Merge pull request #12364 from dkurt:dnn_change_blob_from_image

modules/dnn/include/opencv2/dnn/dnn.hpp

@@ -46,9 +46,9 @@
 #include <opencv2/core.hpp>
 
 #if !defined CV_DOXYGEN && !defined CV_DNN_DONT_ADD_EXPERIMENTAL_NS
-#define CV__DNN_EXPERIMENTAL_NS_BEGIN namespace experimental_dnn_34_v8 {
+#define CV__DNN_EXPERIMENTAL_NS_BEGIN namespace experimental_dnn_34_v9 {
 #define CV__DNN_EXPERIMENTAL_NS_END }
-namespace cv { namespace dnn { namespace experimental_dnn_34_v8 { } using namespace experimental_dnn_34_v8; }}
+namespace cv { namespace dnn { namespace experimental_dnn_34_v9 { } using namespace experimental_dnn_34_v9; }}
 #else
 #define CV__DNN_EXPERIMENTAL_NS_BEGIN
 #define CV__DNN_EXPERIMENTAL_NS_END
@@ -843,7 +843,7 @@ CV__DNN_EXPERIMENTAL_NS_BEGIN
      *  @returns 4-dimensional Mat with NCHW dimensions order.
      */
     CV_EXPORTS_W Mat blobFromImage(InputArray image, double scalefactor=1.0, const Size& size = Size(),
-                                   const Scalar& mean = Scalar(), bool swapRB=true, bool crop=true,
+                                   const Scalar& mean = Scalar(), bool swapRB=false, bool crop=false,
                                    int ddepth=CV_32F);
 
     /** @brief Creates 4-dimensional blob from image.
@@ -852,7 +852,7 @@ CV__DNN_EXPERIMENTAL_NS_BEGIN
      */
     CV_EXPORTS void blobFromImage(InputArray image, OutputArray blob, double scalefactor=1.0,
                                   const Size& size = Size(), const Scalar& mean = Scalar(),
-                                  bool swapRB=true, bool crop=true, int ddepth=CV_32F);
+                                  bool swapRB=false, bool crop=false, int ddepth=CV_32F);
 
 
     /** @brief Creates 4-dimensional blob from series of images. Optionally resizes and
@@ -873,7 +873,7 @@ CV__DNN_EXPERIMENTAL_NS_BEGIN
      *  @returns 4-dimensional Mat with NCHW dimensions order.
      */
     CV_EXPORTS_W Mat blobFromImages(InputArrayOfArrays images, double scalefactor=1.0,
-                                    Size size = Size(), const Scalar& mean = Scalar(), bool swapRB=true, bool crop=true,
+                                    Size size = Size(), const Scalar& mean = Scalar(), bool swapRB=false, bool crop=false,
                                     int ddepth=CV_32F);
 
     /** @brief Creates 4-dimensional blob from series of images.
@@ -882,7 +882,7 @@ CV__DNN_EXPERIMENTAL_NS_BEGIN
      */
     CV_EXPORTS void blobFromImages(InputArrayOfArrays images, OutputArray blob,
                                    double scalefactor=1.0, Size size = Size(),
-                                   const Scalar& mean = Scalar(), bool swapRB=true, bool crop=true,
+                                   const Scalar& mean = Scalar(), bool swapRB=false, bool crop=false,
                                    int ddepth=CV_32F);
 
     /** @brief Parse a 4D blob and output the images it contains as 2D arrays through a simpler data structure

modules/dnn/test/test_caffe_importer.cpp

@@ -307,7 +307,7 @@ TEST_P(Reproducibility_SqueezeNet_v1_1, Accuracy)
     net.setPreferableBackend(DNN_BACKEND_OPENCV);
     net.setPreferableTarget(targetId);
 
-    Mat input = blobFromImage(imread(_tf("googlenet_0.png")), 1.0f, Size(227,227), Scalar(), false);
+    Mat input = blobFromImage(imread(_tf("googlenet_0.png")), 1.0f, Size(227,227), Scalar(), false, true);
     ASSERT_TRUE(!input.empty());
 
     Mat out;
@@ -403,7 +403,7 @@ TEST_P(Test_Caffe_nets, DenseNet_121)
     const string model = findDataFile("dnn/DenseNet_121.caffemodel", false);
 
     Mat inp = imread(_tf("dog416.png"));
-    inp = blobFromImage(inp, 1.0 / 255, Size(224, 224));
+    inp = blobFromImage(inp, 1.0 / 255, Size(224, 224), Scalar(), true, true);
     Mat ref = blobFromNPY(_tf("densenet_121_output.npy"));
 
     Net net = readNetFromCaffe(proto, model);

modules/dnn/test/test_tf_importer.cpp

@@ -62,8 +62,7 @@ TEST(Test_TensorFlow, inception_accuracy)
 
