mouth
7. Can recite the salient features of PD 1575 - Dental Records
Law of 1978
8. Can explain the evidentiary value of the testimony of
handwriting experts in the case of Lee v. People, G.R. No.
192274, February 8, 2012 as to the merit of the decision in light
of the general advances in handwriting analysis
9. Can express basic knowledge on the subject of forgery.
——————-
People v. Medina (1933)
Appellant: Marciano Medina
Appellee: People of the Phil. Islands
Topic: Module 2
Doctrine:
It is now well settled that evidence, showing correspondence
of fingerprints, is admissible for proving identity.
FACTS:
- Feb. 1932: A robbery occurred in the house of James C.
Rockwell.
o A silver box was taken from the room of Mrs. Rockwell
and found in the garden next morning.
- Agripino Ruiz, a Constabulary agent and a fingerprint
expert, was the one investigating the said robbery.
o While investigating that said case, he went to visit
Medina, who was already under arrest at the time for
breaking into the house of another.
o Ruiz took Medina’s fingerprints and compared them
with the print he found on the silver box.
o He found that the two prints (specifically, Medina’s right
middle finger print, and the one on the box) coincided
with each other on 10 diff. points.
o He also found that Medina had already been convicted
three times for the crime of theft.
- Medina was arrested and tried under a plea of no guilty. He
admitted to the ff. facts:
o That the Rockwells’ house was robbed
o That a silver box was taken from a room and was later
the said box contained a fingerprint
o That Ruiz is a Constabulary agent and is a competent
fingerprint expert.
o That he had been convicted of theft three times
already.
- Medina, however, denies being the author of the crime and
interposed a defense of alibi.
- RTC: Accused guilty.
- Medina now questions the propriety of his identification as
the robber and his subsequent conviction based on the
evidence used.
ISSUE(S):
1. WON Medina was properly convicted on the basis
of the fingerprint that was identified to be
matched with his (YES)
RATIO:
1. YES. The conviction was proper.
- SC: It is now well settled that evidence, showing
correspondence of fingerprints, is admissible for proving
identity.
- People v. Sallow: Science has declared that fingerprints are
reliable as a means of identification.
o Fingerprints were first used as a manual seal, which
would give personal authenticity to documents.
o They were officially used for the first time to record the
identity of individuals by Sir William Herschel, in Bengal,
in order to guard against forgeries by natives in India.
o They have been constantly used as a basis of
information for the courts since Sir Francis Galton
proved that the papillay ridges which cover the inner
surface of the hands and the soles of the feet form
patterns, the main details of which remain the same
from the sixth month of the embryonic period until
decomposition sets in after death
o The system has been in general use in the criminal
courts in England since 1891.
- Medina: The fingerprint found was blurred and hence
could not have been employed as evidence.
o SC: Argument is untenable. Wentworth and Wilder,
authorities in fingerprints, has declared that “hese
imprints at best will be poor; that one will never find an
accidental imprint that is absolutely perfect; that it is
seldom, indeed, that a very good one is found.”
o “The only important question is whether or not the
evidence identifies the accused beyond a reasonable
doubt as the person whose finger print appears on the
box.”
- These were the 10 points of correspondence between the
two fingerprints:
1. Upward end of a ridge,
2. Core,
3. Both ends of a short ridge,
4. Both ends of a short ridge,
 5. Downward end of a ridge,
6. Upward end of a ridge,
7. Bifurcation,
8. Upward end of a ridge,
9. Upward end of a ridge,
10. Bifurcation.
- SC: Ruiz, the expert, has stated that only eight
characteristics are need to sufficiently identify a person.
And according to Frederick Kuhn of the Bureau of Criminal
Identification, Police Department of the City of New York,
in the "Finger Print Instructor," these characteristics are:
o the peculiarities of the ridges, such as abrupt endings,
o bifurcations,
o the formation of what is termed an island,
o short ridge lines,
o ridge dots,
o some peculiarity as to the information of the delta or
core;
o in fact any peculiarity out of the ordinary may be
considered a characteristic point, and serve as a
positive means of identification.
- SC: In explaining the 10 points of identity between the two
prints, Ruiz testified:
o That he found four endings of ascending ridges in
Exhibit B that corresponded exactly to those of Exhibit
A;
o That as to the number and location with respect to the
core, which he marked 2 in both photographs, he found
that they agreed;
o That he found in Exhibit B two bifurcations or forks that
corresponded exactly to those in Exhibit A as to
number and location;
o That he found in Exhibit B a short ridge, the two ends of
which he marked 3 and 4, that was identical with the
corresponding short ridge in Exhibit A, which he also
marked 3 and 4.
- Medina: There was another impression of a finger on the
box that was not identified.
o SC: While this is true, it was only a small part and
hence, the expert did not make an attempt to study it.
“And in any event, it does not alter the fact that a
fingerprint identical with that of the defendant in ten
homologous points of comparison was found on the
box.”
- “Although there is some differences of opinion among the
authorities as to what constitutes proof of identity, the
older writers regarding twelve points as necessary to prove
certain identity; and more than that for absolute
identification, the more recent writers think that six or eight
homologous points of comparison leave no room for
reasonable doubt. "In the end it is the microscopic identity
of the ridge characteristics (Galton's minutiae) that settles
the question."
HELD: Appeal denied. Conviction affirmed.
Lee v. People (2012)
Petitioner: Norberto Lee
Respondents: People of the Philippines and Allied Bank
Topic: Module 2
Doctrine:
It is hornbook rule that as a rule, forgery cannot be presumed
and must be proved by clear, positive and convincing evidence
and the burden of proof lies on the party alleging forgery.
FACTS:
- May 1999: Lee, being the New Accounts Service
