(2007) Performance Analysis for Multi Sensor Fingerprint Recognition System
Upcoming SlideShare
Loading in...5
×
 

(2007) Performance Analysis for Multi Sensor Fingerprint Recognition System

on

  • 587 views

The increasing use of distributed authentication architecture has made interoperability of systems an important issue. Interoperability of systems re°ects the maturity of the technology and also ...

The increasing use of distributed authentication architecture has made interoperability of systems an important issue. Interoperability of systems re°ects the maturity of the technology and also improves
confidence of users in the technology. Biometric systems are not immune to the concerns of interoperability. Interoperability of fingerprint sensors and its effect on the overall performance of the recognition sys-
tem is an area of interest with a considerable amount of work directed towards it. This research analyzed effects of interoperability on error rates for fingerprint datasets captured from two optical sensors and a
capacitive sensor when using a single commercially available fingerprint
matching algorithm. The main aim of this research was to emulate a centralized storage and matching architecture with multiple acquisition stations. Fingerprints were collected from 44 individuals on all three sensors and interoperable False Reject Rates of less than .31% were achieved
using two different enrolment strategies.

Statistics

Views

Total Views
587
Views on SlideShare
584
Embed Views
3

Actions

Likes
0
Downloads
23
Comments
0

2 Embeds 3

http://www.slideshare.net 2
http://translate.googleusercontent.com 1

Accessibility

Categories

Upload Details

Uploaded via as Adobe PDF

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Processing…
Post Comment
Edit your comment

(2007) Performance Analysis for Multi Sensor Fingerprint Recognition System (2007) Performance Analysis for Multi Sensor Fingerprint Recognition System Presentation Transcript

