# \[ANN\] LibFaceDetection

**URL:** <https://discourse.julialang.org/t/ann-libfacedetection/51150>\
**Category:** Package Announcements\
**Tags:** package, announcement\
**Created:** [December 2, 2020, 8:59pm UTC](https://discourse.julialang.org/t/ann-libfacedetection/51150 "2020-12-02T20:59:39Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![sdanisch](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/sdanisch/32/1406_2.png) [@sdanisch](https://discourse.julialang.org/u/sdanisch)\
**Post date:** [December 2, 2020, 8:59pm UTC](https://discourse.julialang.org/t/ann-libfacedetection/51150/1 "2020-12-02T20:59:39Z")

</div>

In my quest to make it easy to extract the maximal amount of information from my photos, I wrapped [libfacedetection](https://github.com/ShiqiYu/libfacedetection/):

> **[GitHub - SimonDanisch/LibFaceDetection.jl: Wrapper for...](https://github.com/SimonDanisch/LibFaceDetection.jl)**
>
> Wrapper for https://github.com/ShiqiYu/libfacedetection - GitHub - SimonDanisch/LibFaceDetection.jl: Wrapper for https://github.com/ShiqiYu/libfacedetection

It works pretty well, but still needs to down sample photos (it will not recognize faces correctly on e.g. a 3000x3000 photo)  
Next mission: recognize faces! If anyone has pointers on the state of the art, let me know!  
Last thing I learned was still mostly PCA + Eigenfaces

---

<div class="post-metadata">

**Author:** ![jbrea](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/jbrea/32/3879_2.png) [@jbrea](https://discourse.julialang.org/u/jbrea)\
**Post date:** [December 3, 2020, 8:11am UTC](https://discourse.julialang.org/t/ann-libfacedetection/51150/2 "2020-12-03T08:11:28Z")

</div>

State-of-the-art 6.5 years ago: [DeepFace](https://research.fb.com/publications/deepface-closing-the-gap-to-human-level-performance-in-face-verification/); no clue about current state-of-the-art.