Predefined: My A4 sheet will always be of white color.
I need to detect A4 sheet from image. I am able to detect rectangles, now the problem is I am getting multiple rectangles from my image. So I extracted the images from the detected rectangle points.
Now I want to match image color with white color.
Using below method to extract image from contours detected :
- (cv::Mat) getPaperAreaFromImage: (std::vector<cv::Point>) square, cv::Mat image
{
// declare used vars
int paperWidth = 210; // in mm, because scale factor is taken into account
int paperHeight = 297; // in mm, because scale factor is taken into account
cv::Point2f imageVertices[4];
float distanceP1P2;
float distanceP1P3;
BOOL isLandscape = true;
int scaleFactor;
cv::Mat paperImage;
cv::Mat paperImageCorrected;
cv::Point2f paperVertices[4];
// sort square corners for further operations
square = sortSquarePointsClockwise( square );
// rearrange to get proper order for getPerspectiveTransform()
imageVertices[0] = square[0];
imageVertices[1] = square[1];
imageVertices[2] = square[3];
imageVertices[3] = square[2];
// get distance between corner points for further operations
distanceP1P2 = distanceBetweenPoints( imageVertices[0], imageVertices[1] );
distanceP1P3 = distanceBetweenPoints( imageVertices[0], imageVertices[2] );
// calc paper, paperVertices; take orientation into account
if ( distanceP1P2 > distanceP1P3 ) {
scaleFactor = ceil( lroundf(distanceP1P2/paperHeight) ); // we always want to scale the image down to maintain the best quality possible
paperImage = cv::Mat( paperWidth*scaleFactor, paperHeight*scaleFactor, CV_8UC3 );
paperVertices[0] = cv::Point( 0, 0 );
paperVertices[1] = cv::Point( paperHeight*scaleFactor, 0 );
paperVertices[2] = cv::Point( 0, paperWidth*scaleFactor );
paperVertices[3] = cv::Point( paperHeight*scaleFactor, paperWidth*scaleFactor );
}
else {
isLandscape = false;
scaleFactor = ceil( lroundf(distanceP1P3/paperHeight) ); // we always want to scale the image down to maintain the best quality possible
paperImage = cv::Mat( paperHeight*scaleFactor, paperWidth*scaleFactor, CV_8UC3 );
paperVertices[0] = cv::Point( 0, 0 );
paperVertices[1] = cv::Point( paperWidth*scaleFactor, 0 );
paperVertices[2] = cv::Point( 0, paperHeight*scaleFactor );
paperVertices[3] = cv::Point( paperWidth*scaleFactor, paperHeight*scaleFactor );
}
cv::Mat warpMatrix = getPerspectiveTransform( imageVertices, paperVertices );
cv::warpPerspective(image, paperImage, warpMatrix, paperImage.size(), cv::INTER_LINEAR, cv::BORDER_CONSTANT );
if (true) {
cv::Rect rect = boundingRect(cv::Mat(square));
cv::rectangle(image, rect.tl(), rect.br(), cv::Scalar(0,255,0), 5, 8, 0);
UIImage *object = [self UIImageFromCVMat:paperImage];
}
// we want portrait output
if ( isLandscape ) {
cv::transpose(paperImage, paperImageCorrected);
cv::flip(paperImageCorrected, paperImageCorrected, 1);
return paperImageCorrected;
}
return paperImage;
}
EDITED: I used below method to get the color from image. But now my problem after converting my original image to cv::mat, when I am cropping there is already transparent grey color over my image. So always I am getting the same color.
Is there any direct way to get original color from cv::mat image?