  • Collaborative Project with Purdue University Since August 2006 Analysis on Finger Preference of Users for Fingerprint Recognition Systems Fi i tR iti S t Jihyun Moon and Hale Kim, Inha Univ. Matt Young and Steve Elliott, Purdue Univ. February 1, 2007 2007 BERC Workshop
  • Class note for the 1st term of 2005 Contents reference Introduction Test Protocol bituation and Pr Data Collection Analysis Results y n Conclusion and Future Work Analysis on Hab A s 2
  • Class note for the 1st term of 2005 Introduction reference Background User habituation is a concept and term that is widely used within the biometric industry, especially that of d ithi th bi ti i d t i ll th t f bituation and Pr the biometric standards community, without a detailed definition or means necessary to measure y n and determine habituation. Purpose Analysis on Hab To assess the concept of “habituation” for biometric systems, study. systems fingerprints in particular for this study s Furthermore, to investigate the affects of handedness and finger preference in discussing “habituation”. g p g A 3
  • Class note for the 1st term of 2005 Test Protocol reference Expected Measurements Demographic information PURDUE & INHA Handedness PURDUE & INHA bituation and Pr Finger preference PURDUE & INHA Image quality (NFIQ) INHA n Condition: Use-ness of Hand cream Region of Overlap g p INHA Analysis on Hab Matching Performance (BOZORTH3) INHA Statistical analysis s ROC curves in time series for each group ROC curves for inter-group analysis (except for G4) Distributions in time series A IQ, OL 4
  • Class note for the 1st term of 2005 Test Protocol(INHA) reference Sensor U.Are.U4000 by DigitalPersona bituation and Pr Subject At least 15 persons per each group n Procedure (enrolled, attempt) Group# Week1 Week2 Week3 Week4 Week5 Week6 1 7 images i 3 images i 3 images i 3 images 3 images i i 3 images i Analysis on Hab 3 images 2 7 images 3 images 3 images s 3 7 images 3 images 3 images A 4 7 images 3 images /3 images 5
  • Class note for the 1st term of 2005 Test Protocol reference Fingerprint Image Filename convention SSS-F-I-W#.bmp Where SSS is the subject #, F is the finger # (1-3), I is the bituation and Pr image # (1-10 or 1-3), and W# is the week # (1-6). Purdue will use the subject #s from 1-99. Inha will use the n subject #s from 100 – 199 (or greater as needed). Restrictions Analysis on Hab Role of the supervisor The supervisor shall inform the users of the instructions con s tained in the first point in the delimitations section. Howev er; the supervisor shall not engage in any physical assistanc e of any sort while the user is submitting finger images. A 6
  • Class note for the 1st term of 2005 Data Collection(INHA) reference Subjects Group1 Group2 SubjectID SubjectID 100 120 126 143 bituation and Pr 101 121 131 144 102 122 132 145 105 123 133 146 108 124 136 147 111 125 137 148 n 112 127 138 149 113 128 139 150 114 129 140 151 118 141 152 Total Subjects 19 Total Subjects 20 Analysis on Hab Group3 Group4 SubjectID SubjectID 153 164 174 183 193 203 154 165 175 184 194 204 s 155 166 176 185 195 205 156 167 177 186 196 206 157 168 178 187 197 159 169 179 188 198 160 170 180 189 199 161 171 181 190 200 A 162 172 182 191 201 163 173 192 202 Total Subjects 29 Total Subjects 24 7
