Facial Analysis: Lite Detector 2D (Python API)

• Introduction
• Trained Models
• Requirements
• Status
• Related projects

Introduction

facialAnalysisLiteDetection2D module use tensorflow , cvlib and openCV python API. The module analyze faces using pre-trained models and adds facial analysis doing prediction about some features like gender, age and emotions. Also use YARP to send video source pre and post-procesed. Also admits YARP source video like input. This module also publish detection results in YARP port.

Documentation available on docs

Trained Models

facialAnalysisLiteDetection2D requires images source to detect. First run program will download gender pre-trained models, the rest of the models are located in models dir, about features to detect:

1. Execute programs/facialAnalysisLiteDetection2D.py, to start the program.

python3 facialAnalysisLiteDetection2D.py

3. Connect video source to facialAnalysisLiteDetection2D.

yarp connect /videoSource /facialAnalysisLiteDetection2D/img:i

NOTE:

• Video results are published on /facialAnalysisLiteDetection2D/img:o
• Data results are published on /facialAnalysisLiteDetection2D/data:o

Requirements

facialAnalysisLiteDetection2D requires:

• Install OpenCV 3.4.7+
• Install YARP 2.3.XX+
• Install pip
• Install tensorflow 1.13.1+:

pip3 install tensorflow==1.13.1

• Install cvlib:

pip3 install cvlib

Tested on: windows 10, ubuntu 14.04, ubuntu 16.04, ubuntu 18.04, lubuntu 18.04 and raspbian.

Status

Related projects

• arunponnusamy: cvlib project
• atulapra: Emotion-detection project