Document Sample

ControlNumber 1 Large Scale AFIS Engineering Rajiv Khanna 29 November 2000 ControlNumber 2 Overview AFIS Applications Functionality Performance parameters Systems engineering relationships Test and measurement Modeling ControlNumber 3 AFIS Applications Enter Wanted Person AFIS Search Response Wanted Person Missing Person – Where – Why Encounter – Cautions Missing Person – Who Felon – Where Felon – Criminal Record ControlNumber 4 Large Scale AFIS Functional Architecture Finger- print(s) Feature Classification Prescreen Extraction (File Partitioning) Matcher Secondary Decision Logic Matcher ControlNumber 5 Feature Extraction Locate and encode features from fingerprint images Features are used by – Classifier – Matchers Direct relationship to image quality – Produce image quality measurements – Small correlation to matcher performance ControlNumber 6 Fingerprint Classification (File Partitioning) Top-down representation of fingerprints Fully Referenced Right Loop Uses global features, typically – Core – delta locations 2% 3% 13% 29% – Ridge counts – Central ridge structure Limit searches to similar 1% classes 1% 0% 22% Three types of Classifiers 5% 12% 2% – Syntactic: Representation 6% 0% 4% and logical rules Whorl – Statistical: Global feature Right Loop/Whorl measurements – Hybrid ControlNumber 7 Prescreen Matcher Coarse (low resolution) matcher Input: Relatively large candidate list & search print Output: Filtered candidate list for secondary matcher Benefits: – Can use older technology – Requires less computer resources per candidate than secondary matcher – Can minimize system computer requirements ControlNumber 8 Secondary Matcher High resolution matcher – More features – Higher discrimination Input: Filtered candidate list & search print Output: Similarity measures for each candidate (to search print) Benefits: – Provide detailed matching – Improve performance Costs: – Requires more computer resources per candidate – Reduce performance if not used properly ControlNumber 9 Decision Logic Combine results for the final report – Accumulate results from distributed processes – Fuse results from • Different matchers • Multiple fingerprints Typically at the end of the processing thread May be embedded in components Prim ary and Secondary Matcher Scores True No-hits 5000 True Hits 4500 False Alarms Miss 4000 Secondary Matcher Score 3500 3000 2500 2000 1500 1000 500 0 0 1000 2000 3000 4000 5000 6000 7000 Prim ary Matcher Score ControlNumber 10 System Performance Parameter Definitions System Reliability (R) – Chance that the system will report a correct match given that there is one in the file System Selectivity (S) – Average number of false candidates per search expected to be reported by the system False Alarm Rate (RFA) – Chance that the system will report an incorrect match Standard Error Margin – Confidence interval for measurements ControlNumber 11 Internal Performance Parameter Definitions Conditional Reliability (Rk) – Chance that the kth stage will pass a correct match given that it passed at previous stages – Output/Input relationship for true matches Filter Rate (Fk) – Expected percentage of input false candidates passed (output) by the kth stage – Output/Input relationship for candidate matches ControlNumber 12 Some System Engineering Relationships System Reliability is the product of conditional reliabilities: RSystem = R1· R2· · · Rk System [average] Filter Rate is the product of stage filter rates: FSystem = F1· F2· · · Fk System Selectivity is the product of file size ( f ) and system filter rate (FSystem): S = f ·FSystem ControlNumber 13 Benchmarking AFIS Benchmarking is a process to measure AFIS performance – Collect representative data • Background File • Mated Pairs – File Fingerprints – Search Fingerprints • Un-mated Search prints – Load File • Background File • File prints with mated search prints – Run Search prints against the file as a benchmark Measure performance parameters ControlNumber 14 Measuring Reliability R is the probability that the N system will report the ˆR 1 R R i correct match given that it N i 1 where is in the file Measured with mated pairs 1 if search results in correct candidate Ri Use a relative frequency 0 if search result is incorrect approach to estimate R i is an index to the searches There is a trade-off N is the number of searches with mates in the file. between Reliability and Selectivity Confidence Interval: ˆ ˆ R(1 R) z / 2 N where z is the number of standard deviations 2 from the mean for the confidenceinterval. ControlNumber 15 Measuring Selectivity N ˆS 1 S is the number of false S N S i 1 i candidates per search where expected to be reported by Si is the number of falsecandidates the system reported for the i th search Use the average to estimate S N is the number of searches. Expect Selectivity to Confidence Interval: increase as file size grows 1 N – Use projection models S2 ˆ N 1 i 1 ˆ ( Si S ) 2 – May need to adjust system to reduce S z 2 ˆ selectivity – Adjustment will lower N Reliability