  • Class note for the 1st term of 2005 Data Collection(BSPA) reference Subjects Group1 Group2 SubjectID SubjectID bituation and Pr 18 30 2 13 19 31 3 15 21 69 4 17 22 6 24 9 n 25 11 26 12 Total Subjects 10 Total Subjects 10 Analysis on Hab Group3 Group4 SubjectID SubjectID 28 42 50 59 35 44 52 60 s 36 46 53 65 37 47 55 38 48 56 39 71 57 40 58 A Total S Subjects 13 Total S Subjects 10 8
  • Class note for the 1st term of 2005 Data Collection(INHA) reference Procedure Before adjustment bituation and Pr Group# Week1 Week2 Week3 Week4 Week5 Week6 1 10 images 3 images 3 images 3 images 3 images 3 images 2 10 images 3 images n 3 10 images 3 images 4 10 images /3 images Analysis on Hab After adjustment Group# p Week1 Week2 Week3 Week4 Week5 Week6 Week7 s 1 10 images 3 images 3 images 3 images 3 images 3 images 2 10 images 3 images 3 10 images 3 images A 4 10 images /3 images 9
  • Class note for the 1st term of 2005 Data Collection(BSPA) reference Procedure Before adjustment bituation and Pr Group# Week1 Week2 Week3 Week4 Week5 Week6 1 10 images 3 images 3 images 3 images 3 images 3 images 2 10 images 3 images n 3 10 images 3 images 4 10 images /3 images Analysis on Hab After adjustment Group# p Week1 Week2 Week3 Week4 Week5 Week6 Week7 s 1 10 images 3 images 3 images 3 images 3 images 2 10 images 3 images 3 10 images 3 images A 4 10 images /3 images 10
  • Class note for the 1st term of 2005 Data Collection(INHA) reference Fingerprint Image Filename convention Before adjustment: SSS-F-I-W#.bmp bituation and Pr After adjustment: SSS-F-II-#.bmp File Size (Adjustment) n Fix size to Width 320 and Height 352 Number of Images Analysis on Hab Group Images per subject Subjects Total 1 75 19 1425 2 39 20 780 3 39 29 1131 s 4 39 24 936 A 11
  • Class note for the 1st term of 2005 Data Collection(BSPA) reference Fingerprint Image Filename convention Before adjustment: SSS-F-I-W#.bmp bituation and Pr After adjustment: SSS-F-II-#.bmp File Size (Adjustment) n Fix size to Width 320 and Height 352 Number of Images Analysis on Hab Group Im ages per subject Subjects Total 1 66 10 660 2 39 10 390 3 39 13 507 s 4 39 10 390 A 12
  • Class note for the 1st term of 2005 Data Collection reference Environment1 – CVLab bituation and Pr Analysis on Hab A s n 13
  • Class note for the 1st term of 2005 Data Collection reference Environment2 – Computer Room 424 bituation and Pr Analysis on Hab A s n 14
  • Class note for the 1st term of 2005 Data Collection reference Forms for collecting information bituation and Pr Analysis on Hab A s n 15
  • Class note for the 1st term of 2005 Analysis Results(INHA) reference Summary on Personal Data (persons) (persons) Total # of subjects Gender Male Female Group1 G 1 19 Group1 G 1 18 1 bituation and Pr Group2 20 Group2 16 4 Group3 29 Group3 28 1 Group4 24 Group4 24 0 93.5% (persons) n Ethnicity Indian etc. Asian Black Hispanic etc. White Other Group1 0 19 0 0 0 0 Group2 0 20 0 0 0 0 Group3 0 29 0 0 0 0 Group4 0 24 0 0 0 0 100.0% 100 0% Analysis on Hab (persons) <고찰> Handedness Right Left Ambidextrous 1. 성별 구성에 있어서 남성의 비율이 월등히 큼 Group1 16 2 1 Group2 16 1 3 2. 모두 동양인임 대부분 오른손잡이임 Group3 26 2 1 3 남성이 대부분이기 때문에 피부 보습을 위한 3. s Group4 23 0 1 조처를 하지 않는 경우가 상대적으로 많음 88.0% (persons) (persons) 4. 지문 인식 시스템을 사용해본 경험이 없는 Hand cream Yes No Used before Yes No 사람들로 참여자를 구성하고자 하였으나, 면접 Group1 6 13 Group1 3 16 후 일부에서 사용 경험이 있었던 것으로 나타남 A Group2 8 12 Group2 3 17 Group3 9 20 Group3 4 25 Group4 6 18 Group4 3 21 68.5% 85.9% 16
