Results of testing algorithms of Russian biometric companies in the world market
Russia is discussing the creation of a mega National Biometric Center with a database of 100-150 million records. And the draft law on mandatory biometric registration has already been submitted to the State Duma. Since all this, theoretically, is obliged to work on patriotic equipment, that is, for reasons of information protection, it is desirable that the brains and equipment should geographically be located within the country, I think you will be interested in what is good, theoretically, we can this turn out.
Most recently, two-year testing of the pVTE-12 (Fingerprint Vendor Technology Evaluation 2012) has been completed at the US National Standards Institute (NIST).
')
The purpose of testing is to assess the real capabilities of fingerprint identification systems today. This is the largest testing (large databases and data types), which lasted for two years.
Test data are divided into three groups:
And - prints of two index fingers without segmentation of 1.6 million records.
B - prints of ten fingers, in a group of 4 + 4 + 2 (this is eat four fingers + thumb from each hand) with segmentation. The volume of base is 3 million records.
C - rolling and contact prints of ten fingers in the group 4 + 4 + 1 + 1 with segmentation. The base volume is 5 million records.
Task: for a limited amount of time, search for information in the one-to-many mode. Companies that did not meet the time limit were removed from the test. Therefore, all companies have prepared new high-speed identification algorithms.
The protocol recorded not only the accuracy of the comparison but also the speed. Therefore, for testing the company provided two variants of the algorithm: fast and slower.
Of the 22 two companies, only 18 were able to pass at least one test. These are almost all world-famous biometric companies (NEC, 3M, Safran, etc.) as well as two Russian companies - Sonda, Papillon and several other new lesser-known ones.
The most important test is the āCā test based on 5 million records. In accuracy, the first three places were taken by the giants - NEC (Japan), Morpho / Safran (France) 3M Cogent (USA).
And our company Sonda (severe Chelyabinsk!) In the search mode for contact prints on rolling took 4th place!
In the search mode contact on the contact and rolling on rolling - 5th.
The probability of an error at the level of 0.3% differs from the group of leaders by a factor of two, however, Sonda surpasses the leaders in the speed of comparison and the length of the mathematical code.
As for Papillon, it is a pity. Apparently, the guys did something wrong with the algorithms and the probability of an error differs 40ā100 times from the leader group and ranges from 5 to 20%, which in practice is, of course, unacceptable.
According to the test results, NIST identified five companies that provided optimal algorithms taking into account three factors: identification accuracy, comparison speed and required resources: Sonda (Russia), Innovatrics (Slovakia), Morpho (France), IDSolutions (USA) and AA Technology (China ).
In the wake of this event, I wanted to be able to get a comment on the test results from our local biometrics specialist ZlodeiBaal .
Full test report: nvlpubs.nist.gov/nistpubs/ir/2014/NIST.IR.8034.pdf
Most recently, two-year testing of the pVTE-12 (Fingerprint Vendor Technology Evaluation 2012) has been completed at the US National Standards Institute (NIST).
')
The purpose of testing is to assess the real capabilities of fingerprint identification systems today. This is the largest testing (large databases and data types), which lasted for two years.
Test data are divided into three groups:
And - prints of two index fingers without segmentation of 1.6 million records.
B - prints of ten fingers, in a group of 4 + 4 + 2 (this is eat four fingers + thumb from each hand) with segmentation. The volume of base is 3 million records.
C - rolling and contact prints of ten fingers in the group 4 + 4 + 1 + 1 with segmentation. The base volume is 5 million records.
Task: for a limited amount of time, search for information in the one-to-many mode. Companies that did not meet the time limit were removed from the test. Therefore, all companies have prepared new high-speed identification algorithms.
The protocol recorded not only the accuracy of the comparison but also the speed. Therefore, for testing the company provided two variants of the algorithm: fast and slower.
Of the 22 two companies, only 18 were able to pass at least one test. These are almost all world-famous biometric companies (NEC, 3M, Safran, etc.) as well as two Russian companies - Sonda, Papillon and several other new lesser-known ones.
C afis team A, B, C D 3M Cogent A, B, C E Neurotechnology A, B, C F Papillon A, B, C G Dermalog A, B, C H Hisign Bio-Info Institute A, B, C I NEC A, B, C J Sonda A, B, C K Tiger IT A L Innovatrics A, B, C M SPEX A, B, C O ID Solutions A, B, C P id3 A Q Morpho A, B, C S Decatur Industries A, B, C T BIO-key A U Aware A, B, C V AA Technology A, B, C The most important test is the āCā test based on 5 million records. In accuracy, the first three places were taken by the giants - NEC (Japan), Morpho / Safran (France) 3M Cogent (USA).
And our company Sonda (severe Chelyabinsk!) In the search mode for contact prints on rolling took 4th place!
In the search mode contact on the contact and rolling on rolling - 5th.
The probability of an error at the level of 0.3% differs from the group of leaders by a factor of two, however, Sonda surpasses the leaders in the speed of comparison and the length of the mathematical code.
As for Papillon, it is a pity. Apparently, the guys did something wrong with the algorithms and the probability of an error differs 40ā100 times from the leader group and ranges from 5 to 20%, which in practice is, of course, unacceptable.
According to the test results, NIST identified five companies that provided optimal algorithms taking into account three factors: identification accuracy, comparison speed and required resources: Sonda (Russia), Innovatrics (Slovakia), Morpho (France), IDSolutions (USA) and AA Technology (China ).
In the wake of this event, I wanted to be able to get a comment on the test results from our local biometrics specialist ZlodeiBaal .
Full test report: nvlpubs.nist.gov/nistpubs/ir/2014/NIST.IR.8034.pdf
Source: https://habr.com/ru/post/250725/
All Articles