user528322
user528322

Reputation: 109

Facecrop with openimaj

Crop an MBFImage

I detect a face using the superb openimaj library 1.3.8 but i struggle crop the face from the original image and save the cropped face to some file. The cropped faces must be in 800x600 px so i need some scaling as well.

It must be a simple task but the api is huge and i dont find a tutorial that fits this usecase

Maybe you show me where i can find information?

import java.io.File;
import java.io.IOException;
import java.util.Iterator;
import java.util.List;

import org.openimaj.image.DisplayUtilities;
import org.openimaj.image.FImage;
import org.openimaj.image.ImageUtilities;
import org.openimaj.image.MBFImage;
import org.openimaj.image.colour.RGBColour;
import org.openimaj.image.colour.Transforms;
import org.openimaj.image.processing.face.detection.DetectedFace;
import org.openimaj.image.processing.face.detection.FaceDetector;
import org.openimaj.image.processing.face.detection.HaarCascadeDetector;
import org.openimaj.math.geometry.shape.Rectangle;


public class App {
    public static void main(String[] args) throws Exception, IOException {


        final MBFImage image = ImageUtilities.readMBF(new File("d:\\java\\face\\bin.jpeg"));

        FaceDetector<DetectedFace, FImage> fd = new HaarCascadeDetector(200);
        List<DetectedFace> faces = fd.detectFaces(Transforms.calculateIntensity(image));
        System.out.println("# Found faces, one per line.");
        System.out.println("# <x>, <y>, <width>, <height>");

        for (Iterator<DetectedFace> iterator = faces.iterator(); iterator.hasNext();) {
            DetectedFace face = iterator.next();
            Rectangle bounds = face.getBounds();

            image.drawShape(face.getBounds(), RGBColour.RED);

            // System.out.println(bounds.x + ";" + bounds.y + ";" + bounds.width + ";" +
            // bounds.height);

        }

        DisplayUtilities.display(image);

    }
}

Upvotes: 0

Views: 309

Answers (1)

user528322
user528322

Reputation: 109

solved

        DetectedFace face = iterator.next();
        Rectangle bounds = face.getBounds();

        Point2d center = bounds.calculateCentroid();

        // image.drawShape(bounds, RGBColour.RED);

        // auf 800 x 600 bringen

        float b = (bounds.width * 800) / 600;

        MBFImage crop = image.extractCenter(
                (int) center.getX() , 
                (int) center.getY()  ,
                (int) bounds.width , 
                (int) b  ) ;


        ResizeProcessor resize = new ResizeProcessor(800,600);
        MBFImage small = crop.processInplace(resize);

        DisplayUtilities.display(small);

Upvotes: 0

Related Questions