Develop Reference

Android openCV can`t IDFT back to orginal image

enter image description hereHello, i try to transform image from time domain to frequency domain by using opencv DFT() function, it works, but i can`t transform it back by using IDFT() function。
In my getIDFT() function , i get phase from dft complex and use polarToCart to get Re and Im Data, but something wrong with my image , can somebody help me , thanks.
Github : https://github.com/pighaddt/opencv_demo/tree/master/app/src
private Mat getIDFT(Mat DFTimage){
DFTimage.convertTo(DFTimage, CvType.CV_64FC1);
DFTimage = DFTShift(DFTimage);
Mat Re = new Mat(DFTimage.size(), CvType.CV_64FC1); // expand input image to optimal size
Mat Im = new Mat(DFTimage.size(), CvType.CV_64FC1); // expand input image to optimal size
Mat ph = new Mat(DFTimage.size(), CvType.CV_64FC1);
Core.phase(planes.get(0), planes.get(1), ph, false);
Core.polarToCart(DFTData, ph, Re, Im, false);
Mat complexI = Mat.zeros(Re.rows(), Re.cols(), CvType.CV_64FC2);
Mat complexI3 = Mat.zeros(Re.rows(), Re.cols(), CvType.CV_64FC2);
List<Mat> planesIDFT = new ArrayList<Mat>();
planesIDFT.add(Re);
planesIDFT.add(Im);
Core.merge(planesIDFT, complexI); // Add to the expanded another plane with zeros
Mat invDFTcvt = new Mat(Re.size(), CvType.CV_8UC1);
Core.idft(complexI, complexI3, Core.DFT_INVERSE | Core.DFT_COMPLEX_OUTPUT | Core.DFT_SCALE, 0);
Core.split(complexI3, planesIDFT); // planes[0] = Re(DFT(I)), planes[1] = Im(DFT(I))
Core.normalize(planesIDFT.get(0), invDFTcvt, 0, 255, Core.NORM_MINMAX);
invDFTcvt.convertTo(invDFTcvt, CvType.CV_8UC1);
isDFT = false;
return invDFTcvt;
}

Unexpected results in attempt to perform Image Alignment | Image Registeration | OpenCV | Android