- (UIColor *)averageColor: (UIImage *) image {
CGColorSpaceRef colorSpace = CGColorSpaceCreateDeviceRGB();
unsigned char rgba[4];
CGContextRef context = CGBitmapContextCreate(rgba, 1, 1, 8, 4, colorSpace, kCGImageAlphaPremultipliedLast | kCGBitmapByteOrder32Big);
CGContextDrawImage(context, CGRectMake(0, 0, 1, 1), image.CGImage);
CGColorSpaceRelease(colorSpace);
CGContextRelease(context);
if(rgba[3] > 0) {
CGFloat alpha = ((CGFloat)rgba[3])/255.0;
CGFloat multiplier = alpha/255.0;
return [UIColor colorWithRed:((CGFloat)rgba[0])*multiplier
green:((CGFloat)rgba[1])*multiplier
blue:((CGFloat)rgba[2])*multiplier
alpha:alpha];
}
else {
return [UIColor colorWithRed:((CGFloat)rgba[0])/255.0
green:((CGFloat)rgba[1])/255.0
blue:((CGFloat)rgba[2])/255.0
alpha:((CGFloat)rgba[3])/255.0];
}
}
EDIT 2 :
Input Image
Getting this output
Need to detect only A4 sheet of white color.
I just resolved it using Google Vision api.
My objective was to calculate the cracks for builder purpose from image so in my case User will be using A4 sheet as reference on the image where crack is, and I will capture the A4 sheet and calculate the size taken by each pixel. Then build will tap on two points in the crack, and I will calculate the distance.
In google vision I used document text detection api and printed my app name on A4 sheet fully covered vertically or horizontally. And google vision api detect that text and gives me the coordinate.
Related
I am doing a background subtraction capture demo recently but I met with difficulties. I have already get the pixel of silhouette extraction and I intend to draw it into a buffer through createGraphics(). I set the new background is 100% transparent so that I could only get the foreground extraction. Then I use saveFrame() function in order to get png file of each frame. However, it doesn't work as I expected. I intend to get a series of png of the silhouette extraction
with 100% transparent background but now I only get the general png of frames from the camera feed. Is there anyone could help me to see what's the problem with this code? Thanks a lot in advance. Any help will be appreciated.
import processing.video.*;
Capture video;
PGraphics pg;
PImage backgroundImage;
float threshold = 30;
void setup() {
size(320, 240);
video = new Capture(this, width, height);
video.start();
backgroundImage = createImage(video.width, video.height, RGB);
pg = createGraphics(320, 240);
}
void captureEvent(Capture video) {
video.read();
}
void draw() {
pg.beginDraw();
loadPixels();
video.loadPixels();
backgroundImage.loadPixels();
image(video, 0, 0);
for (int x = 0; x < video.width; x++) {
for (int y = 0; y < video.height; y++) {
int loc = x + y * video.width;
color fgColor = video.pixels[loc];
color bgColor = backgroundImage.pixels[loc];
float r1 = red(fgColor); float g1 = green(fgColor); float b1 = blue(fgColor);
float r2 = red(bgColor); float g2 = green(bgColor); float b2 = blue(bgColor);
float diff = dist(r1, g1, b1, r2, g2, b2);
if (diff > threshold) {
pixels[loc] = fgColor;
} else {
pixels[loc] = color(0, 0);
}
}}
pg.updatePixels();
pg.endDraw();
saveFrame("line-######.png");
}
void mousePressed() {
backgroundImage.copy(video, 0, 0, video.width, video.height, 0, 0, video.width, video.height);
backgroundImage.updatePixels();
}
Re:
Then I use saveFrame() function in order to get png file of each frame. However, it doesn't work as I expected. I intend to get a series of png of the silhouette extraction with 100% transparent background but now I only get the general png of frames from the camera feed.
This won't work, because saveFrame() saves the canvas, and the canvas doesn't support transparency. For example, from the reference:
It is not possible to use the transparency alpha parameter with background colors on the main drawing surface. It can only be used along with a PGraphics object and createGraphics(). https://processing.org/reference/background_.html
If you want to dump a frame with transparency you need to use .save() to dump it directly from a PImage / PGraphics.
https://processing.org/reference/PImage_save_.html
If you need to clear your PImage / PGraphics and reuse it each frame, either use pg.clear() or pg.background(0,0,0,0) (set all pixels to transparent black).
I am trying to implement something similar to this using openCV
https://mathematica.stackexchange.com/questions/19546/image-processing-floor-plan-detecting-rooms-borders-area-and-room-names-t
However, I am running into some walls (probably due to my own ignorance in working with OpenCV).