  • Class note for the 1st term of 2005 Analysis Results(BSPA) reference Summary on Personal Data (persons) (persons) Total # of subjects Gender Male Female Group1 10 Group1 8 2 bituation and Pr Group2 10 Group2 8 2 Group3 13 Group3 12 1 Group4 10 Group4 9 1 86.0% (persons) n Ethnicity Indian etc. Asian Black Hispanic etc. White Other Group1 0 1 0 0 9 0 Group2 0 0 0 0 10 0 Group3 0 0 0 0 13 0 Group4 1 0 0 0 9 0 95.3% 95 3% Analysis on Hab (persons) <고찰> Handedness Right Left Ambidextrous 1. 성별 구성에 있어서 남성의 비율이 월등히 큼 Group1 9 0 1 Group2 8 1 1 2. 모두 동양인임 대부분 오른손잡이임 Group3 13 0 0 3 남성이 대부분이기 때문에 피부 보습을 위한 3. s Group4 10 0 0 조처를 하지 않는 경우가 상대적으로 많음 93.0% (persons) (persons) 4. 지문 인식 시스템을 사용해본 경험이 없는 Hand cream Yes No Used before Yes No 사람들로 참여자를 구성하고자 하였으나, 면접 Group1 3 7 Group1 6 4 후 일부에서 사용 경험이 있었던 것으로 나타남 A Group2 2 8 Group2 7 3 Group3 2 11 Group3 4 9 Group4 4 6 Group4 5 5 74.4% 51.2% 17
  • Class note for the 1st term of 2005 Analysis Results(INHA) reference Summary on Personal Data Total # of subjects bituation and Pr Group1 Group2 Group3 Group4 n Gro up1 Gro up4 21% 26% Analysis on Hab Gro up2 22% Gro up3 31% A s 18
  • Class note for the 1st term of 2005 Analysis Results(BSPA) reference Summary on Personal Data Total # of subjects bituation and Pr Group1 Group2 Group3 Group4 n Gro up4 Gro up1 23% 23% Analysis on Hab Gro up2 Gro up3 23% 31% A s 19
  • Class note for the 1st term of 2005 Analysis Results(INHA) reference Summary on Personal Data Gender distributions of 4 groups bituation and Pr Male Female 35 ns 30 n Num be r of person 25 20 15 Analysis on Hab 10 5 0 Group1 G 1 Group2 G 2 Group3 G 3 Group4 G 4 s Group# A 20
  • Class note for the 1st term of 2005 Analysis Results(BSPA) reference Summary on Personal Data Gender distributions of 4 groups bituation and Pr Male Female 15 n Num b er o f p erso ns s 10 Analysis on Hab e 5 0 s Group1 Group2 Group3 Group4 Gro up# A 21
  • Class note for the 1st term of 2005 Analysis Results(INHA) reference Summary on Personal Data Handedness distributions of 4 groups bituation and Pr Right Left Ambidextrous 30 ns n 25 Num be r of person 20 15 Analysis on Hab 10 5 0 s Group1 G 1 Group2 G 2 Group3 G 3 Group4 G 4 Group# A 22
  • Class note for the 1st term of 2005 Analysis Results(BSPA) reference Summary on Personal Data Handedness distributions of 4 groups bituation and Pr Right Left Ambidextrous 15 n Num b er o f p erso ns s 10 Analysis on Hab e 5 0 s Group1 Group2 Group3 Group4 Gro u p# A 23
  • Class note for the 1st term of 2005 Analysis Results(INHA) reference Summary on Personal Data Hand- Hand cream useness distributions of 4 groups bituation and Pr Yes No 30 ns n 25 Num be r of person 20 15 Analysis on Hab 10 5 0 s Group1 G 1 Group2 G 2 Group3 G 3 Group4 G 4 Group# A 24
  • Class note for the 1st term of 2005 Analysis Results(BSPA) reference Summary on Personal Data Hand- Hand cream useness distributions of 4 groups bituation and Pr Yes No 15 n Num b er o f p erso ns s 10 Analysis on Hab e 5 0 s Group1 Group2 Group3 Group4 Gro up# A 25
  • Class note for the 1st term of 2005 Analysis Results(INHA) reference Summary on Personal Data Sensor useness distributions of 4 groups bituation and Pr Yes No 30 ns n 25 Num be r of person 20 15 Analysis on Hab 10 5 0 s Group1 Group2 Group3 Group4 Group# A 26