I attempted to implement Image Alignment using OpenCV for android which worked on one of my test case but it failed to work on another test case.
Test Case #1 - for which my code worked:
Given two Images, like for example Scene Image and Object Image,
I want output object Image to be aligned to Scene Image. Check out the Final Output.
Test Case #2 - for which my code didn't worked:
Given Images, Scene Image and Object Image,
I got this feature matching result and this as my output to warpPerspective.
My question is, can anyone please tell me why I am unable to align Images in second test case.
Mat mObjectMat = new Mat();
Mat mSceneMat = new Mat();
Mat img3 = mSceneMat.clone();
//Bitmap to Mat
Utils.bitmapToMat(inputImage2, mObjectMat);
Utils.bitmapToMat(inputImage1, mSceneMat);
//rgb to gray
Imgproc.cvtColor(mObjectMat, mObjectMat, Imgproc.COLOR_RGBA2GRAY);
Imgproc.cvtColor(mSceneMat, mSceneMat, Imgproc.COLOR_RGBA2GRAY);
//find interest points/keypoints in an image
MatOfKeyPoint keypoints_object = new MatOfKeyPoint();
MatOfKeyPoint keypoints_scene = new MatOfKeyPoint();
FeatureDetector fd = FeatureDetector.create(FeatureDetector.ORB);
fd.detect(mObjectMat, keypoints_object);
fd.detect(mSceneMat, keypoints_scene);
//extract descriptor
Mat descriptors_object = new Mat();
Mat descriptors_scene = new Mat();
DescriptorExtractor extractor = DescriptorExtractor.create(DescriptorExtractor.ORB);
extractor.compute(mObjectMat, keypoints_object, descriptors_object);
extractor.compute(mSceneMat, keypoints_scene, descriptors_scene);
//match keypoint descriptors
MatOfDMatch matches = new MatOfDMatch();
DescriptorMatcher matcher = DescriptorMatcher.create(DescriptorMatcher.BRUTEFORCE_HAMMING);
matcher.match( descriptors_object, descriptors_scene, matches);
List<DMatch> matchesList = matches.toList();
//Calculate max and min distances between keypoints
matchesList = matches.toList();
Double maxDistance = 0.0;
Double minDistance = 100.0;
for( int i = 0; i < descriptors_object.rows(); i++ )
{
Double dist = (double) matchesList.get(i).distance;
if( dist < minDistance ) minDistance = dist;
if( dist > maxDistance ) maxDistance = dist;
}
//display
Toast.makeText(getApplicationContext(), "[ Max dist : " + maxDistance + " ] [ Min dist : " + minDistance + " ]", Toast.LENGTH_LONG).show();
//find good matches
LinkedList<DMatch> good_matches = new LinkedList<DMatch>();
MatOfDMatch gm = new MatOfDMatch();
//Draw only good matches
for(int i = 0; i < descriptors_object.rows(); i++){
if(matchesList.get(i).distance < 3*minDistance){
good_matches.addLast(matchesList.get(i));
}
}
gm.fromList(good_matches);
//display matches on imageView
Mat opt = new Mat();
Scalar RED = new Scalar(255,0,0);
Scalar GREEN = new Scalar(0,255,0);
MatOfByte drawnMatches = new MatOfByte();
Features2d.drawMatches(mObjectMat,keypoints_object,mSceneMat,keypoints_scene,gm,opt,GREEN, RED, drawnMatches, Features2d.NOT_DRAW_SINGLE_POINTS);
List<KeyPoint> keypoints_objectList = keypoints_object.toList();
List<KeyPoint> keypoints_sceneList = keypoints_scene.toList();
LinkedList<Point> objList = new LinkedList<Point>();
LinkedList<Point> sceneList = new LinkedList<Point>();
MatOfPoint2f obj = new MatOfPoint2f();
MatOfPoint2f scene = new MatOfPoint2f();
//Localize the object & find the keypoints from the good matches
//separate corresponding points for both images
for(int i = 0; i<good_matches.size(); i++){
objList.addLast(keypoints_objectList.get(good_matches.get(i).queryIdx).pt);
sceneList.addLast(keypoints_sceneList.get(good_matches.get(i).trainIdx).pt);
}
obj.fromList(objList);
scene.fromList(sceneList);
//Find homography - perspective transformation between two planes
Mat H = Calib3d.findHomography(obj, scene, Calib3d.RANSAC);
//perform perspective warp
Mat imgWarped = new Mat();
Imgproc.warpPerspective(mObjectMat, imgWarped, H, mSceneMat.size());
//warp and scene images
Mat finalImage = new Mat();
Core.add(mSceneMat, imgWarped,finalImage);
//add image to imageView
Bitmap imageMatched = Bitmap.createBitmap(finalImage.cols(), finalImage.rows(), Bitmap.Config.RGB_565);//need to save bitmap
Utils.matToBitmap(finalImage, imageMatched);
imageView1.setImageBitmap(imageMatched);

Android OpenCv people count

I am developing an Android application to count number of people in real time video. I used OpenCv to detect people but not finding a way to count them. If any one knows how to do it then please help me.
Here is the code to detect people in coming video frame
#Override
public Mat onCameraFrame(CameraBridgeViewBase.CvCameraViewFrame inputFrame) {
List<MatOfPoint> list = new ArrayList<>();
Mat frame = new Mat();
Mat gray = new Mat();
Mat hierarchy = new Mat();
Mat originalFrame = inputFrame.rgba();
Core.transpose(originalFrame,mRgbaT);
Imgproc.resize(mRgbaT,mRgbaF,mRgbaF.size(),0,0,0);
Core.flip(mRgbaF,originalFrame,1);
Imgproc.medianBlur(originalFrame,originalFrame,3);
Imgproc.cvtColor(originalFrame, gray, Imgproc.CV_BGR2GRAY, 0);
HOGDescriptor hog = new HOGDescriptor();
//Получаем стандартный определитель людей и устанавливаем его нашему дескриптору
MatOfFloat descriptors = HOGDescriptor.getDefaultPeopleDetector();
// MatOfFloat dfdfdf=HOGDescriptor.getDefaultPeopleDetector();
hog.setSVMDetector(descriptors);
MatOfRect locations = new MatOfRect();
MatOfDouble weights = new MatOfDouble();
hog.detectMultiScale(gray, locations, weights);
Point rectPoint1 = new Point();
Point rectPoint2 = new Point();
Point fontPoint = new Point();
if (locations.rows() > 0) {
List<Rect> rectangles = locations.toList();
for (Rect rect : rectangles) {
rectPoint1.x = rect.x;
rectPoint1.y = rect.y;
fontPoint.x = rect.x;
fontPoint.y = rect.y - 4;
rectPoint2.x = rect.x + rect.width;
rectPoint2.y = rect.y + rect.height;
final Scalar rectColor = new Scalar( 0 , 0 , 0 );
// Добавляем на изображения найденную информацию
Imgproc.rectangle(originalFrame, rectPoint1, rectPoint2, rectColor, 2);
}
}
frame.release();
gray.release();
hierarchy.release();
int i=list.size();
list.clear();
return originalFrame;
}

