https://github.com/davidemodolo/imagemorphingsiv
Jupyter Notebook and more for Image Morphing project of SIV course (UNITN)
https://github.com/davidemodolo/imagemorphingsiv
affine-transformation fading image-morphing morphing signals
Last synced: 2 months ago
JSON representation
Jupyter Notebook and more for Image Morphing project of SIV course (UNITN)
- Host: GitHub
- URL: https://github.com/davidemodolo/imagemorphingsiv
- Owner: davidemodolo
- Created: 2022-04-05T21:15:57.000Z (about 3 years ago)
- Default Branch: main
- Last Pushed: 2022-05-24T12:30:02.000Z (almost 3 years ago)
- Last Synced: 2025-03-11T09:50:45.860Z (2 months ago)
- Topics: affine-transformation, fading, image-morphing, morphing, signals
- Language: Jupyter Notebook
- Homepage:
- Size: 69.2 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Image Morphing - SIV Project
by Davide Modolo
## Presentation
The [presentation](https://docs.google.com/presentation/d/1DMnK3zVJN2qQJb5nfwMydtcnt2dF2MUdNUQ3A90HNE4/edit?usp=sharing) aims to explain what is Image Morphing and what is it used for. It also explains how our notebook works.
## Jupyter Notebook
### resize.py
Since functions we use require two images of the same size, we wrote a library that edit one or both of them with a minimum (to none) information loss.
### Fading
We started explaining the easier approach to image morphing: the Fading Effect. It requires two Pillow Images
### Morphing Function
Function to compute the affine transformation steps. It requires two images as numpy array.
### Point-picking
Function to pick by hand three points in each image in order to perform the morph. It requires two images as numpy array.
### Autopick by Template-matching
Look for 3 high-similarity points and morph on them. It requires two images as numpy array.
### Face detection
Using DLIB library and shape_predictor_68_face_landmarks.dat to recognise faces in images and morph. It requires two images as numpy array.
It requires shape_predictor_68_face_landmarks.dat file taken from [here](http://dlib.net/files/shape_predictor_68_face_landmarks.dat.bz2)
Faces are taken from [This Person Does Not Exist](https://this-person-does-not-exist.com/)
## Anaconda Environment
Since DLIB can easly bring errors, this environment ensures everything works.