kpzhang93/MTCNN_face_detection_alignment

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2862 stars · 979 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Reference MATLAB/Caffe implementation of MTCNN, a multi-task cascaded convolutional neural network for joint face detection and facial landmark alignment. It is the official code accompanying the 2016 IEEE SPL paper of the same name.

Use cases

• detect faces in images with a CNN
• find facial landmarks for face alignment
• preprocess faces for a face recognition pipeline
• reproduce MTCNN paper results
• run face detection on GPU with Caffe

When to choose

• you need the original reference implementation of MTCNN
• your stack is MATLAB with Caffe
• you want a well-cited baseline for face detection and alignment research

When to avoid

• you want a maintained Python or PyTorch implementation instead
• you need production deployment without MATLAB/Caffe dependencies
• you need active development or recent bug fixes

Facets

library · maturity maintenance

machine-learning deep-learning computer-vision image-processing computer-vision deep-learning machine-learning image-processing windows cpp face-detection face-alignment mtcnn cascaded-cnn caffe landmark-detection research-code linux matlab gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="kpzhang93/MTCNN_face_detection_alignment")