Representative of Managers Check and Gift Check
Processor, at the Cash Department of Allied Bank, forged
and falsified the signatures of the approving officers of
Allied Bank for the release of a manager’s check in the
amount of P200,500.00, in payable to Noli Baldonado, in
favor of Filway Marketing Inc.
- He subsequently misrepresented himself as the payee and
collected the proceeds of the check.
- Lee was later arrested and charged with 8 counts of Estafa
thru Falsification of Commercial Documents.
- Feb. 2007: After the beginning of trial, Lee filed a “Motion
or Document and Handwriting Examination by the NBI”
wherein he claimed:
o The Crime Laboratory failed to examine the questioned
and standard signatures of the accused, in elation to
the questioned and standard documents and signatures
of the other signatories of the subject Allied Bank
checks, application forms and related documents.
o That there is a suspicion on the credibility, neutrality,
and sincerity of the Crime Laboratory examiners, in that
they conducted the examination without the notice to
and participation of the accused.
o Hence, he argues that there is a need for a new,
confirmatory and independent document and
handwriting examination
- RTC: Motion denied
o The proper remedy would have for the defense to
question the NBI witness during the presentation of the
defense’s evidence-in-chief.
o Also, the Court is not bound by the NBI’s findings, and
is behooved to examine on its own the questioned
signature.
- CA: RTC affirmed.
o The motion only intended to dispute the examination
by the Crime Laboratory, which may be properly done
during the defense’s presentation of its evidence-in-
chief.
ISSUE(S):
WON the RTC and CA erred in denying the motion
for a credible examination by the NBI (NO)
RATIO:
The RTC correctly denied the motion and the CA
correctly affirmed the denial of Lee’s motion.
- SC: The RTC was correct in pointing out that Lee could
have just subjected the NBI to appear in court through a
subpoena, when it was his turn to present evidence.
- The Court has held the following in Marquez v.
Sandiganbayan: “It is hornbook rule that as a rule, forgery
cannot be presumed and must be proved by clear, positive
and convincing evidence and the burden of proof lies on
the party alleging forgery.”
o Thus, Marquez bears the burden of submitting evidence
to prove the fact that his signatures were indeed
forged. In order to be able to discharge his burden, he
must be afforded reasonable opportunity to present
evidence to support his allegation. This opportunity is
the actual examination of the signatures he is
questioning by no less than the country’s premier
investigative force – the NBI. If he is denied such
opportunity, his only evidence on this matter is negative
testimonial evidence which is generally considered as
weak. And, he cannot submit any other examination
result because the signatures are on the original
documents which are in the control of either the
prosecution or the graft court.
- SC: The Marquez ruling is inapplicable, however.
o In Marquez, the accused had requested for the
examination of the disbursement vouchers, purchase
requests and authorization requests by the NBI from the
beginning.
o In the case at bench, the trial had already started and,
worse, the accused’s motion for reconsideration was
filed beyond the reglementary period.
HELD: Petition denied. RTC and CA affirmed.
I. BIOMETRICS
A. GENERAL PROCESS of Identification
The problem of resolving the identity of a person can be
categorized into two fundamentally distinct types of problems
with different inherent complexities
1. Verification (authentication) - refers to the problem of
confirming or denying a person’s claimed identity (Am I who I
claim I am?).
2. Recognition - (Who am I?) refers to the problem of
establishing a subject’s identity
A person can be identified in three ways:
1. Person’s possession – e.g. keys to access a building
2. Person’s knowledge of a piece of information - e.g. user ID
and password
3. BIOMETRICS - positive identification is based on identifying
physical characteristics of the person; since the biological
characteristics can not be forgotten (like passwords) and can
not be easily shared or misplaced (like keys), they are generally
considered to be a more reliable approach to solving the
personal identification problem.
System Architecture
The architecture of a fingerprint-based automatic identity
authentication system is shown in Figure 2. It consists of four
components: user interface, system database, enrollment
module, and authentication module.
1. The user interface provides mechanisms for a user to
indicate his/her identity and input his/her fingerprints into the
system.
2. The system database consists of a collection of records, each
of which corresponds to an authorized person that has access
to the system. Each record contains the following fields which
are used for authentication purpose:
i. user name of the person,
ii. minutiae templates of the person’s fingerprint, and
iii. other information (e.g., specific user privileges).
3. The task of enrollment module is to enroll persons and their
fingerprints into the system database. When the fingerprint
images and the user name of a person to be enrolled are fed
to the enrollment module, a minutiae extraction algorithm is
first applied to the fingerprint images and the minutiae
patterns are extracted. A quality checking algorithm is used to
ensure that the records in the system database only consist of
fingerprints of good quality, in which a significant number
(default value is 25) of genuine minutiae may be detected. If a
fingerprint image is of poor quality, it is enhanced to improve
the clarity of ridge/valley structures and mask out all the
regions that cannot be reliably recovered. The enhanced
fingerprint image is fed to the minutiae extractor again.
4. The task of authentication module is to authenticate the
identity of the person who intends to access the system. The
person to be authenticated indicates his/her identity and
places his/her finger on the fingerprint scanner; a digital image
of his/her fingerprint is captured; minutiae pattern is extracted
from the captured fingerprint image and fed to a matching
algorithm which matches it against the person’s minutiae
templates stored in the system database to establish the
identity.
 b. ulnar/radial/double loops