  • Class note for the 1st term of 2005 Analysis Results(BSPA) reference Summary on Personal Data Sensor useness distributions of 4 groups bituation and Pr Yes No 15 n Num b e r o f p erso ns s 10 Analysis on Hab 5 0 s Group1 Group2 Group3 Group4 Gro up# A 27
  • Class note for the 1st term of 2005 Analysis Results reference Summary on Environmental Data (average) (°C) Temperature Week1 Week2 Week3 Week4 Week5 Week6 Group1 G 1 26. 26 9 27. 27 6 27. 27 2 27. 27 5 29. 29 7 26. 26 7 bituation and Pr Group2 27. 3 26. 8 Group3 28. 9 27. 6 Group4 25. 4 (%) n Moisture Week1 Week2 Week3 Week4 Week5 Week6 Group1 41. 5 39 35. 5 40. 5 38. 5 49 Group2 43 51. 9 Group3 42 29. 6 G oup Group4 5 54. 2 Analysis on Hab A s 28
  • Class note for the 1st term of 2005 Analysis Results(INHA) reference Finger Preference Result Finger Preference - 1st Finger bituation and Pr Group1 Group2 Group3 Group4 18 16 n 14 equenc y 12 10 8 Fre Analysis on Hab 6 4 2 0 LL LR LM LI LT RT RI RM RR RL s Finger Index A 29
  • Class note for the 1st term of 2005 Analysis Results(BSPA) reference Finger Preference Result Finger Preference - 1st Finger bituation and Pr Group1 Group2 Group3 Group4 12 n 10 Fre uenc y 8 6 eq Analysis on Hab 4 2 0 LL LR LM LI LT RT RI RM RR RL s Finger Index A 30
  • Class note for the 1st term of 2005 Analysis Results(INHA) reference Finger Preference Result – cont. Finger Preference - 2nd Finger bituation and Pr Group1 Group2 Group3 Group4 14 12 n 10 equenc y 8 6 Analysis on Hab Fre 4 2 0 s LL LR LM LI LT RT RI RM RR RL Finger Index A 31
  • Class note for the 1st term of 2005 Analysis Results(BSPA) reference Finger Preference Result – cont. Finger Preperence - 2nd Finger bituation and Pr Group1 Group2 Group3 Group4 6 n Fre uenc y 4 eq Analysis on Hab 2 0 LL LR LM LI LT RT RI RM RR RL s Finger Index A 32
  • Class note for the 1st term of 2005 Analysis Results(INHA) reference Finger Preference Result – cont. <고찰> Finger Preference - 3rd Finger bituation and Pr 1. 지문 영상 수집 실험 전 선택한 선호 손가락은, 사용자들의 무의식에 의한 선택에 기반한 경우가 Group1 Group2 Group3 Group4 많았다고 생각됨 12 2. 오른손잡이가 많았던 관계로 무의식적으로 오른손 세 손가락을 선택하는 경우가 많았음 n 10 3. 특히, 첫 번째 선호 손가락은 엄지와 검지인 equenc y 경우가 대부분이었으며, 순번이 뒤로 갈 수록 8 선택에 있어서 별 다른 기준이 없는 것처럼 보임 6 Analysis on Hab Fre 4 2 0 s LL LR LM LI LT RT RI RM RR RL Finger Index A 33
  • Class note for the 1st term of 2005 Analysis Results(BSPA) reference Finger Preference Result – cont. Finger Preference - 3rd Finger bituation and Pr Group1 Group2 Group3 Group4 6 n Fre q uenc y 4 Analysis on Hab 2 0 s LL LR LM LI LT RT RI RM RR RL Finger Index A 34
  • Class note for the 1st term of 2005 Analysis Results(INHA) reference (persons) Finger Preference Change Prefernece change Yes No Group1 9 10 Group2 6 14 After Finger Preference Change g g Group3 p 17 12 bituation and Pr Group4 8 16 Finger1 Finger2 Finger3 25 n 20 Frequency 15 10 Analysis on Hab 5 0 s LL LR LM LI LT RT RI RM RR RL Finger Index <고찰> 1. 센서 사용 후의 선호도 변화를 살펴 본 결과 검지(LI, RI)로의 선호도 변화가 뚜렷해 짐. A 2. 양손 엄지(LT, RT) 및 검지(LI, RI)로의 선호도 변화가 전체의 약 80.8%를 차지함. 35
  • Class note for the 1st term of 2005 Analysis Results(BSPA) reference (persons) Finger Preference Change Preference change Yes No Group1 3 7 Group2 4 6 After Finger Preference Change g g Group3 5 8 bituation and Pr Group4 8 2 Finger1 Finger2 Finger3 8 7 n 6 Frequency 5 4 3 F Analysis on Hab 2 1 0 LL LR LM LI LT RT RI RM RR RL s Finger Index A 36
