Counting 2,987 Big Data & Machine Learning Frameworks, Toolsets, and Examples...
Suggestion? Feedback? Tweet @stkim1

Last Commit
Jul. 19, 2018
Dec. 21, 2017


SeetaFace detection library for the Rust programming language

Bt Example Example of demo program output Linux build License


SeetaFace Detection is an implementation of Funnel-Structured cascade, which is designed for real-time multi-view face detection. FuSt aims at a good trade-off between accuracy and speed by using a coarse-to-fine structure. It consists of multiple view-specific fast LAB cascade classifiers at early stages, followed by coarse Multilayer Perceptron (MLP) cascades at later stages. The final stage is one unified fine MLP cascade, processing all proposed windows in a centralized style.



Crude manual benchmarking shows that the Rust version is slightly faster than the original C++ version. Here are some numbers for a medium-sized image with 29 persons, which you may see above in this readme:

Image size: 1666x1136
Number of faces: 29

CPU: 2,3 GHz Intel Core i7
Single-threaded (OpenMP disabled, Rayon threads set to 1)
SIMD enabled
LTO disabled

* Original *
samples (ms): 893,893,891,883,884,883,890,908,893,879
mean (ms): 889.7
stddev (ms): 7.785

* Rustface *
samples (ms): 867,861,851,850,856,847,855,851,850,861
mean (ms): 854.9
stddev (ms): 6.024

In this particular test the Rust version has been 4% faster on average than its C++ counterpart.

When using multiple threads and enabling LTO (link-time optimization), Rust performance is a tad better (I observe a 8% boost):

Multi-threaded (Rayon threads set to 2)
LTO enabled

* Rustface *
samples (ms): 787,789,795,795,787,785,791,799,795,788
mean (ms): 791.1
stddev (ms): 4.39

Usage example

extern crate rustface;

use rustface::{Detector, FaceInfo, ImageData};

fn main() {
    let mut detector = rustface::create_detector("/path/to/model").unwrap();
    detector.set_slide_window_step(4, 4);
    let mut image = ImageData::new(bytes, width, height);
    for face in detector.detect(&mut image).into_iter() {
        // print confidence score and coordinates
        println!("found face: {:?}", face);

How to build

The project is a library crate and also contains a runnable example for demonstration purposes.

Due to usage of experimental stdsimd crate for SIMD support, the project relies on the nightly Rust toolchain, so you'll need to install it and set it as the default:

rustup default nightly

Then just use the standard Cargo build command:

cargo build --release

Run demo

Code for the demo is located in examples/ file. It performs face detection for a given image and saves the result into a file in the working directory.

The simplest way to run the demo is to use the bin/ script:

./bin/ <path-to-image>

Please note that this library makes use of Rayon framework to parallelize some computations. By default, Rayon spawns the same number of threads as the number of CPUs (logicals cores) available. Instead of making things faster, the penalty of switching between so many threads may severely hurt the performance, so it's strongly advised to keep the number of threads small by manually setting RAYON_NUM_THREADS environment variable.

# empirically found to be the sweet spot for the number of threads
cargo run --release --example image_demo model/seeta_fd_frontal_v1.0.bin <path-to-image>


  • Parallelize remaining CPU intensive loops
  • Tests (it would make sense to start with an integration test for Detector::detect, based on the results retrieved from the original library)


This library is based on the following works:

  • Face detection method described in the paper: "Funnel-structured cascade for multi-view face detection with alignment awareness, Shuzhe Wu, Meina Kan, Zhenliang He, Shiguang Shan, Xilin Chen. In Neurocomputing (under review)"

  • original C++ implementation


Original SeetaFace Detection is released under the BSD 2-Clause license. This project is a derivative work and uses the same license as the original.