When I try to perform a distance transform on my image, I am not getting the expected result at all.
This is the original image I am working with
This is the image I get after doing some cleanup with opencv
This is the wierdness I get after trying to run a distance transform on the above image. My understanding is that this should look more like a blurry heatmap. If I follow the opencv example passed this point and try to run a threshold to find the distance peaks, I get nothing but a black image.
This is the code thus far that I have cobbled together using a few different opencv examples
cv::Mat outerBox = cv::Mat(matImage.size(), CV_8UC1);
cv::Mat kernel = (cv::Mat_<uchar>(3,3) << 0,1,0,1,1,1,0,1,0);
for(int x = 0; x < 3; x++) {
cv::GaussianBlur(matImage, matImage, cv::Size(11,11), 0);
cv::adaptiveThreshold(matImage, outerBox, 255, cv::ADAPTIVE_THRESH_MEAN_C, cv::THRESH_BINARY, 5, 2);
cv::bitwise_not(outerBox, outerBox);
cv::dilate(outerBox, outerBox, kernel);
cv::dilate(outerBox, outerBox, kernel);
removeBlobs(outerBox, 1);
erode(outerBox, outerBox, kernel);
}
cv::Mat dist;
cv::bitwise_not(outerBox, outerBox);
distanceTransform(outerBox, dist, cv::DIST_L2, 5);
// Normalize the distance image for range = {0.0, 1.0}
// so we can visualize and threshold it
normalize(dist, dist, 0, 1., cv::NORM_MINMAX);
//using a threshold at this point like the opencv example shows to find peaks just returns a black image right now
//threshold(dist, dist, .4, 1., CV_THRESH_BINARY);
//cv::Mat kernel1 = cv::Mat::ones(3, 3, CV_8UC1);
//dilate(dist, dist, kernel1);
self.mainImage.image = [UIImage fromCVMat:outerBox];
void removeBlobs(cv::Mat &outerBox, int iterations) {
int count=0;
int max=-1;
cv::Point maxPt;
for(int iteration = 0; iteration < iterations; iteration++) {
for(int y=0;y<outerBox.size().height;y++)
{
uchar *row = outerBox.ptr(y);
for(int x=0;x<outerBox.size().width;x++)
{
if(row[x]>=128)
{
int area = floodFill(outerBox, cv::Point(x,y), CV_RGB(0,0,64));
if(area>max)
{
maxPt = cv::Point(x,y);
max = area;
}
}
}
}
floodFill(outerBox, maxPt, CV_RGB(255,255,255));
for(int y=0;y<outerBox.size().height;y++)
{
uchar *row = outerBox.ptr(y);
for(int x=0;x<outerBox.size().width;x++)
{
if(row[x]==64 && x!=maxPt.x && y!=maxPt.y)
{
int area = floodFill(outerBox, cv::Point(x,y), CV_RGB(0,0,0));
}
}
}
}
}
I've been banging my head on this for a few hours and I am totally stuck in the mud on it, so any help would be greatly appreciated. This is a little bit out of my depth, and I feel like I am probably just making some basic mistake somewhere without realizing it.
EDIT:
Using the same code as above running OpenCV for Mac (not iOS) I get the expected results
This seems to indicate that the issue is with the Mat -> UIImage bridging that OpenCV suggests using. I am going to push forward using the Mac library to test my code, but it would sure be nice to be able to get consistent results from the UIImage bridging as well.