OpenCV Histogram Matching of Color Image

I am trying to write an Android App that performs histogram matching of color images using OpenCV3.1. I found this code example in C++, and converted it to java.
I tried to match each RGB chanel separately but it did not gave me the desired results. So now I'm converting the images to YUV color space and then match the Y chanels. What I hope to achieve is a brightnes matching, so if the source is brighter then the target I will get darker image.
So far it seems that the Y histogram of the final(output) image is somewhat close to the Y histogram of target image, but the actual output dosen't look like the target.
Here is the relevan code:
private Mat calculateLUT(Mat in_cdf_mat, Mat dst_cdf_mat) {
int last = 0;
double epsilon = Double.parseDouble(epsilonTextView.getText().toString());// epsilon set to 0.01
Mat M = new Mat(256, 1,CvType.CV_8UC1);
for(int j=0; j<in_cdf_mat.rows(); j++) {
double F1j = in_cdf_mat.get(j,0)[0];
for(int k = last; k < dst_cdf_mat.rows(); k++) {
double F2k = dst_cdf_mat.get(k,0)[0];
if(Math.abs(F2k - F1j) < epsilon || F2k > F1j) {
double[] data = {k} ;
M.put(j, 0, data);
last = k;
break;
}
}
}
return M;
}
private void calculateCDF (Mat channel, Mat cdf)
{
// channel holds the histogram. The indices represents the pixel color
// and the value is the amount of pixels of that color in the image
for (int i = 1; i < 256; i++) {
double[] data = new double[1];
data[0] = cdf.get(i-1,0)[0] + channel.get(i,0)[0];
cdf.put(i, 0, data);
}
}
private void calcHistogram(String imgPath, Mat y_hist, Mat y_cdf) {
Mat image;
Mat ycrcb = new Mat();
image = Imgcodecs.imread(imgPath);
Imgproc.cvtColor(image, ycrcb, Imgproc.COLOR_RGB2YCrCb);
image.release();
List<Mat> ycrcbChannels= new ArrayList<>();
Core.split(ycrcb,ycrcbChannels);
List<Mat> yList = new ArrayList<>();
yList.add(ycrcbChannels.get(0));
MatOfInt histSize = new MatOfInt(256);
MatOfFloat histRange = new MatOfFloat(0f, 256f);
Imgproc.calcHist(yList, new MatOfInt(0), new Mat(), y_hist, histSize, histRange, false);
Core.normalize(y_hist, y_hist, 3, 255, Core.NORM_MINMAX);
calculateCDF(y_hist, y_cdf);
Core.normalize(y_cdf, y_cdf, 3, 255, Core.NORM_MINMAX);
}
private void transformLight(Mat inputImage, Mat outputImage, Mat ylut) {
Mat imageYCrCb = new Mat();
Imgproc.cvtColor(inputImage, imageYCrCb, Imgproc.COLOR_RGB2YCrCb);
Mat y_chanel = new Mat();
Core.extractChannel(imageYCrCb, y_chanel, 0);
Mat cr_chanel = new Mat();
Core.extractChannel(imageYCrCb, cr_chanel, 1);
Mat cb_chanel = new Mat();
Core.extractChannel(imageYCrCb, cb_chanel, 2);
Core.LUT(y_chanel, ylut,y_chanel);
ArrayList<Mat> ycrcbDest = new ArrayList<>();
ycrcbDest.add(y_chanel);
ycrcbDest.add(cr_chanel);
ycrcbDest.add(cb_chanel);
Core.merge(ycrcbDest,outputImage);
Imgproc.cvtColor(outputImage, outputImage, Imgproc.COLOR_YCrCb2RGB);
}
private static void drawLine (Mat mat, int i, long bin_w, int hist_h, Mat histImage, Scalar color) {
// bin_w set to 1
Point p0 = new Point(bin_w * (i - 1), hist_h - Math.round(mat.get(i-1,0)[0]) );
Point p1 = new Point(bin_w * (i), hist_h - Math.round(mat.get(i,0)[0]) );
Imgproc.line(histImage, p0, p1, color, 5, 8, 0);
}
private void drawHistogram(Mat histImage, Mat graph, Scalar color) {
for (int i = 1; i < 256; i++) {
drawLine(graph, i, bin_w, histImage.rows(), histImage, color);
}
}
private void histNCDFtoFile(String filename, Mat hist, Mat cdf, Scalar histColor, Scalar cdfColor) {
Mat histImage = new Mat(256, 256, CvType.CV_8UC3);
drawHistogram(histImage, hist, histColor);
drawHistogram(histImage, cdf, cdfColor);
saveImage(filename, histImage);
}
private Mat matchHistograms(String input, String traget) {
Mat input_y_hist = new Mat();
Mat target_y_hist = new Mat();
calcHistogram(input, input_y_hist, input_y_cdf_mat);
histNCDFtoFile("inputHistNCDF.jpg", input_y_hist, input_y_cdf_mat, inputHistColor, inputCDFColor);
calcHistogram(traget, target_y_hist, target_y_cdf_mat);
histNCDFtoFile("targetHistNCDF.jpg", target_y_hist, target_y_cdf_mat, targetHistColor, targetCDFColor);
Mat ylut = calculateLUT(input_y_cdf_mat, target_y_cdf_mat);
Mat image;
Mat dst = new Mat(); // this Matrix will hold the transformed image
image = Imgcodecs.imread(input);
transformLight(image, dst, ylut);
return dst;
}
Here is an exmaple image from pixabay that I want to transform:
And this is the image that I use as a target:
And this is the result:
The CDF of the result and the target is here:
The light green is the target CDF and the light blue is the result CDF