c. plain whorl/central pocket loop

d. accidental whorl

Applications of biometrics
• Physical access
• Attendance & time control
2. Galton’s minutiae
• Products
a. dot & ridge endings/spur
• Professional services
b. short and long ridges
• Social services
c. island/lake
• Forensics
d. bifurcation/double bifurcation/trifurcation
• Immigration
e. opposed bifurcation/ridge crossing
• Personal documents

B. FINGERPRINTS

1. Classification

Arches vs Loops vs Whorl

a. plain/tented arches
C. ODONTOMETRICS
Odontometrics is the measurement and study of tooth size. It
is used in biological anthropology and bioarchaeology to study
human phenotypic variation. The rationale for use is similar to
that of the study of dentition, the structure and arrangement of
teeth. There are a number of features that can be observed in
human teeth through the use of odontometrics. (Wiki)
The teeth are the hardest substances in the human body.
Besides being essential for chewing, the teeth play an
important role in speech. Parts of the teeth include:
• Enamel: The hardest, white outer part of the tooth.
Enamel is mostly made of calcium phosphate, a rock-
hard mineral.
• Dentin: A layer underlying the enamel. Dentin is
made of living cells, which secrete a hard mineral
substance.
• Pulp: The softer, living inner structure of teeth.
Blood vessels and nerves run through the pulp of the
teeth.
• Cementum: A layer of connective tissue that binds
the roots of the teeth firmly to the gums and jawbone.
• Periodontal ligament: Tissue that helps hold the
teeth tightly against the jaw.
A normal adult mouth has 32 teeth, which (except for wisdom
teeth) have erupted by about age 13:
• Incisors (8 total): The middlemost four teeth on the
upper and lower jaws.
• Canines (4 total): The pointed teeth just outside the
incisors.
• Premolars (8 total): Teeth between the canines and
molars.
• Molars (8 total): Flat teeth in the rear of the mouth,
best at grinding food.
• Wisdom teeth or third molars (4 total): These teeth
erupt at around age 18, but are often surgically
removed to prevent displacement of other teeth.
The crown of each tooth projects into the mouth. The root of
each tooth descends below the gum line, into the jaw.
(WebMD)
1. Names of teeth (maxillary/mandibular)
Maxillary means “of or attached to a jaw or jawbone, especially
the upper jaw.” The maxillae are the two maxilla bones
forming the upper jaw and palate of the mouth. The two halves
are fused at the intermaxillary suture to form the upper jaw.
(Wiki)
The mandible lower jaw, or jawbone (from Latin mandibula,
"jawbone") in the human, is the largest, strongest and lowest
bone in the face. It forms the lower jaw and holds the lower
teeth in place. (Wiki)
a. Incisors
Incisors (from Latin incidere, "to cut") are the front teeth
present in most heterodont mammals. They are located in the
premaxilla above and on the mandible below. Humans have a
total of eight (two on each side, top and bottom).
Adult humans normally have eight incisors, two of each type.
The types of incisor are:
• maxillary central incisor (upper jaw, closest to the
center of the lips)
• maxillary lateral incisor (upper jaw, beside the
maxillary central incisor)
• mandibular central incisor (lower jaw, closest to the
center of the lips)
• mandibular lateral incisor (lower jaw, beside the
mandibular central incisor)
Children with a full set of deciduous teeth (primary teeth) also
have eight incisors, named the same way as in permanent
teeth. Young children may have from zero to eight incisors
depending on the stage of their tooth eruption and tooth
development. Typically, the mandibular central incisors erupt
first, followed by the maxillary central incisors, the mandibular
lateral incisors and finally the maxillary laterals. The rest of the
primary dentition erupts after the incisors.
Apart from the first molars, the incisors are also the first
permanent teeth to erupt, following the same order as the
primary teeth, among themselves. (Wiki)

