3hair, skin and clothes. The proposed method and the suitability <strong>of</strong> these patch-based traits are thenvalidated both analytically and empirically.Deviating from security related themes, we focus on a completely different application: employings<strong>of</strong>t biometrics in evaluation <strong>of</strong> female facial aesthetics. This approach is novel in that,in the context <strong>of</strong> female facial aesthetics, it combines s<strong>of</strong>t biometrics with previous approaches onphoto quality and beauty assessment. This study helps us to understand the role <strong>of</strong> this specificset <strong>of</strong> features in affecting the way humans perceive facial images. Based on the above objectiveparameters, we further construct a simple linear metric that suggests modifiable parametersfor aesthetics enhancement, as well as tunes systems that would seek to predict the way humansperceive facial aesthetics. Moreover using the designed metric we evaluate beauty indices withrespect to aging, facial surgery and females famous for their beauty. We simulate an automatictool for beauty prediction with both realistic accuracy and performance.Remaining in the realm <strong>of</strong> human perception, we also provide a comparative study <strong>of</strong> differentaccess control systems based on fingerprint, PIN, s<strong>of</strong>t biometrics and face recognition. Towardscomparing these systems, we design real–life access control interfaces, each based on the abovementioned methods, and then proceeded to empirically evaluate the degree <strong>of</strong> usability for each <strong>of</strong>these interfaces. Our study is based on the recorded assessments <strong>of</strong> a set <strong>of</strong> users who rated theirinteraction with each interface, in terms <strong>of</strong> privacy, ease <strong>of</strong> use, user-friendliness, comfort andinteraction time. The results reinforce, from a usability point <strong>of</strong> view, the employment <strong>of</strong> novelbiometric authentication methods as viable alternatives to the currently predominant PIN basedmethods for access control.Overall this dissertation has contributed the following:– identification and introduction <strong>of</strong> novel applications for s<strong>of</strong>t biometrics, such as humanidentification (bag <strong>of</strong> s<strong>of</strong>t biometrics), re–identification as well as aesthetics prediction– development <strong>of</strong> theoretical framework for SBSs in the applications: pruning the search andhuman identification– application <strong>of</strong> the developed theoretical framework on existing SBSs– construction <strong>of</strong> a novel image processing tool for classification <strong>of</strong> s<strong>of</strong>t biometric traits andemploying such a tool in challenging scenarios– obtaining evidence for the high user friendliness <strong>of</strong> s<strong>of</strong>t biometric based control accesssystems.This work was conducted in part within the European Project ACTIBIO [ACT11] and wassupported in part by the European Commission under contract FP7-215372.S<strong>of</strong>t BiometricsTraditional biometrics <strong>of</strong>fer a natural and reliable solution for establishing the identity <strong>of</strong> anindividual, and for this reason, the use <strong>of</strong> human physical and behavioral characteristics has beenincreasingly adopted in security applications. With this approach maintaining various advantagessuch as universality, robustness, permanence and accessibility, it is not surprising that currentintrusion detection and security mechanisms and systems include by default at least one biometrictrait.Building on this progress, the latest addition <strong>of</strong> s<strong>of</strong>t biometrics builds and adds on the mainadvantages <strong>of</strong> classical biometrics.The beginnings <strong>of</strong> s<strong>of</strong>t biometric science were laid by Alphonse Bertillon in the 19th century,
