A massive multi-biometric voter registration deduplication project for the Democratic Republic of the Congo (DRC) has identified that more than 10% of the voter database was duplicated.
Neurotechnology, a provider of high-precision biometric identification technologies, worked with the Independent National Electoral Commission in the DRC to implement the system.
The MegaMatcher Automated Biometric Identification System (ABIS) solution based on the MegaMatcher Accelerator Extreme (MMA Extreme) matching engine was used to perform simultaneous deduplication of more than 46,5-million multibiometric facial and fingerprint voter records – an all-with-all comparison with a magnitude of 46,5-million x 46,5-million records.
The system completed the job in less than two months, using 11 servers for matching and identifying more than 5,3-million duplicates – more than 10% of the original voter database.
“In the voter registry cleaning process our goal is to find as many duplicates and other noncompliant cases as possible,” says Corneille Nangaa Yobeluo, president of Commission Électorale Nationale Indépendante. “Neurotechnology helped us achieve our goals and exceeded our expectations by starting and completing the deduplication process in record time, and they were able to identify millions of duplicates.”
For the DRC, more than 46,5-million voter records were collected with 10 fingerprints and a facial biometric for each record. MegaMatcher ABIS identified more than 5,3-million duplicate records.
Neurotechnology’s age estimation algorithm was used to check each registered voter’s photo, estimate age and flag potential noncompliant records for review. During this process more than 900 000 records were found as non-compliant according to voter age requirements. This will have a significant impact on the upcoming elections where DRC constituencies are represented in National and Provincial Assemblies based on their voter numbers.
The accuracy of the process was verified by nearly 300 human operators who manually reviewed and confirmed the duplicates and under-age records identified by the system.
“To create, deploy and use Automated Biometric Identification Systems at a small scale is relatively easy; complexity and major challenges appear with scale,” says Denis Kacan, MegaMatcher ABIS product manager for Neurotechnology. “With successful implementation of this project, our MegaMatcher ABIS and MegaMatcher Accelerator Extreme products proved to be suitable for large national scale deployments.”