Skip to content

In this repo I gathered everything I did for "Analysis of images and videos" subject of Data Science degree at UPV

Notifications You must be signed in to change notification settings

grlisa/ml-for-image-analysis

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Machine Learning for Image and Video Analysis

Hey there! I made this repo where I gathered everything I used for "Analysis of images and videos" subject in my fourth year of Data Science degree at UPV. It's got all my notes for studying the boring theoretical exam 🥱 and all the stuff I did to smash 💥 the practical evaluation. The bad news is that both the theoretical content and the comments in the Jupyter notebooks are in Spanish 🇪🇸💃🏽 since the subject was oficially taught in Spanish.

Although it's been almost two years since I finished my degree, I decided to upload this to my GitHub because I had a blast 🤩 with this subject and I'm still really into this field of study.

All code is in Python3 using mostly Numpy and Image from PIL. The purpose was to develop the methods "by hand" despite the fact that there are already optimized builtin functions in certain libraries that give the same results.

In Pract1 directory, you'll find the implementations I made for:

  • Parte1: Bright and contrast, Stretching, Ecualizer and Local Ecualizer
  • Parte2: Convolution, Contour detection filters (Sobel, Laplace, Roberts, Prewit)
  • Parte3: Thresholding (Otsu) and Connected Components
  • Parte4: Morphological Operators (Erosion, Dilation, Opening, Closing)
  • Ejercicio1:Use the above methods to calculate and draw Minimum Bounding Boxes for a given image.
  • Ejercicio2: Count the amount of coins on a given image using a combination of aforementioned methods.

About

In this repo I gathered everything I did for "Analysis of images and videos" subject of Data Science degree at UPV

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published