4who firstly introduced the idea <strong>of</strong> a person identification system based on biometric, morphologicaland anthropometric determinations, see [Rho56]. In his effort, Bertillon considered traits likecolors <strong>of</strong> eye, hair, beard and skin; shape and size <strong>of</strong> the head, as well as general discriminators likeheight or weight and also indelible marks such as birth marks, scars or tattoos. These descriptorsmainly comprise what is now referred to as the family <strong>of</strong> s<strong>of</strong>t biometrics, a term first introducedby Jain et al. [JDN04b] to describe the set <strong>of</strong> characteristics that provide (some) information aboutan individual, but that are not generally sufficient for fully describing and identifying a person,mainly due to the lack <strong>of</strong> distinctiveness and permanence <strong>of</strong> such traits. As stated later [JDN04a],such s<strong>of</strong>t biometrics traits can be inexpensive to compute, can be sensed at a distance, do notrequire the cooperation <strong>of</strong> the surveillance subjects, and can be efficiently used to narrow downa search for an individual from a large set <strong>of</strong> people. Along the lines <strong>of</strong> semantic annotation([SGN08] and [RN10]) we here note the human compliance <strong>of</strong> s<strong>of</strong>t biometrics as a main differencebetween s<strong>of</strong>t biometrics and classical biometrics - a difference that renders s<strong>of</strong>t biometrics suitablefor many applications. The terms light biometrics see in [ALMV04], similes see in [KBBN09]and attributes see in [VFT + 09] have been describing traits we associate to s<strong>of</strong>t biometrics. Thefollowing definition clarifies what is considered here as s<strong>of</strong>t-biometric traits.Definition: S<strong>of</strong>t biometric traits are physical, behavioral or adhered human characteristics,classifiable in pre–defined human compliant categories. These categories are, unlike in the classicalbiometric case, established and time–proven by human experience with the aim <strong>of</strong> differentiatingindividuals. In other words s<strong>of</strong>t biometric traits are created in a natural way, used by peopleto characterize other people.Our interest in this thesis is in understanding the role that s<strong>of</strong>t biometrics can play in securityand commercial systems <strong>of</strong> the future. In brief we begin by specifying s<strong>of</strong>t biometric traits thatadhere to the above definition. After an overview <strong>of</strong> related work, we proceed to explore differentapplications that benefit from s<strong>of</strong>t biometric systems (SBSs), focusing on surveillance relatedperson identification, and on pruning <strong>of</strong> large surveillance related searches. We also consider thespecific scenario <strong>of</strong> applying s<strong>of</strong>t biometrics for human frontal-to-side re-identification. We thenchange gear and deviate from security related applications to the more commercially oriented application<strong>of</strong> employing s<strong>of</strong>t biometrics in quantifying and predicting female facial aesthetics. Theabove approaches are then complemented by a more practical automatic s<strong>of</strong>t biometric classificationtool that we present. Finally, motivated by human acceptance issues, we proceed to provide ausability study relating to s<strong>of</strong>t biometrics.Achievements <strong>of</strong> the dissertationWe proceed with an explicit description <strong>of</strong> the scenarios and applications <strong>of</strong> interest in thethesis.S<strong>of</strong>t biometrics: characteristics, advantages and related workWe illustrate in Table 1) a range <strong>of</strong> facial characteristics which accept the definition statedin for s<strong>of</strong>t biometrics. In a first attempt to differentiate between s<strong>of</strong>t biometric traits we firstlyidentify the affiliation to face or accessory categories. We abuse slightly annotation and includehair color in the group <strong>of</strong> facial s<strong>of</strong>t biometrics. The presented traits list is not exhaustive andwill naturally increase with technological progress.We here note that even though classically accessoriesdo not belong to biometrics, the new stated definition clearly incorporates such traits inthe class <strong>of</strong> s<strong>of</strong>t biometrics. The motivation for including accessories to s<strong>of</strong>t biometrics lays in theassociated highly descriptiveness and discrimination <strong>of</strong> attributes such as clothes color, e.g. “the