Performance Issues in OpenCV for Android Keypoint Matching and threshold using ORB and RANSAC

I recently started developing an app on Android studio and I just finished writing the code. The accuracy which I get is more than satisfactory but the time taken by the device is a lot. {}I followed some tutorials on how to monitor the performance on android studio and I saw that one small part of my code is taking 6 seconds, which half the time my app takes to display the entire result. I have seen a lot of posts Java OpenCV - extracting good matches from knnMatch , OpenCV filtering ORB matches on OpenCV/JavaCV but haven't come across anyone asking for this problem. The OpenCV link http://docs.opencv.org/2.4/doc/tutorials/features2d/feature_homography/feature_homography.html does provide a good tutorial but the RANSAC function in OpenCV takes different arguments for keypoints as compared to C++.
Here is my code
public Mat ORB_detection (Mat Scene_image, Mat Object_image){
/*This function is used to find the reference card in the captured image with the help of
* the reference card saved in the application
* Inputs - Captured image (Scene_image), Reference Image (Object_image)*/
FeatureDetector orb = FeatureDetector.create(FeatureDetector.DYNAMIC_ORB);
/*1.a Keypoint Detection for Scene Image*/
//convert input to grayscale
channels = new ArrayList<Mat>(3);
Core.split(Scene_image, channels);
Scene_image = channels.get(0);
//Sharpen the image
Scene_image = unsharpMask(Scene_image);
MatOfKeyPoint keypoint_scene = new MatOfKeyPoint();
//Convert image to eight bit, unsigned char
Scene_image.convertTo(Scene_image, CvType.CV_8UC1);
orb.detect(Scene_image, keypoint_scene);
channels.clear();
/*1.b Keypoint Detection for Object image*/
//convert input to grayscale
Core.split(Object_image,channels);
Object_image = channels.get(0);
channels.clear();
MatOfKeyPoint keypoint_object = new MatOfKeyPoint();
Object_image.convertTo(Object_image, CvType.CV_8UC1);
orb.detect(Object_image, keypoint_object);
//2. Calculate the descriptors/feature vectors
//Initialize orb descriptor extractor
DescriptorExtractor orb_descriptor = DescriptorExtractor.create(DescriptorExtractor.ORB);
Mat Obj_descriptor = new Mat();
Mat Scene_descriptor = new Mat();
orb_descriptor.compute(Object_image, keypoint_object, Obj_descriptor);
orb_descriptor.compute(Scene_image, keypoint_scene, Scene_descriptor);
//3. Matching the descriptors using Brute-Force
DescriptorMatcher brt_frc = DescriptorMatcher.create(DescriptorMatcher.BRUTEFORCE_HAMMING);
MatOfDMatch matches = new MatOfDMatch();
brt_frc.match(Obj_descriptor, Scene_descriptor, matches);
//4. Calculating the max and min distance between Keypoints
float max_dist = 0,min_dist = 100,dist =0;
DMatch[] for_calculating;
for_calculating = matches.toArray();
for( int i = 0; i < Obj_descriptor.rows(); i++ )
{ dist = for_calculating[i].distance;
if( dist < min_dist ) min_dist = dist;
if( dist > max_dist ) max_dist = dist;
}
System.out.print("\nInterval min_dist: " + min_dist + ", max_dist:" + max_dist);
//-- Use only "good" matches (i.e. whose distance is less than 2.5*min_dist)
LinkedList<DMatch> good_matches = new LinkedList<DMatch>();
