Hisign Biometric Identification Engine



 

Product Introduction

 

HBIE (Hisign Biometric Identification Engine) is a cross-platform software and hardware solution of multi-modal biometric identification including face, fingerprint, palm print and iris.

 

http://www.hisign.com.cn/uploads/allimg/160818/1-160QQ54R2259.png

 

The system can be applied in biometric identification projects of tens of millions of records.

The system can be supplied as a ready-to-use solution or as a software running on common PC.

The system can provide fast matching speed up to one hundred million faces (one face image for each person), or two million fingerprints (four prints for each person), or two million iris (one image for each person) per second.  The system supports for three biometric modals of face, iris and fingerprint.

 

•  The system supports for clustered extension.

•  The system supports for ISO & ANSI standards.

•  The system supports for multi-language API.

•  The system is composed of Master (control unit)and Matcher (matching unit).

 

Algorithm Accuracy

 

        We have participated in several international test and obtained good results.

 

http://www.hisign.com.cn/uploads/allimg/160818/1-160QQ42230403.pnghttp://www.hisign.com.cn/uploads/allimg/160818/1-160QQ42253102.png

 

a) FVC-onGoing

FVC-onGoing is a web-based automated evaluation system for fingerprint recognition algorithms. Tests are carried out on a set of sequestered datasets and results are reported on-line by using well known performance indicators and metrics.

The aim is to track the advances in fingerprint recognition technologies, through continuously updated independent testing and reporting of performances on given benchmarks. The algorithms are evaluated using strongly supervised approaches to maximize trustworthiness.

Recently, we took the Fingerprint Verification Tests in the name of Beijing Hisign Bio-info Institute and won the first place in both stand and hard modes. Results are shown as blow,

 

  

 

For details of the test results navigate to Click Here

 

 

b) NIST-MINEX

The Minutiae Interoperability Exchange Test (MINEX) is an ongoing evaluation of the INCITS 378 fingerprint template. The test program has two mandates:

 

•  To provide measurements of performance and interoperability of core template encoding and matching capabilities to users, vendors and interested parties.

•  To establish compliance for template encoders and matchers for the United States Government's Personal Identity Verification (PIV) program.

 

We have passed the Generator test of MINEXIII, the template generated conformed to NIST requirements. According to the result, Hisign ranks the fourth.

 

 

c) NIST-PFT-II

NIST Proprietary Fingerprint Template Evaluation II (PFT II) is one-to-one verification evaluation which measures the performance of fingerprint matching algorithms by utilizing proprietary fingerprint templates. The samples dataset have been increased to 120,000 subjects compared to previous PFT evaluation. Number of experiments was also increased to 33 with different combinations of single and two fingerprint matching.

In 2017 Hisign fingerprint algorithm was submitted to NIST Proprietary Fingerprint Template Evaluation II. The algorithm's template matching accuracy was among the best participants in most of the experiments.

The test result for each vendors can be found at https://www.nist.gov/itl/iad/image-group/proprietary-fingerprint-template-evaluation-ii-pftii-results, and the data in below sheets are the summary of combined and comparison of each vendors test results.

 

 

d) FRVT2013

The Face Recognition Vendor Test (FRVT) 2013 continues a series of large scale independent evaluations for face recognition systems. The primary goal of the FRVT 2013 is to measure advancements in the capabilities of prototype systems and algorithms from the commercial and academic communities. The FRVT 2013 aims to evaluate performance on several recognition tasks, including:

 

•  One-to-many identification in a set of mugshot images

•  One-to-one verification of visa images

•  Multi-sample still facial imagery

•  Recognition of persons in video sequences

•  Twins

  90 degree profile-view

•  Gender estimation (M/F)

  Age estimation (in years)

•  Pose estimation

•  Expression neutrality

 

We participated this test in the name of Beijing Ivsign Technology Co., Ltd. with assigned company letter code G (Hisign), and obtained a result of FNMR = 0.094 at FMR = 0.001. The test report is available at http://ws680.nist.gov/publication/get_pdf.cfm?pub_id=915761

 

 

e) CCIR2014

The First CCBR Competition on Iris Recognition(CCIR2014)is open to both academia and industry. We participated this test and the equal error rate (EER) of our algorithm is 0.0319.  The final result of the test is not available publicly yet and the details of the test is given at http://biometrics.idealtest.org/2014/CCIR2014.jsp

 

 

f) Palm Verification

Palm verification is a test of the performance of the participants’ matching algorithm on their own characteristics.


All benchmarks: ranked the second, and the results shown below. (Ranking may be changed after updated date.)

Related Web link:

Click Here

 

 

For more test results please see http://www.hisign.com.cn/en/Hisign_News/