flat assembler
Message board for the users of flat assembler.

Index > Heap > is writing a facial recognition software equal to AI

Author
Thread Post new topic Reply to topic
sleepsleep



Joined: 05 Oct 2006
Posts: 8897
Location: ˛                             ⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣Posts: 334455
sleepsleep
somehow, this struck me a moment ago,
is writing a facial recognition software that able to fast check through images equal to writing some sort of highly intelligent AI?

if you use google images search by using image, it could perform something like finding relevant images, which is quite awesome!, as if there is a person there getting you list of equal or roughly equal images.

the result is so so, i wonder if some bots start tag tons series of pictures into un-relevant tag, what would be the result?

could the AI understand those images that purposely with corrupted tag or it needs programmers to correct and inform it?

or AI that able to recognizes any kinda of location,
coding it is like trying to code a human...
Post 25 Jul 2014, 15:02
View user's profile Send private message Reply with quote
AsmGuru62



Joined: 28 Jan 2004
Posts: 1409
Location: Toronto, Canada
AsmGuru62
I think facial recognition is just a comparison of geometry of a facial points.
So, basically, it is like comparing the set of numbers/angles and calculating the percentage of a match to a 2nd set of numbers.
Not sure if you need a lot of AI here. Like spell checking.
Post 25 Jul 2014, 17:06
View user's profile Send private message Send e-mail Reply with quote
sleepsleep



Joined: 05 Oct 2006
Posts: 8897
Location: ˛                             ⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣⁣Posts: 334455
sleepsleep
thanks, AsmGuru62
i will read and google more.
Post 26 Jul 2014, 05:52
View user's profile Send private message Reply with quote
AsmGuru62



Joined: 28 Jan 2004
Posts: 1409
Location: Toronto, Canada
AsmGuru62
Now, that I think more about it - a part of that software is also the image processing code.
It suppose to determine the facial points (geometry) from an image of a face.
So, this part is much more complex that just comparing the values.
By looking at the pixels in an image the code should determine the locations of
facial details, nose, its width, eyes and distance between them, ears, etc.
I think this is much more complex than the solution I was thinking about.
Or maybe operator can just do it by clicking on an image - I do not know.
Post 26 Jul 2014, 13:29
View user's profile Send private message Send e-mail Reply with quote
Display posts from previous:
Post new topic Reply to topic

Jump to:  


< Last Thread | Next Thread >
Forum Rules:
You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot vote in polls in this forum
You can attach files in this forum
You can download files in this forum


Copyright © 1999-2020, Tomasz Grysztar.

Powered by rwasa.