FACIAL SOFT BIOMETRICS - Library of Ph.D. Theses | EURASIP
FACIAL SOFT BIOMETRICS - Library of Ph.D. Theses | EURASIP FACIAL SOFT BIOMETRICS - Library of Ph.D. Theses | EURASIP
96 8. USER ACCEPTANCE STUDY RELATING TO SOFT BIOMETRICSFigure 8.2: User rating of the provided access methods in terms of ease of access, user friendliness,speed and clarity: MOS and standard deviation.ceived in terms of both, user friendliness and ease of access. We explain this result with theseamless soft biometrics based verification without cumbersome additional interaction (as in allother cases, placing finger on scanner, face in blue mark or entry of a PIN). The majority of femaleusers expressed though concerns regarding the non-permanence of captured soft biometric traitssuch as hair color. Few users questioned the distinctiveness of a soft biometrics related system.Some users stated that they would prefer an access control system without any contact. The majoritystated to be biased by the prevalent use of PIN based systems, but was still convinced such asystem bears disadvantages as of forgetting a password or having to keep too many. Few test participantshad hygienic concerns related to the fingerprint access system. As of time of acquisition,users were asked to evaluate the time used for operating the access system (different from systemprocessing time). All systems exhibit similar acquisition time ratings. The clarity of the systemswas a measure for the feedback a user gets from each system. Here users appreciated the bluemark of the face recognition based system as it helped control the capturing, whereas in regardsto PIN they valued the feedback to each step (e.g. the "*" symbols for how many digits they hadalready have entered).8.2.2 Access of private computer vs. crowded environment accessIn the next step the access methods were associated in two scenarios, personal computer accessand crowded environment access, and rated. Confronted with the thought of employing thosemethods for personal verification, the majority of users expressed immediate concern about the accuracyof the systems. They were asked to disregard for the study this factor. Figure 8.3 illustratesthe access method preference in terms of personal computer access. There was no strong userpreference; all methods were basically comparably rated. Here one user noted the illuminationdependence of the camera based traits and stated not be willing to adjust to that in this scenario.Figure 8.3: User preference of access methods for personal computer use: MOS and confidenceintervals for a confidence of 0.95.In the second scenario users showed a significant preference to use fingerprint in crowdedenvironments. The PIN based verification is last with the reason that user had experienced or were
97scared of their PIN being spying. Regarding face and soft biometrics, two users reported not to befully comfortable to be captured by a camera in front of colleagues. It is interesting to comparethe two scenarios (see Figure 8.3 with Figure 8.4), where the task was basically the same, given adifferent environment. The ratings though are partly significantly different (see FP and PIN).Figure 8.4: User preference of access methods in crowded environment: MOS and confidenceintervals for a confidence of 0.95.8.2.3 Time to Acquire, Ease of Use and Data SecurityTo evaluate statistical significance of the differences between the access methods, we performedadditionally Wilcoxon tests [Sie56], due to the relatively small sample size. Hence weasked users to rank the four access methods (1 to 4, 1 being the number one) in terms of speed,ease to access and data security. For the following graphs, the smaller the bars are the better theaccess method was ranked.Figure 8.5: User comparison of presented access methods in terms of speed, simplicity and datasecurity: MOS and standard deviation. Small bars represent high rankings.In terms of acquisition time and simplicity soft biometrics were ranked significantly better thanthe other methods. In respect to privacy, users were made aware that their data, in particular faceimage, list of soft features, PIN and fingerprint, would be stored on a database. This data can beon the one hand misused by operators, and on the other hand hacked. Users felt most comfortablewith providing both, PIN or a soft biometrics based list for storage on a database. Users wereambiguous about which they found is the riskiest trait to give away, fingerprint or a face image.8.2.4 Ranking of favorite access methodsThe last question regarded the overall satisfaction of the methods. Users named in this contextdifferent priorities. On the one hand privacy preservation was named by three users as justificationfor their ranking, on the other hand the easiness of use. The results on this ranking are displayed in
- 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: 95Table 8.1: User experience on acc
- 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
96 8. USER ACCEPTANCE STUDY RELATING TO <strong>SOFT</strong> <strong>BIOMETRICS</strong>Figure 8.2: User rating <strong>of</strong> the provided access methods in terms <strong>of</strong> ease <strong>of</strong> access, user friendliness,speed and clarity: MOS and standard deviation.ceived in terms <strong>of</strong> both, user friendliness and ease <strong>of</strong> access. We explain this result with theseamless s<strong>of</strong>t biometrics based verification without cumbersome additional interaction (as in allother cases, placing finger on scanner, face in blue mark or entry <strong>of</strong> a PIN). The majority <strong>of</strong> femaleusers expressed though concerns regarding the non-permanence <strong>of</strong> captured s<strong>of</strong>t biometric traitssuch as hair color. Few users questioned the distinctiveness <strong>of</strong> a s<strong>of</strong>t biometrics related system.Some users stated that they would prefer an access control system without any contact. The majoritystated to be biased by the prevalent use <strong>of</strong> PIN based systems, but was still convinced such asystem bears disadvantages as <strong>of</strong> forgetting a password or having to keep too many. Few test participantshad hygienic concerns related to the fingerprint access system. As <strong>of</strong> time <strong>of</strong> acquisition,users were asked to evaluate the time used for operating the access system (different from systemprocessing time). All systems exhibit similar acquisition time ratings. The clarity <strong>of</strong> the systemswas a measure for the feedback a user gets from each system. Here users appreciated the bluemark <strong>of</strong> the face recognition based system as it helped control the capturing, whereas in regardsto PIN they valued the feedback to each step (e.g. the "*" symbols for how many digits they hadalready have entered).8.2.2 Access <strong>of</strong> private computer vs. crowded environment accessIn the next step the access methods were associated in two scenarios, personal computer accessand crowded environment access, and rated. Confronted with the thought <strong>of</strong> employing thosemethods for personal verification, the majority <strong>of</strong> users expressed immediate concern about the accuracy<strong>of</strong> the systems. They were asked to disregard for the study this factor. Figure 8.3 illustratesthe access method preference in terms <strong>of</strong> personal computer access. There was no strong userpreference; all methods were basically comparably rated. Here one user noted the illuminationdependence <strong>of</strong> the camera based traits and stated not be willing to adjust to that in this scenario.Figure 8.3: User preference <strong>of</strong> access methods for personal computer use: MOS and confidenceintervals for a confidence <strong>of</strong> 0.95.In the second scenario users showed a significant preference to use fingerprint in crowdedenvironments. The PIN based verification is last with the reason that user had experienced or were