+ (UIImage*)fromCVMat:(const cv::Mat&)cvMat
{
// (1) Construct the correct color space
CGColorSpaceRef colorSpace;
if ( cvMat.channels() == 1 ) {
colorSpace = CGColorSpaceCreateDeviceGray();
} else {
colorSpace = CGColorSpaceCreateDeviceRGB();
}
// (2) Create image data reference
CFDataRef data = CFDataCreate(kCFAllocatorDefault, cvMat.data, (cvMat.elemSize() * cvMat.total()));
// (3) Create CGImage from cv::Mat container
CGDataProviderRef provider = CGDataProviderCreateWithCFData(data);
CGImageRef imageRef = CGImageCreate(cvMat.cols,
cvMat.rows,
8,
8 * cvMat.elemSize(),
cvMat.step[0],
colorSpace,
kCGImageAlphaNone | kCGBitmapByteOrderDefault,
provider,
NULL,
false,
kCGRenderingIntentDefault);
// (4) Create UIImage from CGImage
UIImage * finalImage = [UIImage imageWithCGImage:imageRef];
// (5) Release the references
CGImageRelease(imageRef);
CGDataProviderRelease(provider);
CFRelease(data);
CGColorSpaceRelease(colorSpace);
// (6) Return the UIImage instance
return finalImage;
}
I worked out distance transform in OpenCV using python and I was able to obtain this:
You stated "I get nothing but a black image". Well I faced the same problem initially, until I converted the image to type int using: np.uint8(dist_transform)
I did something extra as well (you might/might not need it). In order to segment the rooms to a certain extent, I performed threshold on the distance transformed image. I got this as a result:
I have some
CGImageRef cgImage = "something"
Is there a way to manipulate the pixel values of this cgImage? For example if this image contains values between 0.0001 and 3000 thus when I try to view or release the image this way in an NSImageView (How can I show an image in a NSView using an CGImageRef image)
I get a black image, all pixels are black, I think it has to do with setting the pixel range values in a different color map (I don't know).
I want to be able to manipulate or change the pixel values or just be able to see the image by manipulating the color map range.
I have tried this but obviously it doesn't work:
CGContextDrawImage(ctx, CGRectMake(0,0, CGBitmapContextGetWidth(ctx),CGBitmapContextGetHeight(ctx)),cgImage);
UInt8 *data = CGBitmapContextGetData(ctx);
for (**all pixel values and i++ **) {
data[i] = **change to another value I want depending on the value in data[i]**;
}
Thank you,
In order to manipulate individual pixels in an image
allocate a buffer to hold the pixels
create a memory bitmap context using that buffer
draw the image into the context, which puts the pixels into the
buffer
change the pixels as desired
create a new image from the context
free up resources (note be sure to check for leaks using instruments)
Here's some sample code to get you started. This code will swap the blue and red components of each pixel.
- (CGImageRef)swapBlueAndRedInImage:(CGImageRef)image
{
int x, y;
uint8_t red, green, blue, alpha;
uint8_t *bufptr;
int width = CGImageGetWidth( image );
int height = CGImageGetHeight( image );
// allocate memory for pixels
uint32_t *pixels = calloc( width * height, sizeof(uint32_t) );
// create a context with RGBA pixels
CGColorSpaceRef colorSpace = CGColorSpaceCreateDeviceRGB();
CGContextRef context = CGBitmapContextCreate( pixels, width, height, 8, width * sizeof(uint32_t), colorSpace, kCGBitmapByteOrder32Little | kCGImageAlphaPremultipliedLast );
// draw the image into the context
CGContextDrawImage( context, CGRectMake( 0, 0, width, height ), image );
// manipulate the pixels
bufptr = (uint8_t *)pixels;
for ( y = 0; y < height; y++)
for ( x = 0; x < width; x++ )
{
red = bufptr[3];
green = bufptr[2];
blue = bufptr[1];
alpha = bufptr[0];
bufptr[1] = red; // swaps the red and blue
bufptr[3] = blue; // components of each pixel
bufptr += 4;
}
// create a new CGImage from the context with modified pixels
CGImageRef resultImage = CGBitmapContextCreateImage( context );
// release resources to free up memory
CGContextRelease( context );
CGColorSpaceRelease( colorSpace );
free( pixels );
return( resultImage );
}
I am trying to create a histogram of the depth videos (converted to grayscale first) in order to apply a threshold to keep only highest values, and then do some dilation in order to extract contours. Apparently I am stuck, and besides that i don't know if what I am thinking is the right way to extract contours from depth videos.
In the following code I got stuck in the point of applying the threshold. I think that iam applying it in the wrong way. Which is the correct to apply a threshold in this situation in order to obtain a black and white image?