b. Canine
In mammalian oral anatomy, the canine teeth, also called
cuspids, dog teeth, fangs, or (in the case of those of the upper
jaw) eye teeth, are relatively long, pointed teeth. However,
they can appear more flattened, causing them to resemble
incisors and leading them to be called incisiform. They
developed and are used primarily for firmly holding food in
order to tear it apart, and occasionally as weapons. They are
often the largest teeth in a mammal's mouth. Most species that
develop them normally have four per mammal, two in the
upper jaw and two in the lower, separated within each jaw by
its incisors; humans and dogs are examples. In most species,
canines are the anterior-most teeth in the maxillary bone. The
four canines in humans are the two maxillary canines and the
two mandibular canines. (Wiki)
c. Premolars/molars
The premolar teeth, or bicuspids, are transitional teeth located
between the canine and molar teeth. In humans, there are two
premolars per quadrant in the permanent set of teeth, making
eight premolars total in the mouth. They have at least two
cusps. Premolars can be considered as a 'transitional tooth'
during chewing, or mastication. It has properties of both the
anterior canines and posterior molars, and so food can be
transferred from the canines to the premolars and finally to the
molars for grinding, instead of directly from the canines to the
molars. The premolars in humans are the maxillary first
premolar, maxillary second premolar, mandibular first
premolar, and the mandibular second premolar.
The molars or molar teeth are large, flat teeth at the back of
the mouth. They are more developed in mammals. They are
used primarily to grind food during chewing. The name molar
derives from Latin, molaris dens, meaning "millstone tooth",
from "mola", millstone and dens, tooth. Molars show a great
deal of diversity in size and shape across mammal groups.
(Wiki)
 − Determined by the arrangement of the white fibers
radiating from the center of the iris (or pupil)
− Fibers are uniform and reasonably direct or parallel

B. Flower

− The fibers radiating from the center are distorted (in one
or more places) to produce the effect of petals
− May have only one significant petal with the remainder of
the iris looking like a stream
D. IRIS PATTERNS − The fibers form rounded openings in the iris - these vary in
size, density and intensity
A. Stream

C. Jewel
 In iris recognition, the identification process is carried out by
gathering one or more detailed images of the eye with a
sophisticated, high-resolution digital camera at visible or
infrared (IR) wavelengths, and then using a specialized
computer program called a matching engine to compare the
subject's iris pattern with images stored in a database. The
matching engine can compare millions of images per second
with a level of precision comparable to conventional
fingerprinting or digital fingerscanning.

E. FACIAL RECOGNITION

Facial Recognition
• History
− Can be recognized by the presence of pigmentation or
colored dots on top of the fibers
− These dots (or jewels) can vary in color from light orange
to black
− They can also vary in size
− The pigmentation is superimposed above the fibers
D. Shaker
− Identified by the presence of both flower-like petals in
the fiber arrangement and pigmented dots or jewels
− The distribution and density of flowers and jewels can vary
substantially between the two eyes
• Predominant Approaches
IRIS PATTERN RECOGNITION
Iris recognition is a method of identifying people based on
unique patterns within the ring-shaped region surrounding the
pupil of the eye. The iris usually has a brown, blue, gray, or
• Popular Algorithms
greenish color, with complex patterns that are visible upon
close inspection. Because it makes use of a biological
characteristic, iris recognition is considered a form of biometric
verification.
o First developed in the 1960s, the first semi-
automated system for face recognition required
the administrator to (1) locate features [eyes, ears,
nose, and mouth] on the photographs before it
(2) calculated distances and ratios to a common
reference point, which were then (3) compared to
reference data.
o 1970’s: Goldstein, Harmon, and Lesk used 21
specific subjective markers (hair color, lip
thickness) to automate the recognition.
§ Problem up to this point: measurements and
locations were MANUALLY computed.
o 1988: Kirby and Sirovich applied PRINCIPLE
COMPONENT ANALYSIS.
§ This is a standard linear algebra technique.
§ Showed that less than 100 values were
required to accurately code a suitably aligned
and normalized face image.
o 1991: Turk and Pentland – using the eigenfaces
techniques – discovered that the residual error
could be used to detect faces in images.
§ Enabled real-time automated face recognition
systems.
§ 2001: Applied in Super Bowl – surveillance
images were compared to a database of
digital mugshots.
o PRESENT: used to combat passport fraud,
support law enforcement, identify missing
children, and minimize benefit/identity fraud.
o Geometric (feature based) – looks at
distinguishing features
o Photometric (view based) – statistical approach
that distills an image into values and compares
the values with templates to eliminate variances
o Principal Components Analysis (use of
eigenfaces)