  • Class note for the 1st term of 2005 Analysis Results(INHA) reference Finger Preference Change – occurrence table Finger1 After preference changed Finger2 After preference changed Before B f LL LR LM LI LT RT RI RM RR RL Before B f LL LR LM LI LT RT RI RM RR RL bituation and Pr LL 0 0 1 0 1 2 1 0 0 0 LL 0 0 0 0 0 0 0 0 0 0 LR 0 0 0 0 0 0 0 0 0 0 LR 0 0 0 1 0 0 1 0 0 0 LM 0 0 0 0 0 0 0 0 0 0 LM 0 0 0 0 0 0 0 0 0 0 LI 0 0 0 3 1 0 0 0 0 0 LI 0 0 0 1 0 1 1 0 0 0 LT 0 0 0 3 0 0 1 0 0 0 LT 1 0 0 2 1 1 2 0 0 0 n RT 0 0 0 1 0 0 15 1 0 0 RT 0 0 0 2 0 1 1 0 0 0 RI 0 0 0 0 0 3 7 0 0 0 RI 0 0 1 5 1 2 2 4 0 1 RM 0 0 0 0 0 0 0 0 0 0 RM 0 0 0 3 2 1 1 0 0 0 RR 0 0 0 0 0 0 0 0 0 0 RR 0 0 0 0 0 0 0 0 0 0 RL 0 0 0 0 0 0 0 0 0 0 RL 0 0 0 1 0 0 0 0 0 0 Analysis on Hab Finger3 After preference changed All After preference changed Before LL LR LM LI LT RT RI RM RR RL Before LL LR LM LI LT RT RI RM RR RL LL 0 0 0 0 1 0 0 0 0 0 LL 0 0 1 0 2 2 1 0 0 0 LR 0 0 0 0 0 0 0 0 0 0 LR 0 0 0 1 0 0 1 0 0 0 LM 0 0 0 0 2 2 0 1 0 0 LM 0 0 0 0 2 2 0 1 0 0 LI 0 0 0 1 0 2 2 1 0 0 LI 0 0 0 5 1 3 3 1 0 0 s LT 0 0 0 1 1 0 0 1 0 0 LT 1 0 0 6 2 1 3 1 0 0 RT 0 0 1 0 1 0 1 1 0 0 RT 0 0 1 3 1 1 17 2 0 0 RI 0 0 0 1 1 2 0 1 0 0 RI 0 0 1 6 2 7 9 5 0 1 RM 0 0 1 2 0 3 0 3 2 0 RM 0 0 1 5 2 4 1 3 2 0 RR 0 0 0 0 1 2 0 1 0 0 RR 0 0 0 0 1 2 0 1 0 0 A RL 0 0 0 0 0 0 0 1 0 0 RL 0 0 0 1 0 0 0 1 0 0 80.8% 37
  • Class note for the 1st term of 2005 Analysis Results(BSPA) reference Finger Preference Change – occurrence table Finger1 After preference changed Finger2 After preference changed bituation and Pr Before LL LR LM LI LT RT RI RM RR RL Before LL LR LM LI LT RT RI RM RR RL LL 0 0 0 0 0 0 0 0 0 0 LL 0 0 0 0 0 0 0 0 0 0 LR 0 0 0 0 0 0 0 0 0 0 LR 0 0 0 0 0 0 0 0 0 0 LM 0 0 0 0 0 0 0 0 0 0 LM 0 0 0 0 0 0 0 0 0 0 LI 0 0 0 0 0 0 0 0 0 0 LI 0 0 0 1 0 0 0 0 0 0 LT 0 0 0 0 1 0 0 0 0 0 LT 0 0 0 0 2 0 0 0 0 0 RT 0 0 0 0 0 2 7 0 0 0 RT 0 0 0 0 2 7 0 4 0 0 n RI 0 0 0 0 0 0 31 0 0 0 RI 0 0 0 0 0 1 2 5 1 0 RM 0 0 0 0 0 0 0 2 0 0 RM 0 0 0 1 0 2 0 14 0 0 RR 0 0 0 0 0 0 0 0 0 0 RR 0 0 0 0 0 0 0 0 1 0 RL 0 0 0 0 0 0 0 0 0 0 RL 0 0 0 0 0 0 0 0 0 0 Finger3 After preference changed All After preference changed Analysis on Hab Before LL LR LM LI LT RT RI RM RR RL Before LL LR LM LI LT RT RI RM RR RL LL 0 0 0 0 0 0 0 0 0 0 LL 0 0 0 0 0 0 0 0 0 0 LR 0 0 0 0 0 0 0 0 0 0 LR 0 0 0 0 0 0 0 0 0 0 LM 0 0 1 0 0 0 0 1 0 0 LM 0 0 1 0 0 0 0 1 0 0 LI 0 0 0 5 0 1 0 0 0 0 LI 0 0 0 6 0 1 0 0 0 0 LT 0 0 1 0 5 1 0 0 0 0 LT 0 0 1 0 8 1 0 0 0 0 s RT 0 0 1 0 0 3 0 1 2 0 RT 0 0 1 0 2 12 7 5 2 0 RI 0 0 0 0 0 0 0 0 0 0 RI 0 0 0 0 0 1 33 5 1 0 RM 0 0 0 3 1 1 0 7 2 0 RM 0 0 0 4 1 3 0 23 2 0 RR 0 0 0 1 0 1 0 0 5 0 RR 0 0 0 1 0 1 0 0 6 0 RL 0 0 0 0 0 0 0 0 0 0 RL 0 0 0 0 0 0 0 0 0 0 A 38
  • Class note for the 1st term of 2005 Analysis Results(INHA) reference Finger Preference Change All After preference changed Before LL LR LM LI LT RT RI RM RR RL Total LL 0 0 1 0 2 2 1 0 0 0 6 bituation and Pr LR 0 0 0 1 0 0 1 0 0 0 2 LM 0 0 0 0 2 2 0 1 0 0 5 LI 0 0 0 5 1 3 3 1 0 0 13 LT 1 0 0 6 2 1 3 1 0 0 14 RT 0 0 1 3 1 1 17 2 0 0 25 RI 0 0 1 6 2 7 9 5 0 1 31 n RM 0 0 1 5 2 4 1 3 2 0 18 RR 0 0 0 0 1 2 0 1 0 0 4 RL 0 0 0 1 0 0 0 1 0 0 2 Total 1 0 4 27 13 22 35 15 2 1 120 Analysis on Hab Distributions of before/ after preference change Before After 40 35 s 30 Frequenc y 25 20 15 10 A 5 0 LL LR LM LI LT RT RI RM RR RL Finger Index 39
  • Class note for the 1st term of 2005 Analysis Results(BSPA) reference Finger Preference Change All After preference changed Before LL LR LM LI LT RT RI RM RR RL LL 0 0 0 0 0 0 0 0 0 0 bituation and Pr LR 0 0 0 0 0 0 0 0 0 0 LM 0 0 1 0 0 0 0 1 0 0 LI 0 0 0 6 0 1 0 0 0 0 LT 0 0 1 0 8 1 0 0 0 0 RT 0 0 1 0 2 12 7 5 2 0 n RI 0 0 0 0 0 1 33 5 1 0 RM 0 0 0 4 1 3 0 23 2 0 RR 0 0 0 1 0 1 0 0 6 0 RL 0 0 0 0 0 0 0 0 0 0 Distributio Di t ib ti ns o f b f re/ after preferenc e c h befo / ft f hange Analysis on Hab Before After 45 40 35 s Freq uen c y 30 25 20 15 10 A 5 0 LL LR LM LI LT RT RI RM RR RL Finger Index 40
  • Class note for the 1st term of 2005 Analysis Results – Habituation reference Denominator Foreground Ratio (F) Numerator Number of pixels in foreground area N fforeground F= ×100(%) bituation and Pr d W ×H Image height(=352) Image width(=320) Overlapped area n Sample Foregrounds of 4 Groups Group1 Group2 Group3 Group4 0.25 Analysis on Hab 0.2 Enrolled sample Tested sample uency 0.15 s Frequ 0.1 0.05 A 0 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100% Ratio of area 41
  • Class note for the 1st term of 2005 Analysis Results – Habituation reference Denominator Region of Overlap: Method1 Numerator Number of pixels in overlapped area N overlap M1 = × 100(%) bituation and Pr l N fg _ enrolled Number of pixels in Overlapped area foreground area of enrolled image n M1: OA/ Seg_Enrolled Group1 Group2 Group3 Group4 0.25 Analysis on Hab Enrolled sample Tested sample 0.2 uency 0.15 s Frequ 0.1 0.05 A 0 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100% Score 42
  • Class note for the 1st term of 2005 Analysis Results – Habituation reference Region of Overlap: Method2 N overlap M2= × 100(%) N fg _ enrolled + N fg _ tested − N overlap bituation and Pr Number of pixels in Number of pixels in Number of pixels in overlapped area foreground area of foreground area of tested image enrolled image n M2: OA/ (Seg_Enrolled+Seg_Tested- OA) Denominator Group1 Group2 Group3 Group4 Numerator 0.25 Analysis on Hab 0.2 uency 0.15 s Frequ Overlapped area 0.1 0.05 A 0 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100% Score Enrolled sample Tested sample 43
  • Class note for the 1st term of 2005 Analysis Results – Habituation reference Region of Overlap: Method3 Number of pixels in overlapped area Number of pixels in whole image N overlap N image M3= × × 100(%) bituation and Pr N fg _ enrolled N fg _ enrolled Number of pixels in foreground area of enrolled image n M3: M1/ Foreground_Enrolled Group1 Group2 Group3 Group4 0.25 Analysis on Hab 0.2 uency 0.15 s Frequ 0.1 0.05 A 0 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100% Score 44
  • Class note for the 1st term of 2005 Analysis Results – Habituation reference For All Groups Analysis results for Group1 Analysis results for Group2 Foreground of samples M1(OA/ Enrolled) Foreground of samples M1(OA/ Enrolled) M2(OA/ (Enrolled Tested OA) (Enrolled+Tested- M3(M1/ Foreground Enrolled) M2(OA/ (Enrolled+Tested- OA) (Enrolled Tested M3(M1/ Foreground Enrolled) bituation and Pr 0.25 0.25 0.2 0.2 equency equency 0.15 0.15 n 0.1 0.1 Fre Fre 0.05 0.05 0 0 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100% 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100% Ratio of area Ratio of area Analysis on Hab Analysis results for Group3 Analysis results for Group4 Foreground of samples M1(OA/ Enrolled) Foreground of samples M1(OA/ Enrolled) M2(OA/ (Enrolled+Tested- OA) M3(M1/ Foreground Enrolled) M2(OA/ (Enrolled+Tested- OA) M3(M1/ Foreground Enrolled) 0.25 0.3 s 0.2 0.25 0.2 Frequency Frequency 0.15 0.15 0.1 0.1 A 0.05 0.05 0 0 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100% 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100% Ratio of area Ratio of area 45
