---
title: EER
tags:
- evaluate
- metric
description: "Equal Error Rate (EER) is a measure that shows the performance of a biometric system, like fingerprint or facial recognition. It's the point where the system's False Acceptance Rate (letting the wrong person in) and False Rejection Rate (blocking the right person) are equal. The lower the EER value, the better the system's performance.

EER is used in various security applications, such as airports, banks, and personal devices like smartphones and laptops, to evaluate the effectiveness of the biometric system in correctly identifying users."
sdk: gradio
sdk_version: 3.19.1
app_file: app.py
pinned: false
---

# Metric Card for EER

***Module Card Instructions:*** *Fill out the following subsections. Feel free to take a look at existing metric cards if you'd like examples.*

## Metric Description
*Equal Error Rate (EER) is a measure that shows the performance of a biometric system, like fingerprint or facial recognition. It's the point where the system's False Acceptance Rate (letting the wrong person in) and False Rejection Rate (blocking the right person) are equal. The lower the EER value, the better the system's performance.

EER is used in various security applications, such as airports, banks, and personal devices like smartphones and laptops, to evaluate the effectiveness of the biometric system in correctly identifying users.*

## How to Use
```
eer = evaluate.load("Felipehonorato/eer")
```

### Inputs
*List all input arguments in the format below*
- **predictions** *(int): Predicted values from your model*
- **reference** *(int): Ground truth values from your model*
- **pos_label** *(int): The label id that corresponds to positive labels*

## Citation
*It is difficult to pinpoint the exact first paper that introduced the concept of Equal Error Rate (EER). However, the term "equal error rate" and its significance to biometric systems gained popularity during the late 1990s and early 2000s. One notable early work discussing EER is the book "Biometrics: Personal Identification in Networked Society" written by Anil K. Jain, Ruud M. Bolle, and Sharath Pankanti, published in 1999. The authors provided insights into various metrics used to assess the performance of biometric systems, including EER.*

## Further References
[Codebase](https://github.com/YuanGongND/python-compute-eer)