§ Probe and gallery images must be the SAME
SIZE and must first be NORMALIZED to line
up the eyes and mouth of the subjects within
the images.
§ PCA approach is then used to reduce the
dimension of the data by means of data
compression basics and reveals the most
effective low dimensional structure of facial
patterns.
• This reduction in dimension REMOVES
INFORMATION THAT IS NOT USEFUL
and precisely decomposes the face
structures into orthogonal components
known as EIGENFACES.
• Each face image may be represented as a
weighted sum of the eigenfaces, which are
stored in a 1D array.
§ Probe image is compared against a
gallery image by measuring the
distance between their respective
feature vectors.
§ Limitation: typically requires the full frontal
face to be presented each time – else, image
results in poor performance.
§ Advantage: can reduce the data needed to
identify the individual to 1/1000th of the date
presented.
o Linear Discriminant Analysis
• Where applied?
§ Statistical approach for classifying
samples of unknown classes based on
training samples with known classes.
• Aims to maximize between-class
(i.e. across users) variance and
minimize within-class (i.e. within
user) variance.
§ See figure 2: where each block represents a
class – there are large variances BETWEEN
classes, but little variance WITHIN classes.
§ Limitation: when dealing with high
dimensional face data, LDA faces the small
sample size problem that arises where there
are a small number of available training
samples compared to the dimensionality of
the sample space.
o Elastic Bunch Graph Matching
§ Relies on the concept that real face images
have many non-linear characteristics that are
NOT addressed by the linear analysis
methods – such as variations in illumination,
pose, and expression.
§ A Gabor wavelet transform creates a
dynamic link architecture that projects
the face onto an elastic grid.
• The Gabor jet is anode on the elastic grid,
notated by circles on the image, which
describes the image behavior around a
given pixel.
o It is a result of a convolution of the
image with a Gabor filter – which is
used to DETECT SHAPES and to
EXTRACT FEATURES using image
processing.
• Recognition is based on the
similarity of the Gabor filter
response at each Gabor note.
§ Limitation: the difficulty with LDA is the
requirement of accurate landmark
localizations – which can sometimes be
achieved by combining PCA and LDA
methods.
o Facebook (Do you wish to tag <friend>)
II. BEHAVIOMETRICS
A. HANDWRITING
1. Graphonomics/handwriting movement analysis
Graphonomics is the interdisciplinary field directed towards
the scientific analysis of the handwriting process, product, and
other graphic skills. Researchers in handwriting recognition,
forensic handwriting examination, kinesiology, psychology,
computer science, artificial intelligence, paleography and
neuroscience cooperate in order to achieve a better
understanding of the human skill of handwriting. Research in
graphonomics generally involves handwriting movement
analysis in one form or another.
Handwriting movement analysis is the study and analysis of the
movements involved in handwriting and drawing. It forms an
important part of graphonomics, which became established
after the "International Workshop on Handwriting Movement
Analysis" in 1982 in Nijmegen, The Netherlands
2. Holographs/autographs
A holograph is a document written entirely in the handwriting
of the person whose signature it bears.
An autograph (from the Greek: αὐτός, autós, "self" and γράφω,
gráphō, "write") is a document transcribed entirely in the
handwriting of its author, as opposed to a typeset document
or one written by an amanuensis or a copyist; the meaning
overlaps with that of the word holograph.
3. Handwriting automations
During the last few years the pattern analysis and machine
intelligence community has developed automation tools for
forensic document examination (FDE), in particular for
determining whether a given handwriting specimen can be
attributed to known writing. As with other expert systems, such
as for medical diagnosis, current automation tools are useful
only as part of a larger manually-intensive procedure. Defining
a computational approach for the overall problem not only
places these tools in context but also helps validate and
improve existing manual procedures. We consider the
standard work flow in FDE of handwritten items and annotate
the steps where automation is available or possible. A well-
known ransom note case is considered as an example, where
there are multiple questioned documents, testing for multiple
writers of the same document, determining whether the writing
is disguised, known writing is formal while questioned writing is
informal, etc. The findings for the particular ransom note case
using the tools are given. Observations are made for
developing a more fully automated approach to FDE.
B. FORGERY
1. Types of forgery1
a. Tracing and printing - A traced forgery is created by
tracing over a genuine signature. A forgery of this type can be
tied to the original, or master, signatures if that original
signature can be located.
b. Simulated - A simulated forgery is produced by the writer
who learns to mimic a genuine signature. It may or may not be
possible to identify the forger, depending on the extent to
which the suspect’s normal handwriting characteristics.
c. Blind - A freehand forgery represents the suspect’s normal
handwriting, with no attempt to mimic the style of the genuine
signature.
2. Basis for determining authenticity (form, line quality,
formatting & content)
When a sufficient amount of writing from two different people
is closely examined, there are always identifiable differences.
Comparisons of writing samples take into consideration a wide
variety of handwriting characteristics including word and letter
spacing, slant or slope, speed, pen position, use of
capitalization, embellishments, legibility, use of punctuation,
and proportion of letters and other attributes.
The fluency or smooth flow of the writing line can also indicate
the authenticity of the writing. The lack of smooth line
quality with tremor, pen stops and hesitations may indicate
forgery.
3. Indicators of forgery2 (slowness of execution, touching up
change of hold (pressure), wavering (tremor), uncertain
interrupted strokes, marked variation of angles)
General indications of non-genuineness may include the
following:
a. Blunt starts and stops - The forger places the pen
point in contact with the paper, and then starts
writing. When he is finished with the name or some
portion thereof, he stops the pen and lifts it from the
surface. This may cause an emphasized blunt start or
ending where the pen was placed in contact with the
surface. At times this contact is held so long that if
the pen contains a fluid ink it will wet the paper and
migrate outward from the contact point.
There may be unnecessary and extraneous marks
caused by pen starts and stops. The writer may
decide after putting his pen in contact with the paper,
that it is in the wrong spot, picks it up and moves it to
a position considered more correct. Normally a
signature’s starts and stops are much more dynamic.
The pen is moving horizontally before it contacts the