Any suggestions or links of tutorials would be awesome!!!
Thank you very much!
int bins = 256;
int hsize[] = {bins};
//max and min value of the histogram
float max_value = 0, min_value = 0;
float value;
int normalized;
//ranges - grayscale 0 to 256
float xranges[] = { 0, 256 };
float* ranges[] = { xranges };
//image is the actual source from input depth video
gray = cvCreateImage( cvGetSize(image), 8, 1 );
cvCvtColor( image, gray, CV_BGR2GRAY );
cvNamedWindow("original",1);
cvNamedWindow("gray",1);
cvNamedWindow("histogram",1);
cvNamedWindow("black & white",1);
IplImage* planes[] = { gray };
//get the histogram and some info about it
hist = cvCreateHist( 1, hsize, CV_HIST_ARRAY, ranges,1);
cvCalcHist( planes, hist, 0, NULL);
cvGetMinMaxHistValue( hist, &min_value, &max_value);
printf("min: %f, max: %f\n", min_value, max_value);
imgHistogram = cvCreateImage(cvSize(bins, image->height),8,1);
cvRectangle(imgHistogram, cvPoint(0,0), cvPoint(256,image->height), CV_RGB(255,255,255),-1);
//I think that here i have messed up things :( Any suggestions ???
bw_img = cvCreateImage(cvGetSize(imgHistogram), IPL_DEPTH_8U, 1);
cvThreshold(imgHistogram, bw_img, 150, 255, CV_THRESH_BINARY);
//draw the histogram
for(int i=0; i < bins; i++){
value = cvQueryHistValue_1D( hist, i);
normalized = cvRound(value*image->height/max_value);
cvLine(imgHistogram,cvPoint(i,image->height), cvPoint(i,image->height-normalized), CV_RGB(0,0,0));
}
//show the image results
cvShowImage( "original", image );
cvShowImage( "gray", gray );
cvShowImage( "histogram", imgHistogram );
cvShowImage( "balck & white", bw_img);
I am trying to segment all shades of red form an image using hue saturation values and use InRangeS function to create a mask which should have all red areas whitened and all others blacked(a new 1 channel image). Thwn Inpaint them to kind of obscure the segmented portions.
My code is as given.
However I am unable to get an output image, it doesnt segment the desired color range.
Any pointers on my approach and why it isnt working. ?
int main(){
IplImage *img1=cvLoadImage("/home/techrascal/projects/test1/image2.jpeg");
//IplImage *img3;
IplImage *imghsv;
IplImage *img4;
CvSize sz=cvGetSize(img1);
imghsv=cvCreateImage(sz,IPL_DEPTH_8U,3);
img4=cvCreateImage(sz,IPL_DEPTH_8U,1);
int width = img1->width;
int height = img1->height;
int bpp = img1->nChannels;
//int w=img4->width;
//int h=img4->height;
//int bn=img4->nChannels;
cvNamedWindow("original", 1);
cvNamedWindow("hsv",1);
cvNamedWindow("Blurred",1);
int r,g,b;
// create inpaint mask: img 4 will behave as mask
cvCvtColor(img1,imghsv,CV_BGR2HSV);
CvScalar hsv_min = cvScalar(0, 0, 0, 0);
CvScalar hsv_max = cvScalar(255, 0, 0, 0);
//cvShowImage("hsv",imghsv);
cvInRangeS( imghsv, hsv_min, hsv_max, img4 );
cvInpaint(img1, img4, img1, 3,CV_INPAINT_NS );
cvShowImage("Blurred",img1);
cvReleaseImage(&img1);
cvReleaseImage(&imghsv);
cvReleaseImage(&img4);
//cvReleaseImage(&img3);
char d=cvWaitKey(10000);
cvDestroyAllWindows();
return 0;}
Your code logic seems correct but you will definetely need to adjust your hsv range values
(hsv_min and hsv_max).
Read this detailed guide that show you hsv range defined in opencv
http://www.shervinemami.co.cc/colorConversion.html