Face Analyzer: facial landmarks, pose, gender, age, race – Dev Community

For more detail this asset from the Unity Asset Store: Click Here

Face Analyzer v2.2 (Latest version)

Download Now

“Sharing is caring”

Face Analyzer is a deep-learning based face analyzer plugin, trained with 150,000+ datasets and OpenCV/NCNN API for Unity C#.

It provides:

1) 51 / 84 facial landmarks detection

2) head pose estimation (roll, pitch and yaw)

3) gender estimation (male / female)

4) age estimation (0 ~ 99)

5) race estimation (white / black / Asian / Indian / others)

6) baldness estimation (bald or not bald)

7) blond hair estimation (blond or not blond)

8) eyeglasses detection (wearing eyeglasses or not)

9) hat detection (wearing hat or not)

10) facial expression estimation(neutral, happy, sad, fear, disgust, angry, and surprise) [THIS IS BETA]

11) lightweight OpenCV API (https://opencv.org) for Unity C# with only core, imgproc, and dnn module.

(If you want more OpenCV module, feel free to contact us : ) )

12) NCNN API (https://github.com/Tencent/ncnn) for Unity C#

13) Offline work, Doesn’t require server

14) Various AR Sticker Examples

Trained deep learning model is also lightweight.

Facial landmarks(and head pose) model size is just 3.8MB and facial attributes model size(gender, age, race, baldness, blond hair, eyeglasses, hat) is just 14.6MB. Facial expressions model size is just 8.89MB.

If you find a bug or you can’t use the asset as you need,

please first email me to [email protected] (in English or in Korean) before leaving a review on the asset store.

I am here to help and to improve my assets for the best.

Response time can be up to 5 business days.

System Requirements:

Windows, macOS, Android and iOS are supported.

You can see all the features of this plugin in detail in this document.

https://drive.google.com/file/d/1ne603ENy4NiTwvlMBhlQ2QnxlI4CMhw_/view

“This asset uses [OpenCV and NCNN c++ open-source] under [3-clause BSD License]; see Third-Party License.txt file in package for details.”

Best,