Using OpenCV to make a face divider through a camera

jncunha

Using OpenCV to make a face divider through a camera

in Contributed Library Questions • 2 years ago

Hi.

The title must be confusing but I'm making a small Processing project for my University.

The idea is that people put their faces in front of a camera, make an expression and, as long as the face of that person is centered, the next one comes and does the same. The result is a image divided with half the face of each person. Note: it doesn't matter that the heads are not the same size. The global effect is what matters.

So, my problem is that I need to have a way for people to choose their "face position" and then they'd have to hit/click something to save their half-face on a side of the screen. The question is that I really don't know how to do this.

I've already downloaded and installed OpenCV which seems to be the library that will help me more but yet I don't have Processing knowledge to do this without a help at the beginning.

Any ideas where to start :P? The project looks pretty simple for the things I've seen Processing doing. At the end it would be nice to export to a image file the result of the two "half-images" and show the mixture on a second screen for the audience to see.

Thank you.

Replies(1)

jncunha

Re: Using OpenCV to make a face divider through a camera

2 years ago

So, I guess the first explanation was too vague so I'm updating the situation with the work already done and the problems I've found.

Here's the code:

import hypermedia.video.*;
OpenCV opencv;
int i=0;
void setup()
{
size(640,700);
opencv = new OpenCV(this);
opencv.capture(320,240);
}
void draw()
{
opencv.read();
image(opencv.image(),0,0);
}
void keyPressed()
{
i=i+1;
println(i);
image(opencv.image(OpenCV.MEMORY),320,0);
opencv.remember(); // store the actual image in memory
if(i%2==0)
{
copy(320,0,160,240,70,300,230,350);
}
else
{
copy(480,0,160,240,305,300,230,350);
}
}

So, this thing is actually working very close to what I want. The problem is that when we press a key to "make it work, it first shows what is already saved in memory (black because it's the first input in the program) but it also saves to memory what the camera is seeing at that key press. This causes a problem because what I wanted was to press the key, copy a half down and then press again with the face in a new position or with another person, and then, after that key press, the other half completes the face.

I'm a really newbie in Processing so I believe you'll find that my program, is not the best thing to do what I'm trying to do.

The other part of the program that is missing is that, when the image is completed with the 2 half's, it would be great to export a jpeg or something like that with the result to a folder. The problem is that I really don't know how to do that :P.

A little help would be kindly appreciated.

Thank you.

Top Reply