Perspective Transform + Crop in iOS with OpenCV

Question

I\'m trying to implement a cropping & perspective correction feature into an upcoming app. Whilst doing research, I came across:

Executing cv::warpPerspective f

Answer 1

I think the point correspondence in getAffineTransform is incorrect.

Check the point coordinates output by box.points(pts);

Why not just use p1 p2 p3 p4 to calculate the transformation?

Answer 2

So after a few days of trying to solve it, I came up with a solution (Ignore the blue dots on the second image):

As promised, here's a complete copy of the code:

- (void)confirmedImage
{
    cv::Mat originalRot = [self cvMatFromUIImage:_sourceImage];
    cv::Mat original;
    cv::transpose(originalRot, original);

    originalRot.release();

    cv::flip(original, original, 1);


    CGFloat scaleFactor =  [_sourceImageView contentScale];

    CGPoint ptBottomLeft = [_adjustRect coordinatesForPoint:1 withScaleFactor:scaleFactor];
    CGPoint ptBottomRight = [_adjustRect coordinatesForPoint:2 withScaleFactor:scaleFactor];
    CGPoint ptTopRight = [_adjustRect coordinatesForPoint:3 withScaleFactor:scaleFactor];
    CGPoint ptTopLeft = [_adjustRect coordinatesForPoint:4 withScaleFactor:scaleFactor];

    CGFloat w1 = sqrt( pow(ptBottomRight.x - ptBottomLeft.x , 2) + pow(ptBottomRight.x - ptBottomLeft.x, 2));
    CGFloat w2 = sqrt( pow(ptTopRight.x - ptTopLeft.x , 2) + pow(ptTopRight.x - ptTopLeft.x, 2));

    CGFloat h1 = sqrt( pow(ptTopRight.y - ptBottomRight.y , 2) + pow(ptTopRight.y - ptBottomRight.y, 2));
    CGFloat h2 = sqrt( pow(ptTopLeft.y - ptBottomLeft.y , 2) + pow(ptTopLeft.y - ptBottomLeft.y, 2));

    CGFloat maxWidth = (w1 < w2) ? w1 : w2;
    CGFloat maxHeight = (h1 < h2) ? h1 : h2;

    cv::Point2f src[4], dst[4];
    src[0].x = ptTopLeft.x;
    src[0].y = ptTopLeft.y;
    src[1].x = ptTopRight.x;
    src[1].y = ptTopRight.y;
    src[2].x = ptBottomRight.x;
    src[2].y = ptBottomRight.y;
    src[3].x = ptBottomLeft.x;
    src[3].y = ptBottomLeft.y;

    dst[0].x = 0;
    dst[0].y = 0;
    dst[1].x = maxWidth - 1;
    dst[1].y = 0;
    dst[2].x = maxWidth - 1;
    dst[2].y = maxHeight - 1;
    dst[3].x = 0;
    dst[3].y = maxHeight - 1;

    cv::Mat undistorted = cv::Mat( cvSize(maxWidth,maxHeight), CV_8UC1);
    cv::warpPerspective(original, undistorted, cv::getPerspectiveTransform(src, dst), cvSize(maxWidth, maxHeight));

    UIImage *newImage = [self UIImageFromCVMat:undistorted];

    undistorted.release();
    original.release();

    [_sourceImageView setNeedsDisplay];
    [_sourceImageView setImage:newImage];
    [_sourceImageView setContentMode:UIViewContentModeScaleAspectFit];

}

- (UIImage *)UIImageFromCVMat:(cv::Mat)cvMat
{
    NSData *data = [NSData dataWithBytes:cvMat.data length:cvMat.elemSize() * cvMat.total()];

    CGColorSpaceRef colorSpace;

    if (cvMat.elemSize() == 1) {
        colorSpace = CGColorSpaceCreateDeviceGray();
    } else {
        colorSpace = CGColorSpaceCreateDeviceRGB();
    }

    CGDataProviderRef provider = CGDataProviderCreateWithCFData((__bridge CFDataRef)data);

    CGImageRef imageRef = CGImageCreate(cvMat.cols,                                     // Width
                                        cvMat.rows,                                     // Height
                                        8,                                              // Bits per component
                                        8 * cvMat.elemSize(),                           // Bits per pixel
                                        cvMat.step[0],                                  // Bytes per row
                                        colorSpace,                                     // Colorspace
                                        kCGImageAlphaNone | kCGBitmapByteOrderDefault,  // Bitmap info flags
                                        provider,                                       // CGDataProviderRef
                                        NULL,                                           // Decode
                                        false,                                          // Should interpolate
                                        kCGRenderingIntentDefault);                     // Intent

    UIImage *image = [[UIImage alloc] initWithCGImage:imageRef];
    CGImageRelease(imageRef);
    CGDataProviderRelease(provider);
    CGColorSpaceRelease(colorSpace);

    return image;
}

- (cv::Mat)cvMatFromUIImage:(UIImage *)image
{
    CGColorSpaceRef colorSpace = CGImageGetColorSpace(image.CGImage);
    CGFloat cols = image.size.height;
    CGFloat rows = image.size.width;

    cv::Mat cvMat(rows, cols, CV_8UC4); // 8 bits per component, 4 channels

    CGContextRef contextRef = CGBitmapContextCreate(cvMat.data,                 // Pointer to backing data
                                                    cols,                       // Width of bitmap
                                                    rows,                       // Height of bitmap
                                                    8,                          // Bits per component
                                                    cvMat.step[0],              // Bytes per row
                                                    colorSpace,                 // Colorspace
                                                    kCGImageAlphaNoneSkipLast |
                                                    kCGBitmapByteOrderDefault); // Bitmap info flags

    CGContextDrawImage(contextRef, CGRectMake(0, 0, cols, rows), image.CGImage);
    CGContextRelease(contextRef);

    return cvMat;
}

Hope it helps you + happy coding!