# AI Face Compare (1:1)

Compare two images, output embedding distance and match boolean by threshold, only compare the first face in each image

> Canonical page: https://elysiatools.com/en/tools/ai-face-compare

- **Category:** AI Tools

- **Keywords:** face, compare, distance, recognition

## Overview

The AI Face Compare (1:1) tool allows you to compare two images to determine if they contain the same person. By analyzing the first face detected in each image, the tool calculates the embedding distance and outputs a boolean match result based on your custom threshold and confidence settings.

## Inputs

- **Image A** (file): Upload first image
- **Image B** (file): Upload second image
- **Match Threshold** (number): 0.6
- **Minimum Confidence (0-1)** (number): 0.5

## When to use

- When verifying user identity by comparing a live selfie against a photo ID.
- When checking if two portrait photos belong to the same person under different lighting or angles.
- When deduplicating profile pictures in a database to find matching individuals.

## How it works

- Upload two images in BMP, JPEG, PNG, or GIF format containing the faces you want to compare.
- Adjust the Match Threshold and Minimum Confidence values to fine-tune the comparison sensitivity.
- The AI detects the first face in each image and extracts their facial embeddings.
- The tool calculates the embedding distance and returns a JSON response indicating whether the faces match.

## Use cases

- Identity verification for user onboarding and registration systems.
- Automated moderation to detect duplicate profile photos.
- Verifying employee badge photos against updated headshots.

## Frequently asked questions

### What image formats are supported?

The tool supports BMP, JPEG, PNG, and GIF formats up to 30MB.

### How does the Match Threshold work?

A lower threshold requires a closer match (smaller embedding distance) to return true, while a higher threshold is more lenient.

### Can I compare images with multiple faces?

The tool only detects and compares the first face found in each image.

### What is the Minimum Confidence setting?

It determines the minimum probability score required for the AI to recognize a shape as a face.

### What does the output JSON contain?

It contains the calculated embedding distance and a boolean match result indicating if the faces are the same.

## Related tools

- [Image Adaptive Threshold](https://elysiatools.com/en/tools/image-adaptive-threshold): Apply adaptive threshold operation that calculates threshold for small regions, suitable for varying lighting conditions
- [Image Boolean AND](https://elysiatools.com/en/tools/image-boolean-and): Apply bitwise AND operation between two images to create intersection mask
- [Image Boolean OR](https://elysiatools.com/en/tools/image-boolean-or): Apply bitwise OR operation between two images to create union mask
- [Image Boolean XOR](https://elysiatools.com/en/tools/image-boolean-xor): Apply bitwise XOR operation between two images to create difference mask
- [Image Box Blur](https://elysiatools.com/en/tools/image-box-blur): Apply box blur kernel for simple uniform averaging and fast noise reduction
- [Image Noise Reduction](https://elysiatools.com/en/tools/image-noise-reduction): Reduce image noise using multiple algorithms including median, gaussian, and bilateral filtering
- [Image Trim Whitespace](https://elysiatools.com/en/tools/image-trim-whitespace): Remove whitespace and empty margins from images by detecting and trimming blank areas
- [Image Color Extractor](https://elysiatools.com/en/tools/image-color-extractor): Extract dominant colors from images using various algorithms including k-means clustering and histogram analysis

## Samples

- [macOS Image Processing Objective-C Samples](https://elysiatools.com/en/samples/macos-image-processing-objectivec): macOS Objective-C image processing examples including image reading/saving, image scaling, and format conversion
- [Web Image Processing Go Samples](https://elysiatools.com/en/samples/web-image-processing-go): Web Go image processing examples including image reading/saving, image resizing, and format conversion
- [Web Image Processing Python Samples](https://elysiatools.com/en/samples/web-image-processing-python): Web Python image processing examples using PIL/Pillow including reading, saving, resizing, and format conversion
- [Web Image Processing TypeScript Samples](https://elysiatools.com/en/samples/web-image-processing-typescript): Web TypeScript image processing examples including image read/save, scaling, and format conversion

## Related content

- [AI Face Analysis: Detection, Comparison, and Recognition Workflows](https://elysiatools.com/en/hubs/ai-face-detection-recognition-workflows): Separate face detection and alignment from descriptor comparison, gallery recognition, and expression or age-gender estimation, with practical privacy and error boundaries.