     Mat sample = imread(_tf("grace_hopper_227.png"));
     ASSERT_TRUE(!sample.empty());
-    resize(sample, sample, Size(224, 224));
-    Mat inputBlob = blobFromImage(sample);
+    Mat inputBlob = blobFromImage(sample, 1.0, Size(224, 224), Scalar(), /*swapRB*/true);
 
     net.setInput(inputBlob, "input");
     Mat out = net.forward("softmax2");

modules/dnn/test/test_torch_importer.cpp

@@ -278,7 +278,7 @@ TEST_P(Test_Torch_nets, OpenFace_accuracy)
     sampleF32 /= 255;
     resize(sampleF32, sampleF32, Size(96, 96), 0, 0, INTER_NEAREST);
 
-    Mat inputBlob = blobFromImage(sampleF32);
+    Mat inputBlob = blobFromImage(sampleF32, 1.0, Size(), Scalar(), /*swapRB*/true);
 
     net.setInput(inputBlob);
     Mat out = net.forward();
@@ -305,7 +305,7 @@ TEST_P(Test_Torch_nets, ENet_accuracy)
     net.setPreferableTarget(target);
 
     Mat sample = imread(_tf("street.png", false));
-    Mat inputBlob = blobFromImage(sample, 1./255);
+    Mat inputBlob = blobFromImage(sample, 1./255, Size(), Scalar(), /*swapRB*/true);
 
     net.setInput(inputBlob, "");
     Mat out = net.forward();

samples/android/mobilenet-objdetect/src/org/opencv/samples/opencv_mobilenet/MainActivity.java

@@ -86,29 +86,13 @@ public class MainActivity extends AppCompatActivity implements CvCameraViewListe
         // Forward image through network.
         Mat blob = Dnn.blobFromImage(frame, IN_SCALE_FACTOR,
                 new Size(IN_WIDTH, IN_HEIGHT),
-                new Scalar(MEAN_VAL, MEAN_VAL, MEAN_VAL), false);
+                new Scalar(MEAN_VAL, MEAN_VAL, MEAN_VAL), /*swapRB*/false, /*crop*/false);
         net.setInput(blob);
         Mat detections = net.forward();
 
         int cols = frame.cols();
         int rows = frame.rows();
 
-        Size cropSize;
-        if ((float)cols / rows > WH_RATIO) {
-            cropSize = new Size(rows * WH_RATIO, rows);
-        } else {
-            cropSize = new Size(cols, cols / WH_RATIO);
-        }
-
-        int y1 = (int)(rows - cropSize.height) / 2;
-        int y2 = (int)(y1 + cropSize.height);
-        int x1 = (int)(cols - cropSize.width) / 2;
-        int x2 = (int)(x1 + cropSize.width);
-        Mat subFrame = frame.submat(y1, y2, x1, x2);
-
-        cols = subFrame.cols();
-        rows = subFrame.rows();
-
         detections = detections.reshape(1, (int)detections.total() / 7);
 
         for (int i = 0; i < detections.rows(); ++i) {
@@ -116,26 +100,24 @@ public class MainActivity extends AppCompatActivity implements CvCameraViewListe
             if (confidence > THRESHOLD) {
                 int classId = (int)detections.get(i, 1)[0];
 
-                int xLeftBottom = (int)(detections.get(i, 3)[0] * cols);
-                int yLeftBottom = (int)(detections.get(i, 4)[0] * rows);
-                int xRightTop   = (int)(detections.get(i, 5)[0] * cols);
-                int yRightTop   = (int)(detections.get(i, 6)[0] * rows);
+                int left   = (int)(detections.get(i, 3)[0] * cols);
+                int top    = (int)(detections.get(i, 4)[0] * rows);
+                int right  = (int)(detections.get(i, 5)[0] * cols);
+                int bottom = (int)(detections.get(i, 6)[0] * rows);
 
                 // Draw rectangle around detected object.
-                Imgproc.rectangle(subFrame, new Point(xLeftBottom, yLeftBottom),
-                        new Point(xRightTop, yRightTop),
+                Imgproc.rectangle(frame, new Point(left, top), new Point(right, bottom),
                                   new Scalar(0, 255, 0));
                 String label = classNames[classId] + ": " + confidence;
                 int[] baseLine = new int[1];
                 Size labelSize = Imgproc.getTextSize(label, Core.FONT_HERSHEY_SIMPLEX, 0.5, 1, baseLine);
 
                 // Draw background for label.
-                Imgproc.rectangle(subFrame, new Point(xLeftBottom, yLeftBottom - labelSize.height),
-                        new Point(xLeftBottom + labelSize.width, yLeftBottom + baseLine[0]),
-                        new Scalar(255, 255, 255), Core.FILLED);
-
+                Imgproc.rectangle(frame, new Point(left, top - labelSize.height),
+                                  new Point(left + labelSize.width, top + baseLine[0]),
+                                  new Scalar(255, 255, 255), Imgproc.FILLED);
                 // Write class name and confidence.
-                Imgproc.putText(subFrame, label, new Point(xLeftBottom, yLeftBottom),
+                Imgproc.putText(frame, label, new Point(left, top),
                         Core.FONT_HERSHEY_SIMPLEX, 0.5, new Scalar(0, 0, 0));
             }
         }