Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/altunenes/part-whole

Swap facial landmarks(or whole facial area) for the part-whole task with OpenCV + dlib and MediaPipe.

https://github.com/altunenes/part-whole

Science Score: 31.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ○
    codemeta.json file
  • ○
    .zenodo.json file
  • ✓
    DOI references
    Found 2 DOI reference(s) in README
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (6.9%) to scientific vocabulary

Keywords

dlib face mediapipe neuroscience-methods opencv part-whole psychology
Last synced: 5 months ago · JSON representation ·

Repository

Swap facial landmarks(or whole facial area) for the part-whole task with OpenCV + dlib and MediaPipe.

Basic Info
  • Host: GitHub
  • Owner: altunenes
  • License: gpl-3.0
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 16.1 MB
Statistics
  • Stars: 7
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Archived
Topics
dlib face mediapipe neuroscience-methods opencv part-whole psychology
Created over 5 years ago · Last pushed over 4 years ago
Metadata Files
Readme License Citation

README.md

CodeFactor

Update for Media Pipe

Since dlib library is getting older, I edited main code and apply with the Media Pipe library. It's faster than dlib but I don't think it giving better results. I added faces that are processed with media pipe, so try both; and use the best result :)

Slayt1

Part-Whole

Swap facial landmarks for the part-whole task

The part-whole task is a well-known task among face researchers especially studying face processing. It has been developed by (Tanaka & Farah, 1993) https://doi.org/10.1080/14640749308401045.

This script provides you a realistic results with seamlessClone function.

In order to get clear results, use high-quality images as much as possible. But if you have low-quality faces you probably need to use some extra filter methods to edges (Gaussian is working well in most scenarios).

Referance for the trained detector: https://github.com/codeniko/shapepredictor81facelandmarks

Example for facial parts:

New Microsoft PowerPoint Presentation

(the leftmost is nose+mouth) TEST

testttt

Faces from: https://thispersondoesnotexist.com/

Owner

  • Name: Enes
  • Login: altunenes
  • Kind: user

I like science, computers, and budgies :-)

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this code, please cite it as below."
authors:
- family-names: "Altun"
  given-names: "Enes"
  orcid: "https://orcid.org/0000-0002-6478-6909"
title: "Part-Whole"
version: 1.0.0
date-released: 2021-08-24
url: "https://github.com/emportent/Part-Whole"

GitHub Events

Total
  • Watch event: 1
Last Year
  • Watch event: 1

Dependencies

requirements.txt pypi
  • dlib *
  • mediapipe *
  • numpy *
  • opencv-python *