where z is the number of standard deviations 2 from the mean for the confidenceinterval. ControlNumber 16 Measuring False Alarm Rate ˆ O PFA RFA is the probability that C the system will report an ˆ ˆ RFA f PFA incorrect match Applies to systems that where have a binary outcome, e.g. O is the number of observed falsecandidates hit/no-hit report C is the number of finger compares Use a relative frequency f is the file size. approach to estimate RFA Confidence Interval: ˆ ˆ PFA (1 PFA ) z / 2 C where z is the number of standard deviations 2 from the mean for the confidenceinterval. ControlNumber 17 Measuring Filter Rate N 1 Fk is the percentage of Fk N F i 1 i non-mating input candidates expected to be where passed by the kth stage Fi is the filter rate for a search Use the average to N is the number of searches at stage k . estimate Fk Confidence Interval: 1 N F ˆ ( Fi Fk ) 2 2 N 1 i 1 F z 2 ˆ k N where z is the number of standard deviations 2 from the mean for the confidenceinterval. ControlNumber 18 Projecting Selectivity Larger file makes discriminating between mate ˆ S and non-mate fingerprints ˆ S P f target harder f More high-score non-mates test Method 1: Traditional where Statistics Model (shown) ˆ S is the measured selectivity – Divide measured f target is the expected system file size selectivity by test file size f test is the test file size – Multiply by target file size Method 2: Apply extreme value statistics model ControlNumber 19 Selectivity Projection from 70K to 40M File 10000 DS1 Selectivity, T= 0.05, 40M 1000 DS1 Selectivity, T= 0.01, 40M 100 Projected Selectivity 10 1 0.1 0.01 900 1000 1100 1200 1300 1400 1500 1600 1700 1800 1900 2000 2100 2200 Threshold Score ControlNumber 20 Measuring Reliability as a Function of Score 100.00% DS1 Reliability,T= 0.05 DS1 Reliability, T=0.1 Poly. (DS1 Reliability, T=0.1) Poly. (DS1 Reliability,T= 0.05) 95.00% Reliability 90.00% 85.00% 80.00% 1000 1500 2000 2500 3000 3500 Threshold Score ControlNumber 21 Projected Reliability and Selectivity 97.00% 96.00% 95.00% 94.00% Reliability 93.00% 92.00% 91.00% 60M File 40M File 20M File 10M File 5M File 90.00% 0.001 0.01 0.1 1 Projected Selectivity ControlNumber 22 Some [Textbook] Systems Engineering Prove that a 95% minimum conditional reliability is needed to achieve 95% system reliability. Let Rmin be the minimum conditional reliability Rmin R1, R2, R3, R4, · · · , Rk Recall the product equation for conditional reliability RSystem = R1· R2· R3 · · · Rk Rmin since Ri 1 Implies that the other conditional reliabilities must equal 1 !!! (which is hard to do) Corollary : Rmin > System Reliability Requirement ControlNumber 23 Conditional Reliability Measurements System RSSP RM1 RM2 RMM Reliability Ten-print Rolled Ink 99.84% 99.07% 99.94% 99.94% 98.96% Error Margins 0.19% 0.44% 0.11% 0.11% 0.47% Two-print Rolled Ink 99.23% 98.79% 100.00% 99.94% 98.74% Error Margins 0.40% 0.50% 0.00% 0.11% 0.51% Two-print Flat LS 99.88% 91.95% 99.22% 98.50% 89.87% Error Margins 0.17% 1.30% 0.42% 0.58% 1.44% Two-print Flat LS 99.88% 91.90% 99.35% 98.04% 89.51% Error Margins 0.17% 1.31% 0.38% 0.66% 1.47% Note: Reliabilities were computed to machine precision and rounded. Multiplying reported values will have rounding errors. ControlNumber 24 Computer Resources Are Modeled as Linear with File Size 16.00 14.00 Selectivity 0.01 - 0.02 Selectivity 0.02 - 0.03 Selectivity 0.06-0.07 12.00 Relative Computer Resources 10.00 8.00 6.00 4.00 Key Assumptions: scalable architectures, 2.00 small fixed resources, and today’s technology 0.00 0 10 20 30 40 50 60 File Size (Millions) ControlNumber 25 Additional Fingers Reduce Computer Resources and Risks 12.00 Low Selectivity < 0.01 Selectivity 0.01-0.02 10.00 Selectivity 0.02-0.03 Selectivity 0.06-0.07 Extrapolations from File Size Model 8.00 Relative Computer Resources 6.00 Additional Assumption: multiple-flat livescan searches are similar to their 4.00 rolled counterparts 2.00 0.00 0 2 4 6 8 10 12 Num ber of Fingers ControlNumber 26 Summary Proposed a generic AFIS architecture and function definitions Presented performance parameters Methods for measurement Systems engineering Modeling

DOCUMENT INFO

Shared By:

Categories:

Tags:

Stats:

views: | 3 |

posted: | 9/14/2012 |

language: | Unknown |

pages: | 26 |

OTHER DOCS BY pOYowRkL

How are you planning on using Docstoc?
BUSINESS
PERSONAL

By registering with docstoc.com you agree to our
privacy policy and
terms of service, and to receive content and offer notifications.

Docstoc is the premier online destination to start and grow small businesses. It hosts the best quality and widest selection of professional documents (over 20 million) and resources including expert videos, articles and productivity tools to make every small business better.

Search or Browse for any specific document or resource you need for your business. Or explore our curated resources for Starting a Business, Growing a Business or for Professional Development.

Feel free to Contact Us with any questions you might have.