- Page 1:
FACIAL SOFT BIOMETRICSMETHODS, APPL
- Page 5:
AcknowledgementsThis thesis would n
- Page 8:
6hair, skin and clothes. The propos
- Page 11 and 12:
97 Practical implementation of soft
- Page 13 and 14:
11Notations used in this workE : st
- Page 15 and 16:
13Chapter 1IntroductionTraditional
- Page 17 and 18:
15event of collision, which is of s
- Page 19 and 20:
17ric. In Section 6.6 we employ the
- Page 21 and 22:
19Chapter 2Soft biometrics: charact
- Page 23 and 24:
21is the fusion of soft biometrics
- Page 25 and 26:
23plied on low resolution grey scal
- Page 27 and 28:
25Chapter 3Bag of facial soft biome
- Page 29 and 30:
27In this setting we clearly assign
- Page 31 and 32:
29Table 3.1: SBSs with symmetric tr
- Page 33 and 34:
31corresponding to p(n,ρ). Towards
- Page 35 and 36:
the same category (all subjects in
- Page 37 and 38:
3.5.2 Analysis of interference patt
- Page 39 and 40:
an SBS by increasing ρ, then what
- Page 41 and 42:
39Table 3.4: Example for a heuristi
- Page 43 and 44:
41for a given randomly chosen authe
- Page 45 and 46:
43Chapter 4Search pruning in video
- Page 47 and 48:
45Figure 4.1: System overview.SBS m
- Page 49 and 50:
472.52rate of decay of P(τ)1.510.5
- Page 51 and 52:
49to be the probability that the al
- Page 53 and 54:
51The following lemma describes the
- Page 55 and 56:
534.5.1 Typical behavior: average g
- Page 57 and 58:
55n = 50 subjects, out of which we
- Page 59 and 60:
5710.950.9pruning Gain r(vt)0.850.8
- Page 61 and 62:
59for one person, for trait t, t =
- Page 63 and 64:
61Chapter 5Frontal-to-side person r
- Page 65 and 66:
63Figure 5.1: Frontal / gallery and
- Page 67 and 68:
6510.90.80.7Skin colorHair colorShi
- Page 69 and 70:
6710.90.80.70.6Perr0.50.40.30.20.10
- Page 71 and 72:
69Chapter 6Soft biometrics for quan
- Page 73 and 74:
71raphy considerations include [BSS
- Page 75 and 76:
73Figure 6.3: Example image of the
- Page 77 and 78:
75A direct way to find a relationsh
- Page 79 and 80:
77- Pearson’s correlation coeffic
- Page 81 and 82:
79shown to have a high impact on ou
- Page 83 and 84:
81Chapter 7Practical implementation
- Page 85 and 86:
834) Eye glasses detection: Towards
- Page 87 and 88:
857.2 Eye color as a soft biometric
- Page 89 and 90:
87Table 7.5: GMM eye color results
- Page 91 and 92:
89and office lights, daylight, flas
- Page 93 and 94:
917.5 SummaryThis chapter presented
- Page 95 and 96:
93Chapter 8User acceptance study re
- Page 97 and 98:
95Table 8.1: User experience on acc
- Page 99 and 100: 97scared of their PIN being spying.
- Page 101 and 102: 99Table 8.2: Comparison of existing
- Page 103 and 104: 101ConclusionsThis dissertation exp
- Page 105 and 106: 103Future WorkIt is becoming appare
- Page 107 and 108: 105Appendix AAppendix for Section 3
- Page 109 and 110: 107- We are now left withN −F = 2
- Page 111 and 112: 109Appendix BAppendix to Section 4B
- Page 113 and 114: 111Blue Green Brown BlackBlue 0.75
- Page 115 and 116: 113Appendix CAppendix for Section 6
- Page 117 and 118: 115Appendix DPublicationsThe featur
- Page 119 and 120: 117Bibliography[AAR04] S. Agarwal,
- Page 121 and 122: 119[FCB08] L. Franssen, J. E. Coppe
- Page 123 and 124: 121[Ley96] M. Leyton. The architect
- Page 125 and 126: 123[RN11] D. Reid and M. Nixon. Usi
- Page 127 and 128: 125[ZG09] X. Zhang and Y. Gao. Face
- Page 129: 2Rapporteurs:Prof. Dr. Abdenour HAD
- Page 132 and 133: Biométrie faciale douce 2Les terme
- Page 134 and 135: Biométrie faciale douce 4une perso
- Page 136 and 137: Couleur depeauCouleur descheveuxCou
- Page 138 and 139: Biométrie faciale douce 8Nous nous
- Page 140 and 141: Biométrie faciale douce 103. Proba
- Page 142 and 143: Biométrie faciale douce 12l’entr
- Page 144 and 145: Biométrie faciale douce 14Figure 6
- Page 146 and 147: Biométrie faciale douce 16pages 77
- Page 148 and 149: Reviewers:Prof. Dr. Abdenour HADID,
- Page 152 and 153: person in the red shirt”. Further
- Page 154 and 155: 7- Not requiring the individual’s
- Page 156 and 157: 9Probability of Collision10.90.80.7
- Page 158 and 159: 11the color FERET dataset [Fer11] w
- Page 160 and 161: 13Table 2: Table of Facial soft bio
- Page 162 and 163: 15Chapter 1PublicationsThe featured
- Page 164 and 165: 17Bibliography[ACPR10] D. Adjeroh,
- Page 166 and 167: 19[ZESH04] R. Zewail, A. Elsafi, M.