22 2. <strong>SOFT</strong> <strong>BIOMETRICS</strong>: CHARACTERISTICS, ADVANTAGES AND RELATED WORK2.3.1 Facial s<strong>of</strong>t biometric algorithmsFormer work on s<strong>of</strong>t biometrics has been performed predominantly with the aim <strong>of</strong> preprocessing.In face recognition for person identification, for instance, beard detection and removal servesan improvement <strong>of</strong> recognition results, disregarding the information <strong>of</strong> the presence <strong>of</strong> beard.Color based facial s<strong>of</strong>t biometrics: The color based facial s<strong>of</strong>t biometric traits (eye, skin,and hair color) are the most obvious facial identifiers, mentioned primarily by humans, whenportraying unknown individuals. Challenges for skin classification are on the one hand the lowspread <strong>of</strong> different skin colors in color space, and as a consequence, on the other hand the highillumination dependance <strong>of</strong> classification. Latter is described in various skin locus papers, forexample in [HPM02].Hair color is detected by similar techniques like skin color and <strong>of</strong>ten researched along, buthas more broadly scattered color categories. In [SBYL02] a method for human head detectionbased on hair–color is proposed through the use <strong>of</strong> Gaussian mixture density models describingthe distribution <strong>of</strong> hair color. In [GHJW00] the fuzzy theory is used to detect faces in color images,where two fuzzy models describe the skin color and hair color, respectively.Eye color classification, unlike the other color based facial s<strong>of</strong>t biometrics is a relatively newresearch topic. Few publications <strong>of</strong>fer insight, see [BRM + 06] and section 7.2, probably due tothe fact that 90% <strong>of</strong> humans possess brown eyes. An advantage <strong>of</strong> eye color categorization is theavailability <strong>of</strong> all necessary information in images used for iris pattern analysis, in other words iriscolor is a free side effect. Work on fusion between iris texture and color can be found in [ZESH04],where the authors fuse iris and iris color with fingerprint and provide performance improvementin respect with the unimodal systems. In [PS08] iris color is used to successfully support an irisindexing method.Beard and Moustache detection: Presence <strong>of</strong> beard and moustache do not appear in the literatureas an identification trait, but rather as an obstacle for face recognition, which is why theirremoval is performed as a preprocessing step. As an example, in [KM06] a beard removal algorithmis shown using the concept <strong>of</strong> structural similarity and coordinate transformations.Age: Age plays an important role for long time employable systems based on face or bodyand is a challenging and relatively new field. An interesting study on face changes over time canbe found in [PSA + 07], which spans a biometric, forensic, and anthropologic review, and furtherdiscusses work on synthesizing images <strong>of</strong> aged faces. In [WM07] the authors distinguish childrenfrom adults based on the face/iris size ratio. Viola–Jones face detection technique [VJ01b] isused, followed by an iterative Canny edge detection and a modified circular Hough transformfor iris measuring, with good results. In [NBS + 08] the authors observe facial skin regions <strong>of</strong>Caucasian women and build partial least square regression models to predict the chronologicaland the perceived age. They find out that the eye area and the skin color uniformity are the mainattributes related to perceived age.Gender: Gender perception and recognition has been much researched already in social andcognitive psychology work in the context <strong>of</strong> face recognition. From image processing point <strong>of</strong>view, the topic <strong>of</strong>fers as well many <strong>of</strong> approaches. A basic approach <strong>of</strong> understanding simplemetrology in connection to gender is <strong>of</strong>fered in [CCP + 11]. The latest efforts employ a selection<strong>of</strong> fused biometric traits to deduce gender information. For example in [CSM07] gait energy imagesand facial features are fused and classified by support vector machines. In [YHP11] contrastand local binary patterns are fused. Another approach in [ST06] proposes a combined gender andexpression recognition system by modeling the face using an Active Appearance Model, featureextraction and finally linear, polynomial and radial based function based support vector machinesfor classification. The work in [BR06] proposes using adaboost on several weak classifiers, ap-
23plied on low resolution grey scale images with good results. Matta et al. in [MSMD08] present amultimodal gender recognition system, based on facial appearance, head and mouth motion, employingthe means <strong>of</strong> a unified probabilistic framework. Another approach based on motion andappearance is the work in [HP09]. On a different note the authors <strong>of</strong> [CR11a] employ thermal andnear infra-red images for gender classification.Ethnicity: Ethnicity recognition is an ethically and sociological hot debated trait, once againrelevant for face recognition. In the context <strong>of</strong> ethnicity a uniquely defined classification is adifficult and important task. For recognition <strong>of</strong> Asian and non–Asian faces in [LJ04] machinelearning framework applies a linear discriminant analysis (LDA) and multi scale analysis. Afurther framework, integrating the LDA analysis for input face images at different scales, furtherimproves the classification performance. In the paper [HTK04] an ethnicity recognition approachis based on Gabor Wavelets Transformation, combined with retina sampling for key facial featuresextraction. Finally support vector machines are used for ethnicity classification providing verygood results, even in the presence <strong>of</strong> various lighting conditions.Facial measurements: Facial measurements were early on found as very distinctive and helpfulin the context <strong>of</strong> facial recognition [Nix85]. Later studies continue employing facial measurements,and apply on 3D [CC06].Recent work on facial s<strong>of</strong>t biometrics is performed on scars, marks and tattoos by the authorsin [LJJ08]. Moreover patterns in the sclera have been employed as a s<strong>of</strong>t biometric trait as well,see [CR11b].2.3.2 Accessory s<strong>of</strong>t biometricsThe new s<strong>of</strong>t biometrics definition allows the inclusion <strong>of</strong> accessories among these traits. Accessoriescan indeed be related to personal characteristics (as sight problems in case <strong>of</strong> glases), orpersonal choices (as adornment in case <strong>of</strong> jewelry).Eye Glasses detection: The forerunner for glasses detection are Jiang et al. in [JBAB00],performing classical edge detection on a preprocessed gray level image. Certain face areas areobserved and an indicator for glasses is searched for. The most successful identifier region forglasses is found to be the nose part <strong>of</strong> the glasses, between the eyes. A different approach forglasses extraction is employed in [XY04], where a face model is established based on the Delaunaytriangulation. A 3D method to detect glasses frames is presented in [WYS + 02], where 3D featuresare obtained by a trinocular stereo vision system. The best results on glasses detection up to noware achieved on thermal images [HKAA04].Scarf and glasses detection: The work [MHD11] handles facial recognition in the presence<strong>of</strong> occlusions caused by glasses and scarfs. The occlusion is hereby detected by Gabor wavelets,PCA and support vector machines, followed by facial recognition <strong>of</strong> the non-occluded part basedon block–based local binary patterns.Cap detection: In [MD11] the authors work on an additional occlusion, which impedes facerecognition, namely cap detection.2.3.3 Combined s<strong>of</strong>t biometricsSince s<strong>of</strong>t biometric traits are individually not distinctive and permanent, a combination <strong>of</strong>those could overcome those limits. In this context, many recent papers deal with fusion <strong>of</strong> classicalbiometry and s<strong>of</strong>t biometry or exclusively with fusion <strong>of</strong> s<strong>of</strong>t biometric traits. An examplefor latter is the work in [OPD94]. The authors propose algorithms for gender, body size, height,cadence, and stride using a gait analysis tool. In [DFBS09] height, and appearance are extracted
- 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: 21is the fusion of soft biometrics
- 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 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.