double ratio_dist=2.5;
ratio_dist = ratio_dist*min_dist;
int i, iter = matches.toArray().length;
matches.release();
for(i = 0;i < iter; i++){
if (for_calculating[i].distance <=ratio_dist)
good_matches.addLast(for_calculating[i]);
}
System.out.print("\n done Good Matches");
/*Necessary type conversion for drawing matches
MatOfDMatch goodMatches = new MatOfDMatch();
goodMatches.fromList(good_matches);
Mat matches_scn_obj = new Mat();
Features2d.drawKeypoints(Object_image, keypoint_object, new Mat(Object_image.rows(), keypoint_object.cols(), keypoint_object.type()), new Scalar(0.0D, 0.0D, 255.0D), 4);
Features2d.drawKeypoints(Scene_image, keypoint_scene, new Mat(Scene_image.rows(), Scene_image.cols(), Scene_image.type()), new Scalar(0.0D, 0.0D, 255.0D), 4);
Features2d.drawMatches(Object_image, keypoint_object, Scene_image, keypoint_scene, goodMatches, matches_scn_obj);
SaveImage(matches_scn_obj,"drawing_good_matches.jpg");
*/
if(good_matches.size() <= 6){
ph_value = "7";
System.out.println("Wrong Detection");
return Scene_image;
}
else{
//5. RANSAC thresholding for finding the optimum homography
Mat outputImg = new Mat();
LinkedList<Point> objList = new LinkedList<Point>();
LinkedList<Point> sceneList = new LinkedList<Point>();
List<org.opencv.core.KeyPoint> keypoints_objectList = keypoint_object.toList();
List<org.opencv.core.KeyPoint> keypoints_sceneList = keypoint_scene.toList();
//getting the object and scene points from good matches
for(i = 0; i<good_matches.size(); i++){
objList.addLast(keypoints_objectList.get(good_matches.get(i).queryIdx).pt);
sceneList.addLast(keypoints_sceneList.get(good_matches.get(i).trainIdx).pt);
}
good_matches.clear();
MatOfPoint2f obj = new MatOfPoint2f();
obj.fromList(objList);
objList.clear();
MatOfPoint2f scene = new MatOfPoint2f();
scene.fromList(sceneList);
sceneList.clear();
float RANSAC_dist=(float)2.0;
Mat hg = Calib3d.findHomography(obj, scene, Calib3d.RANSAC, RANSAC_dist);
for(i = 0;i<hg.cols();i++) {
String tmp = "";
for ( int j = 0; j < hg.rows(); j++) {
Point val = new Point(hg.get(j, i));
tmp= tmp + val.x + " ";
}
}
Mat scene_image_transformed_color = new Mat();
Imgproc.warpPerspective(original_image, scene_image_transformed_color, hg, Object_image.size(), Imgproc.WARP_INVERSE_MAP);
processing(scene_image_transformed_color, template_match);
return outputImg;
}
} }
and this part is what is taking 6 seconds to implement on runtime -
LinkedList<DMatch> good_matches = new LinkedList<DMatch>();
double ratio_dist=2.5;
ratio_dist = ratio_dist*min_dist;
int i, iter = matches.toArray().length;
matches.release();
for(i = 0;i < iter; i++){
if (for_calculating[i].distance <=ratio_dist)
good_matches.addLast(for_calculating[i]);
}
System.out.print("\n done Good Matches");}
I was thinking may be I can write this part of the code in C++ using NDK but I just wanted to be sure that the language is the problem and not the code itself.
Please don't be strict, first question! Any criticism is much appreciated!

So the problem was the logcat was giving me false timing results. The lag was due to a Huge Gaussian Blur later on in the code. Instead of System.out.print, I used System.currentTimeMillis, which showed me the bug.