Skip to content

caiorgarcez/Facial-Recognition-Dataset-Generator

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

fr-dataset

Script for generating a custom facial recognition dataset for deep learning applications.


1. Install the environment

Packages and other requirements to run fr-dataset is provided for conda in requirements.yml and for pip in requirements.txt.

for conda run: $ conda env create -f requirements.yml

for pip run: $ pip install -r requirements.txt


2. Usage and features:

-isrc Path of the video file. If the video source comes from a webcam set: <0>
-sol Solution for facial detection. Options: or
-c Crop output frame. Options: <0> for no <1> for yes
-o Path of the output folder for writing frames
-n Name of the person -res Folder of RESNET facial detector files compatible with the .dnn Opencv lib
-conf Minimum probability to filter weak detections

Example: $ python main.py -isrc 0 -sol dlib -c 0 -o output -n <name1>


3. Observations:

Within the project repository it is necessary to create a folder named output to store the captured frames. Later, provide in the parse the name of the folder as in: $ ... -o <output path>

The code for this project is based in: [1]

About

Scripts for generating a facial recognition dataset for deep learning applications.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages