MTCNN Face Detection

Face detection and landmark localisation using deep learning.
1.4K Downloads
Updated 3 Mar 2021

Editor's Note: This file was selected as MATLAB Central Pick of the Week

This repository implements deep learning based face detection and facial landmark localisation using Multi-Task Cascaded CNNs.
For more details see the GitHub repository: https://github.com/matlab-deep-learning/mtcnn-face-detection

Cite As

Justin Pinkney (2026). MTCNN Face Detection (https://github.com/matlab-deep-learning/mtcnn-face-detection/releases/tag/v1.2.4), GitHub. Retrieved .

MATLAB Release Compatibility
Created with R2020b
Compatible with R2019a and later releases
Platform Compatibility
Windows macOS Linux

code/mtcnn/doc

Versions that use the GitHub default branch cannot be downloaded

Version Published Release Notes
1.2.4

See release notes for this release on GitHub: https://github.com/matlab-deep-learning/mtcnn-face-detection/releases/tag/v1.2.4

1.2.3

See release notes for this release on GitHub: https://github.com/matlab-deep-learning/mtcnn-face-detection/releases/tag/v1.2.3

1.2.2

Fixes bug in relative ordering of boxes and landmarks as well as potential error when there are overlapping boxes (#17)

1.2.1

Fixes bug when using UseGPU=True with UseDagNet=True (i.e. R2019a support) (#12)

1.2.0

- Adds support for R2019a
- detect and detectFaces functions accept uint8, single, and double image types
- fixes a bug in proposeRegions for certain image sizes.

1.0.1.0

See release notes for this release on GitHub: https://github.com/matlab-deep-learning/mtcnn-face-detection/releases/tag/v1.0.1

1.0

To view or report issues in this GitHub add-on, visit the GitHub Repository.
To view or report issues in this GitHub add-on, visit the GitHub Repository.