paper and is lifted at the end while still in flight. This
leaves a tapered appearance at the beginnings and
1
http://highered.mheducation.com/sites/0072564938/student_view0/chapter3/cha
pter_outline.html
2
http://www.questioneddocuments.com/services-offered-by-ndl/signatures-
forgery/
 endings of names or letters. There are, of course,
exceptions to this.
b. Pen lifts and hesitation - This is occasioned when
the pen stops at an unusual point in the writing;
perhaps where a radical change in direction is about
to take place or a new letter formation is about to be
started. This may take on the appearance of a small
gap in the written line where one is not expected, or
an overlapping of two ink lines where there should be
only one continuous line.
c. Tremor - Because the creation of most forms of non-
genuine signatures are little more than drawings, the
pen is moving so slowly that small, sometimes
microscopic changes in direction take place in what
should be a fluid-looking line. The resultant line is not
smooth, but reflects the “shaking” pen.
d. Speed and pressure - Because the pen is moving
slowly rather than with the dynamic movement
associated with most genuine writings, the ink line
remains constant in thickness, resulting from the same
constant pressure exerted on a slowly moving pen.
There will be little, if any, tapering of internal lines.
e. Patching - Infrequently, but at one time or another,
most of us have made an error while writing our own
signature. Some individuals may leave the signature
alone, caring little about the mistake or imperfection,
while others will simply “fix” the signature by
correcting the offending portion. This may be done
in order to make the signature more readable, or
because a defect in the pen or paper has affected
what we perceive to be our “normal” signature, or for
some other reason that may even be subconscious.
These “fixes” are usually patent, with no attempt
made on the part of the writer to mask or otherwise
hide the correction.
These signature corrections are quite different than
the patching that is frequently found in non-genuine
signatures. On these occasions, the writer is not
attempting to make the signature more readable, but
to make its appearance passable. He is fixing an
obvious defect that he perceives as detectable, and
might uncover his fraudulent product and foil his
scheme. These usually take the form of a correction to
a flaw in the writing line rather than in the form of a
letter. Extensions to entry or terminal strokes, or to
lower descending portions of letters, along with
corrections to embellishments, are typical of non-
genuine patching.
NOTE: There are times when some of these same forgery
indicators will be displayed in genuine signatures. Aged or
infirmed writers will frequently display similar patterns. The
mere presence of these indicators does not mean that the
signature under scrutiny is non-genuine, but should contribute
to the overall determination as to genuineness. Alternately, the
signature devoid of these indications may not be assumed to
be genuine. The signature of an elderly individual may, for
instance, be expected to contain tremor and hesitation. If,
however, the questioned signature appears to be written in a
fluid manner and/or on a higher skill level than what is
expected, the red warning flag should be waving. This
occurrence may itself be indicative of non-genuineness. Often,
a forger, because of an inherent high skill level in his writing,
may produce a product that contains fewer indications of
forgery than a counterpart with a lower skill-level.
4. Points of Comparison (uniformity, irregularities, size &
proportion, connecting letters, continuity, alignment (line
habits), spacing, degree of slant, weight of strokes (pen
pressure) t-bars and i-dots, loops, circle formation, the needle,
the wedge, the round, the flat, the initial and final strokes)
a. Line Quality - Do the letters flow or are they erratic and
shaky?
b. Spacing - Are the letters equally spaced or crowded?
c. Size consistency - Is the ratio of height to width
consistent?
d. Continuous - Is the writing continuous or does the writer
lift the pen
e. Connecting Letters - Are capitals and lowercase letters
connected and continuous?
f. Letters Complete - Are letters completely formed? Or,
is a part of the letter missing?
g. Cursive and printed letters - Are there printed letters,
cursive letters, or both?
h. Pen Pressure - Is pressure equal when applied to
upward and downward strokes?
i. Slant - Left, right, or variable?
j. Line Habits - Is the text on the line, above the line, or
below the line?
k. Fancy curls or loops - Are there fancy curls?
l. Placement of crosses on t’s and dots on i’s -
Correct or misplaced? Are t’s crossed, crossed in the
middle, toward top, or toward the bottom? Are the i’s
dotted, dotted toward the right, left, or centered?
5. Forgery Detection Tools (magnifying glasses, microscopes,
electron microscopy, digital imaging, 3-D imaging softwares,
infrared, ultraviolet, visible filter, infrared luminescence and
ultraviolet fluorescence, side or oblique lighting or electrostatic
detection apparatus (EDSA))
a. Infrared Viewing - can detect chemical erasures and
changes in the writing instrument
b. Visible Filter- detects ink or other absorptions or
reflections
c. Infrared luminescence and ultraviolet
fluorescence viewing - electromagnetic techniques
that detect non-visible reflections and absorptions
d. Electron Microscopy - stereo-binocular microscopes
capable of enlarging images up to 120X, which is useful in
the detection of traced and simulated forgeries and the
detection of slight differences in the color of inks
e. Electrostatic detection apparatus (EDSA) – is a
specialized piece of equipment commonly used in
questioned document examination to reveal indentations
or impressions in paper which may otherwise go
unnoticed. It is a non-destructive technique (will not
damage the evidence in question) thus allowing further
tests to be carried out. It is a sensitive technique capable
of detecting indentations on pages several layers below
the top sheet, and many years after the indentations were
created. Documents that may contain indented
impressions not visible to the naked eye can be visualized
through the use of an Electrostatic Detection Device
(EDD) such as the Electrostatic Detection Apparatus
(ESDA). An EDD uses applied charges and toner to
Larynx
visualize areas of indented writing, making them visible to
Highly specialized structure atop the windpipe responsible for
the eye. The ESDA uses the principle that indented areas
sound production, air passage during breathing and
of the document carry less negative charge than
protecting the airway during swallowing
surrounding areas. This causes the toner used in the EDD
to be attracted to these areas, revealing indentations that
Vocal Folds (also called Vocal Cords)
are present.
“Fold-like” soft tissue that is the main vibratory component of
the voice box; comprised of a cover (epithelium and superficial
6. Research Advances in Forgery Detection (wavelets &
lamina propria), vocal ligament (intermediate and deep
statistics, fractal number, 3D Microprofilometry)
laminae propria), and body (thyroarytenoid muscle)

