BVAS face matching accredited Nigerian voters when fingerprints failed

Three observer missions found that BVAS facial recognition accredited voters where fingerprints failed in Nigeria's 2023 elections. Two saw it work faster, and the EU mission saw fewer rejections.

  • 2 a person

    Where fingerprint scanning failed, observers saw facial recognition accredit voters so that they could vote, and the EU mission saw fewer rejections. No mission counted the voters affected.

  • 1 an organization

    The EU and Commonwealth observers saw INEC's polling staff accredit voters faster with the facial mode than with fingerprints.

Depth runs from 1, a convenience or time saved, to 5, a life or a livelihood preserved.

Status
Reported benefit.
Evidence

foundstudiedreportedclaimed

Three independent assessment reports support the benefit.

Compared with

Fingerprint accreditation on the same BVAS devices. Measured.

The system’s part
Not isolated. The observers compared the device's facial mode with its fingerprint mode and gave no counts. They did not compare accreditation with and without BVAS. No report describes the face-matching software or shows that it learns from data, and the Commonwealth group could not rule out false positives.
Limits
Not yet checked.
Costs and harms
Not yet checked.
Later
Not yet checked.

Download data Cite Suggest a correction

Benefit type
Reduced Task Time
System
Bimodal Voter Accreditation System (BVAS), facial recognition function
Made by
Independent National Electoral Commission (INEC), an in-house design according to the EU mission (the supplier of the face-matching software is not named)
Used by
Independent National Electoral Commission (INEC), Nigeria
Where
Nigeria (polling units nationwide)
Stage
In routine use
Date
Kind
Aggregate result
Broad benefit
Identifying Objects, Actions, and Events, Processing Information
Collections
Scrutiny and findings
Last revised
31 October 2026

Sources

  1. Assessment report, by authors with no tie to the system.

    European Union Election Observation Mission Nigeria 2023. Final Report: General Elections 25 February and 18 March 2023, section VII (Election technology), b. Implementation, pp. 19-20. Presented 27 June 2023. The mission states that it is independent in its findings and conclusions. It reports its own observers' findings, and it calls BVAS an INEC in-house development.

    During both election days BVAS was able to accredit voters without significant issues. The facial accreditation process was on many occasions surprisingly faster and had fewer rejection

  2. Assessment report, by authors with no tie to the system.

    Commonwealth Secretariat. Nigeria Presidential and National Assembly Elections, 25 February 2023: Report of the Commonwealth Observer Group, chaired by Thabo Mbeki. Chapter 3, Legal Framework and Electoral Administration, p. 25. Letter of transmittal dated 16 February 2024. The Commonwealth Secretary-General constituted the group, which reports its own observers' findings and has no role in BVAS.

    On election day, the Group noted widespread failure of the fingerprint scanning functionality of BVAS devices. In such instances, facial recognition was used instead, with much faster and better results. Yet fingerprint scanning is widely regarded as being more stable than facial recognition.

  3. Assessment report, by authors with no tie to the system.

    International Republican Institute and National Democratic Institute. IRI/NDI International Election Observation Mission to Nigeria: Final Report of the 2023 General Election, 2023. Executive summary and the section on the presidential and National Assembly election day. A joint mission of two US democracy institutes, with a 40-member delegation that observed in 20 states on 25 February 2023.

    Observers noted that the BVAS largely functioned properly, although some polling officials struggled to understand how to operate the system and in many cases the BVAS failed to authenticate voters via fingerprints, while the facial recognition feature functioned well.

Details

AI system

Workflow

The BVAS device matched each voter's fingerprints or face with the biometric data stored on it at the polling unit. Polling officials switched to the facial mode when fingerprint matching failed, as INEC's procedures allowed.

Follow-up

Conditions for replication

The register must hold a usable facial image for each voter. The face-matching threshold must be strict enough to avoid false matches, which the observers could not check.

Entry details

Sector

Elections.

Purpose

INEC built the Bimodal Voter Accreditation System to verify each voter's identity by fingerprint or face at the polling unit and to upload the results forms.

Not yet checked: model, release, provider, role, configuration, inputs and outputs, autonomy, human oversight, AI contribution, beneficiaries, reach, distribution and access, duration, every measurement question, every money question, ownership and control, dependencies, cross-border connections, geopolitical implications, replication attempts, availability, institutional decision, grounds, action and result, success criterion, every evidence question, observed or intended, alternative assessments, related entries, other identifiers, category mappings.

Cite this record

Peter H. Vartanian. (2026). BVAS face matching accredited Nigerian voters when fingerprints failed (AIBD-0859). Artificial Intelligence Benefits Database, edition of 31 October 2026. https://petervartanian.xyz/aibd/records/AIBD-0859.html (archived at https://doi.org/10.7910/DVN/AADSII, version 4.0)

BibTeX Data Field definitions