Description
Return false-accept/reject rates and expected error cost at one point.
Biometric scores depend on matcher version, score direction, acquisition handling and an explicit operating threshold. Score transformations and observed error fractions are different from identity verification; equality, quantization and excluded attempts can change the local reported result.
Return false-accept/reject rates and expected error cost at one point.
When to use this tool
Use Biometric Detection Error One Operating Point when checking the stated biometric score, threshold, reporting precision or error-denominator convention.
How to use the tool and how it works
- Enter falseAccepts, impostorAttempts, falseRejects, genuineAttempts, priorImpostor, falseAcceptCost, falseRejectCost. Use the units and conventions below.
- Run the tool. Correct any format, range, or cross-field input error before interpreting the output.
- Read far, frr, weightedCost. Use the output convention below.
Return false-accept/reject rates and expected error cost at one point. Require bounded whole error/attempt counts, priorImpostor in [0,1] and nonnegative costs; weightedCost = prior*acceptCost*FAR+(1-prior)*rejectCost*FRR.1
| Input field | Meaning and units | Accepted input |
|---|---|---|
| falseAccepts | False Accepts | Required. Safe integer; minimum 0. |
| impostorAttempts | Impostor Attempts | Required. Safe integer; minimum 1. |
| falseRejects | False Rejects | Required. Safe integer; minimum 0. |
| genuineAttempts | Genuine Attempts | Required. Safe integer; minimum 1. |
| priorImpostor | Prior Impostor | Required. Finite number; minimum 0; maximum 1. |
| falseAcceptCost | False Accept Cost | Required. Finite number; minimum 0. |
| falseRejectCost | False Reject Cost | Required. Finite number; minimum 0. |
| Output field | Interpretation | Returned shape |
|---|---|---|
| far | Far | Required. Finite number. |
| frr | Frr | Required. Finite number. |
| weightedCost | Weighted Cost | Required. Finite number. |
{
"input": {
"falseAccepts": 2,
"impostorAttempts": 1000,
"falseRejects": 5,
"genuineAttempts": 100,
"priorImpostor": 0.1,
"falseAcceptCost": 10,
"falseRejectCost": 1
},
"output": {
"far": 0.002,
"frr": 0.05,
"weightedCost": 0.047
}
}Limitations and assumptions
- No operating-point optimization, error tradeoff curve, uncertainty, identity verification or appropriate cost/prior choice is provided.
- Inputs must satisfy both the field types and the cross-field conditions above. Invalid input causes an error; a successful false flag or documented placeholder is a different result.
- Numeric calculations use binary floating point unless exact decimal-integer arithmetic is explicitly stated. No hidden measurement tolerance or decimal rounding is added; nonfinite or out-of-contract results are rejected. Numeric signed-zero results are exported as zero.
Alternative or Complementary methods
Evaluate a validated matcher on relevant complete data with explicit acquisition/exclusion and threshold policies; assess uncertainty, privacy and fairness independently.
References
Similar or alternative tools
- Biometric Failure Acquisition Share
Return acquisition-failure rate and usable-acquisition count.
- Biometric False Match Count Denominator
Return false-match rate under an excluded-count denominator policy.