a. Wavelets & Statistics – first used in detection of forged

Glottis (also called Rima Glottides)
art pieces, this technique describes how line quality,
Opening between the two vocal folds; the glottis opens during
arrangement, and form can be aggregated into a set of
breathing and closes during swallowing and sound production
numbers by first applying a wavelet transform to create
wavelet coefficients, then creating what is called a linear
Three parts of speech
predictor for the wavelet coefficients, and final applying
descriptive statistics
Taking responsibility for your vocal health starts with
b. Fractal Number – this technique presumes that
understanding how the system works. To do that, you must
forgeries are wrinklier (less smooth) than genuine
appreciate the three production steps: respiration, phonation
handwriting because forgeries are usually written more
and articulation.
slowly than authentic handwriting. Given this, it uses
statistics to use such date to detect forgeries.
Simply, respiration is air. You need it to produce the pressure
c. 3D Microprofilometry- creates 3D holograms of the
and vibration necessary for sound. Phonation means making
path of a piece of writing, generating an image on a
sounds. As air passes through your larynx (voice box), tissues
computer that looks like a ditch or furrow. This makes it
vibrate to produce sound waves. Articulation is the shaping of
easy to analyze variations or "bumps" generated by the
raw sound into recognizable speech. Quite cleverly, you move
writer's pressure on the paper at cross over points, for
the tongue, palate and other structures in just the right way at
example the mid-point of the figure eight.
just the time time to form words. For simplicity, we will leave
out the mastermind of this whole system: the brain. As you
C. VOICE
explore speech production, though, you will undoubtedly
appreciate how masterfully many tasks are be coordinated --
1. Anatomical basis of voice production (larynx, vocal chords,
within fractions of seconds.
respiratory system, brain areas for speech production)