  • Class note for the 1st term of 2005 Observations reference Little difference in distributions of personal information between Purdue and Inha Universities except the sensor useness U i iti t th bituation and Pr may affect the analysis results on habituation. n As users get experienced, they prefer right or left index fingers most most. Analysis on Hab This particular sensor becomes inconvenient to s use thumb fingers depending on the placement condition. A 46
  • Class note for the 1st term of 2005 Conclusions reference Finger preferences of users for fingerprint sensor exist, and the preferences of Asians and Westerns are quite similar. W t it i il bituation and Pr n Exterior design of a fingerprint sensor gives an influence to the finger preference of users. Analysis on Hab A s 47
  • Class note for the 1st term of 2005 Future Works reference Habituation analysis on data collected during the experiments Image quality distributions of individual groups bituation and Pr Inter-week Overlap ratio distributions of individual groups n ROC curves in time series for each group Same-week Inter-group ROC curves g p Analysis on Hab p Comparison of habituation results with s preference results A 48
  • Class note for the 1st term of 2005 Comparison reference Based on transferred data BSPA INHA Comment # of subjects (G1) 13 19 2 groups in BSPA are not # of subjects (G2) 16 20 satisfied protocol. bituation and Pr # of subjects (G3) 15 29 # of subjects (G4) 10 24 # of images/finger (G1) 15 25 BSPA did not give 7 images n # of images/finger (G2) 6 13 per group, which are used for enrollment process. Moreover # of images/finger (G3) 6 13 in case of Group1, BSPA # of images/finger (G4) fi /fi 6 13 collected image only 5 times. times Analysis on Hab Total # of images 1323 4272 About 3.23 times A s 49
  • Class note for the 1st term of 2005 Comparison reference Based on transferred data BSPA INHA Comment # of subjects (G1) 13 19 2 groups in BSPA are not # of subjects (G2) 16 20 satisfied protocol. bituation and Pr # of subjects (G3) 15 29 # of subjects (G4) 10 24 # of images/finger (G1) 15 25 BSPA did not give 7 images n # of images/finger (G2) 6 13 per group, which are used for enrollment process. Moreover # of images/finger (G3) 6 13 in case of Group1, BSPA # of images/finger (G4) 6 13 collected image only 5 times. times Analysis on Hab Total # of images 1323 4272 About 3.23 times # of ROL pairs (G1) 8190 34200 = # of images/finger x (# of # of ROL pairs (G2) f i 1440 9360 images/finger - 1) x 3(fingers) s x # of subjects # of ROL pairs (G3) 1350 13752 # of ROL pairs (G4) 900 11232 A Total # of ROL pairs 11880 68544 About 5.77 times 50
  • Class note for the 1st term of 2005 Comparison reference Based on transferred data BSPA INHA Comment Size of height Height of BSPA was fixed Various 352 to 320, which is the minimum. bituation and Pr # of iterations for G1 Durations are the same as 6 5 6 weeks between the first and the last. n # of iterations for G2~4 2 2 Analysis on Hab A s 51