These images represent four steps in one computer political program ’s advancement towards repair the Mona Lisa using only 50 semi - transparent polygons . Swedish computer programmer Roger Alsing did this simple weekend project with inherited programming that resulted in a program that could generate , on its own , a pretty awe-inspiring likeness of the famous painting . So how did he do it ?
He wrote a program that would randomly localise shapes on a black background , and make up one’s mind whether the nonobjective pattern attend more or less like the famous picture . After almost a million endeavor , the programme ’s output had develop to the distributor point where Alsing had the figure of speech on the far right hand .
How does this simple programme work ? Alsing explains :
The procedure of the program is quite simple :
0 ) Setup a random DNA string ( software start )
1 ) Copy the current DNA successiveness and mutate it slightly
2 ) employ the Modern DNA to render polygons onto a canvas
3 ) Compare the canvass to the source image
4 ) If the new house painting looks more like the root image than the previous picture did , then overwrite the current desoxyribonucleic acid with the raw desoxyribonucleic acid
5 ) repeat from 1
He alsoincludes reference codefor those who wish to turn over further . Though he ’s had some argument with commenters on his blog as to whether this bet as pure evolutionary scheduling , he argues that it is because the platform has to mutate each clock time it finds an image that ’s unaired to the Mona Lisa . Luckily Sarah Connor is n’t around , because she ’d have this guy ’s ass in a sling .
Genetic Programming : Evolution of Mona Lisa[via Roger Alsing ’s web log ]
ComputerssoftwareTechnology
Daily Newsletter
Get the good tech , scientific discipline , and culture word in your inbox daily .
News from the future , fork out to your nowadays .
You May Also Like
