80 6. <strong>SOFT</strong> <strong>BIOMETRICS</strong> FOR QUANTIFYING AND PREDICTING <strong>FACIAL</strong> AESTHETICS– facial landmark recognition with accuracy <strong>of</strong> <strong>of</strong> 6.23 pixels and 2.1%, reported in the work[DM08],– face localization with accuracy between90% and98% depending on the database presentedin [GLW + 11] and– glasses detection with accuracy <strong>of</strong>94% shown in [WAL04].We deteriorate the manually annotated data with the above realistic algorithmic estimationaccuracies and compute the Pearson’s correlation coefficient between user MOS rating and thepredicted ̂MOS based on simulated error prone algorithms. We obtain a realistic simulated beautyprediction performance presented in Table 6.3. Such an automatic tool, based only on three traitsprovides related results that would outperform outcomes from Eigenfaces <strong>of</strong> r̂MOS,MOS) = 0.18(see [GKYG10]) and neural networks = 0.458 (see [GKYG10]).r̂MOS,MOSCombined Traits x iPearson’s correlationcoefficient r i,MOSx 1 0.5112x 1 , x 2 0.5921x 1 , x 2 , x 8 0.6165x 1 , x 2 , x 8 , x 14 , x 20 , x 23 0.6357Degraded x 1 0.4927Degraded x 1 , x 2 0.5722Degraded x 1 , x 2 , x 8 0.5810x 14 , x 20 , x 23 and degraded x 1 , x 2 , x 8 0.60076.8 SummaryIn this chapter, we presented a study on facial aesthetics in photographs, where we comparedobjective measures (namely photograph quality measures, facial beauty characteristics and s<strong>of</strong>tbiometrics), with human subjective perception. Our analysis revealed a substantial correlation betweendifferent selected traits, and the corresponding MOS-related beauty indices. Specificallywe presented that non permanent features can influence highly the MOS, and based on our analysiswe conclude that facial aesthetics in images can indeed be substantially modifiable. Withother words parameters such as the presence <strong>of</strong> makeup and glasses, the image quality as wellas different image post–processing methods can significantly affect the resulting MOS. Furthermorewe constructed a linear MOS–based metric which was successfully employed to quantifybeauty-index variations due to aging and surgery. Our work applies towards building a basis fordesigning new image-processing tools that further automate prediction <strong>of</strong> aesthetics in facial images.Towards this we provided a simulation <strong>of</strong> an automatic prediction tool based on state <strong>of</strong> theart categorization algorithms and the designed MOS–prediction metric.By now we ensured the user <strong>of</strong> the practicality <strong>of</strong> SBS for security as well as entertainmentapplications. In a next step we provide a chapter 7 featuring classification algorithms <strong>of</strong> a SBS, asemployed and analyzed in the chapters 3 and 4.
81Chapter 7Practical implementation <strong>of</strong> s<strong>of</strong>tbiometrics classification algorithms7.1 Set <strong>of</strong> facial s<strong>of</strong>t biometricsAs elaborated in Chapter 2 higher and more satisfactory distinctiveness can be achieved byusing more than one trait, rather than a single trait. Thus we here propose a set <strong>of</strong> facial s<strong>of</strong>tbiometrics that can be exploited for human identification, as shown in Chapter 3. In an effort t<strong>of</strong>ind a good balance between identification–reliability and complexity, we here propose a s<strong>of</strong>t–biometric system that focuses on simple and robust classification from a bounded set <strong>of</strong> traitsand their trait–instances. In what follows, we will describe these basic elements, as well as theemployed classification algorithms.In the presented set <strong>of</strong> facial s<strong>of</strong>t biometric traits, we allocate 6 traits, which we choose andlabel as shown in Table 7.1.Table 7.1: Table <strong>of</strong> Facial s<strong>of</strong>t biometric traitsSB trait Algorithm DatabaseSkin color Deduced from [KMB] FERETHair color Deduced from [ZSH08] FERETEye color Own developed UBIRIS2Beard Own developed FERETMoustache Own developed FERETGlasses Deduced from [JBAB00] FERETWe proceed now to specify basic aspects <strong>of</strong> the classification algorithms that were used fortrait–instance identification.7.1.1 Classification algorithmsThe basic classification tool consisted <strong>of</strong> an automatic frontal face and facial features detector,which was partially drawn and modified from the algorithms in [vio]. Implementation <strong>of</strong> 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: 79shown to have a high impact on ou
- 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 150 and 151:
3hair, skin and clothes. The propos
- 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.