User:Alexander Roidl/algorithmicthesis: Difference between revisions

From XPUB & Lens-Based wiki
(Created page with "Set of experiments on generating the thesis topic by a set of rules / with a game. 1. Method: Print | What: Collection | Action: transform There is a huge collection of imag...")
 
No edit summary
Line 6: Line 6:
It is an attempt to classify and categories images into a huge database
It is an attempt to classify and categories images into a huge database


Cloud
I picked a random set of images:
 
1399         95.15%
 
pictures Popularity Percentile


Clouds & sky | 1399 pictures


A visible mass of water or ice particles suspended at a considerable altitude  
A visible mass of water or ice particles suspended at a considerable altitude  
Line 17: Line 14:
[[File:Screen Shot 2018-10-10 at 16.32.48.png|thumbnail]]
[[File:Screen Shot 2018-10-10 at 16.32.48.png|thumbnail]]
[[File:Screen Shot 2018-10-10 at 16.34.05.png|thumbnail]]
[[File:Screen Shot 2018-10-10 at 16.34.05.png|thumbnail]]
[[File:20181010 162612.jpg|thumbnail]]
Interestingly the set also features some cloudy explosions.
So I decided to run it through a image detection software.
As I result I figured out that the software would predict quite similar values.
[[File:Screen Shot 2018-10-10 at 16.36.49.png|500px|frameless]]
This is interesting as in my personal (human) opinion these images feature
radical different objects.

Revision as of 16:49, 10 October 2018

Set of experiments on generating the thesis topic by a set of rules / with a game.

1. Method: Print | What: Collection | Action: transform

There is a huge collection of images on http://image-net.org/ It is an attempt to classify and categories images into a huge database

I picked a random set of images:

Clouds & sky | 1399 pictures

A visible mass of water or ice particles suspended at a considerable altitude

Screen Shot 2018-10-10 at 16.32.48.png
Screen Shot 2018-10-10 at 16.34.05.png
20181010 162612.jpg

Interestingly the set also features some cloudy explosions.

So I decided to run it through a image detection software. As I result I figured out that the software would predict quite similar values.

Screen Shot 2018-10-10 at 16.36.49.png

This is interesting as in my personal (human) opinion these images feature radical different objects.