Respiration: air fuels the system: Respiration is the body's cyclic

intake and exhalation of air. When you prepare to breathe, the
diaphragm (the large, flat muscle located below the lungs)
drops. This causes the volume within the lungs to expand, and
air swoops in the nose or mouth, down through the larynx, and
into the trachea, bronchi and, finally, lungs.
Is there is a right or wrong way to breathe? For professional
voice users (such as teachers), a beneficial tip is to keep the
abdominal muscles supple and relaxed. This allows the lungs
to inflate fully for ample air to support your speech.
Phonation: larynx sound makers: Most of the time, air swishes
by the vocal folds, which remain open (abducted, or apart). To
make voice, however, the vocal folds are brought together.
When we do speak, it is always on the exhalation of air. As air
whooshes by them, vocal folds ripple, snap and hum, not
unlike flags blowing in the wind. The faster your vocal folds
vibrate, the higher the pitch of your voice. That is not due to
the speed of the respiration, but rather to the voluntary
shaping of your vocal folds.
Long, thin folds ripple quickly (high pitch). Shorter, bulkier
vocal folds, then, produce lower pitches. Air pressure is also
related to voice loudness. To produce a loud voice, your vocal
folds must be closed tightly together. That requires more air
pressure from the lungs.
Speech does not emerge until these waves are shaped into
specific sounds through the magic of articulation. If you could
hear voice at the level of the vocal folds (before the articulators
shape the raw sound into speech), the sound would be a
buzzing noise.
Articulation: we have speech! In all, 19 points between the
vocal folds and the lips allow us to produce speech. Some are:
the lips, teeth, palates, tongue, vocal folds, nasal cavity, uvula
and jaw. Each part plays a special part in creating specific
sounds.
For example, we begin with a forceful puff of air and use the
upper and lower lips to make the sounds [p], [b] and [m]. Upper
teeth and lower lip produce [f] and [v]. The backs of our
tongues and the soft palates work together to produce [k] and
[g]. For some sounds [h], all we do is open everything up and
allow the sound to travel out the mouth.
Broca’s Area
Language comprehension
For a long time, it was assumed that the role of Broca's area
was more devoted to language production than language
comprehension. However, recent evidence demonstrates that
Broca's area also plays a significant role in language
comprehension. Patients with lesions in Broca's area who
exhibit agrammatical speech production also show inability to
use syntactic information to determine the meaning of
sentences. Also, a number of neuroimaging studies have
implicated an involvement of Broca's area, particularly of the
pars opercularis of the left inferior frontal gyrus, during the
processing of complex sentences. Further, it has recently been
found in functional magnetic resonance imaging (fMRI)
experiments involving highly ambiguous sentences result in a
more activated inferior frontal gyrus. Therefore, the activity
level in the inferior frontal gyrus and the level of lexical
ambiguity are directly proportional to each other, because of
the increased retrieval demands associated with highly
ambiguous content.
Speaking without Broca's area
Damage to Broca's area is commonly associated with
telegraphic like speech made up of functional vocabulary. For
example, a person with Broca's aphasia may say something
like, "Drive, store. Mom." meaning to say, "My mom drove me
to the store today". Therefore, the content of the information
is correct, but the grammar and fluidity of the sentence is
missing.
The essential role of the Broca's area in speech production has
been questioned since it can be destroyed while leaving
language nearly intact. In one case of a computer engineer, a
slow-growing glioma tumor was removed. The tumor and the
surgery destroyed the left inferior and middle frontal gyrus, the
head of the caudate nucleus, the anterior limb of the internal
capsule, and the anterior insula. However, there were minimal
language problems three months after removal and the
individual returned to his professional work. These minor
problems include the inability to create syntactically complex
sentences including more than two subjects, multiple causal
conjunctions, orreported speech. These were explained by
researchers as due to working memory problems. They also
attributed his lack of problems to extensive compensatory
mechanisms enabled by neural plasticity in the nearby cerebral
cortex and a shift of some functions to the homologous area in
the right hemisphere.
2. Speech Recognition
Speech recognition (SR) is the inter-disciplinary sub-field of
computational linguistics which incorporates knowledge and
research in the linguistics, computer science, and electrical
engineering fields to develop methodologies and
technologies that enables the recognition and translation of
spoken language into text by computers and computerized
devices such as those categorized as Smart Technologies and
robotics. It is also known as "automatic speech recognition"
(ASR), "computer speech recognition", or just "speech to text"
(STT).
Some SR systems use "training" (also called "enrollment")
where an individual speaker reads text or isolated vocabulary
into the system. The system analyzes the person's specific
voice and uses it to fine-tune the recognition of that person's
speech, resulting in increased accuracy. Systems that do not
use training are called "speaker independent" systems.
Systems that use training are called "speaker dependent".
Speech recognition applications include voice user interfaces
such as voice dialing (e.g. "Call home"), call routing (e.g. "I
would like to make a collect call"), domotic appliance control,
search (e.g. find a podcast where particular words were
spoken), simple data entry (e.g., entering a credit card
number), preparation of structured documents (e.g. a
radiology report), speech-to-text processing (e.g., word
processors or emails), and aircraft (usually termed Direct Voice
Input).
The term voice recognition or speaker identification refers to
identifying the speaker, rather than what they are saying.
Recognizing the speaker can simplify the task of translating
speech in systems that have been trained on a specific
person's voice or it can be used to authenticate or verify the
identity of a speaker as part of a security process.
3. Speaker recognition (speaker identification; speaker
verification; diarization)
Speaker recognition is the identification of a person from
characteristics of voices (voice biometrics). It is also called
voice recognition.There is a difference between speaker
recognition (recognizing who is speaking) and speech
recognition (recognizing what is being said). These two terms
are frequently confused, and "voice recognition" can be used
for both. In addition, there is a difference between the act of
authentication (commonly referred to as speaker verification or
speaker authentication) and identification. Finally, there is a
difference between speaker recognition (recognizing who is
speaking) and speaker diarisation (recognizing when the same
speaker is speaking). Recognizing the speaker can simplify the
task of translating speech in systems that have been trained on
specific person's voices or it can be used to authenticate or
verify the identity of a speaker as part of a security process.
There are two major applications of speaker recognition
technologies and methodologies. If the speaker claims to be of
a certain identity and the voice is used to verify this claim, this
is called verification or authentication. On the other hand,
identification is the task of determining an unknown speaker's
identity. In a sense speaker verification is a 1:1 match where
one speaker's voice is matched to one template (also called a
"voice print" or "voice model") whereas speaker identification
is a 1:N match where the voice is compared against N
templates.
From a security perspective, identification is different from
verification. For example, presenting your passport at border
control is a verification process: the agent compares your face
to the picture in the document. Conversely, a police officer
comparing a sketch of an assailant against a database of
previously documented criminals to find the closest match(es)
is an identification process.
Speaker verification is usually employed as a "gatekeeper" in
order to provide access to a secure system (e.g. telephone
banking). These systems operate with the users' knowledge
and typically require their cooperation. Speaker identification
systems can also be implemented covertly without the user's
knowledge to identify talkers in a discussion, alert automated
systems of speaker changes, check if a user is already enrolled
in a system, etc.
In forensic applications, it is common to first perform a speaker
identification process to create a list of "best matches" and
then perform a series of verification processes to determine a
conclusive match
Speaker diarisation (or diarization) is the process of partitioning
an input audio stream into homogeneous segments according
to the speaker identity. It can enhance the readability of an
automatic speech transcription by structuring the audio stream
into speaker turns and, when used together with speaker
recognition systems, by providing the speaker’s true identity. It
is used to answer the question "who spoke when?" Speaker
diarisation is a combination of speaker segmentation and
speaker clustering. The first aims at finding speaker change
points in an audio stream. The second aims at grouping
together speech segments on the basis of speaker
characteristics.
With the increasing number of broadcasts, meeting recordings
and voice mail collected every year, speaker diarisation has
received much attention by the speech community, as is
manifested by the specific evaluations devoted to it under the
auspices of the National Institute of Standards and Technology
for telephone speech, broadcast news and meetings