ID: 5fa3fcdfc2a4984b34ef0c62

Age and Gender Recognition

by Spectrico

Age and Gender Recognition


License: MIT License

Tags: age and gender recognition face detection Tensorflow

 Model stats and performance
Framework Tensorflow
OS Used Windows
Inference time in seconds per sample.

Performance data is not available.

Screenshots


Age and Gender Recognition - Python example

Introduction

A Python example for using Spectrico's age and gender classifier. It consists of a face detector for finding the faces, and a classifier to recognize the age and the gender of the detected faces. The face detector is an implementation of MTCNN (Tensorflow backend). The classifier is based on MobileNet (Tensorflow backend). Tested under Windows 10 and Ubuntu.

There is a paid version with better accuracy. Here is a web demo to test it: Age and Gender Recognition

Usage

$ python age_gender_demo.py

Dependencies

pip install numpy

pip install opencv-python

pip install tensorflow

If you use Windows, the OpenCV package is recommended to be installed from: https://www.lfd.uci.edu/~gohlke/pythonlibs/


Credits

The age and gender classifier is based on MobileNet neural network architecture: MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

@misc{howard2017mobilenets,
      title={MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications}, 
      author={Andrew G. Howard and Menglong Zhu and Bo Chen and Dmitry Kalenichenko and Weijun Wang and Tobias Weyand and Marco Andreetto and Hartwig Adam},
      year={2017},
      eprint={1704.04861},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

The face detector is MTCNN: Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks

@ARTICLE{7553523, 
author={K. Zhang and Z. Zhang and Z. Li and Y. Qiao}, 
journal={IEEE Signal Processing Letters}, 
title={Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks}, 
year={2016}, 
volume={23}, 
number={10}, 
pages={1499-1503}, 
keywords={Benchmark testing;Computer architecture;Convolution;Detectors;Face;Face detection;Training;Cascaded convolutional neural network (CNN);face alignment;face detection}, 
doi={10.1109/LSP.2016.2603342}, 
ISSN={1070-9908}, 
month={Oct},}

Reference MTCNN implementation:

https://github.com/davidsandberg/facenet/tree/master/src/align

Author View Profile


Spectrico
Sofia, Bulgaria
Level 9 8800 XP

204 Profile
Views

User Reviews



0 total ratings

Model has not been reviewed yet.

More by this user | Show All



Also checkout...