Merge pull request #2259 from Shreeshrii/distort

implement PrepareDistortedPix as part of DegradeImage

src/training/degradeimage.cpp

@@ -95,6 +95,7 @@ Pix* DegradeImage(Pix* input, int exposure, TRand* randomizer,
   input = pix;
   int width = pixGetWidth(input);
   int height = pixGetHeight(input);
+
   if (exposure >= 2) {
     // An erosion simulates the spreading darkening of a dark copy.
     // This is backwards to binary morphology,
@@ -167,6 +168,12 @@ Pix* DegradeImage(Pix* input, int exposure, TRand* randomizer,
     }
     data += input->wpl;
   }
+
+//  pix = input;
+//  input = PrepareDistortedPix(pix, false, true, true, true, true,
+//                          1, randomizer, nullptr);
+//  pixDestroy(&pix);
+
   return input;
 }
 
@@ -181,8 +188,6 @@ Pix* PrepareDistortedPix(const Pix* pix, bool perspective, bool invert,
                          GenericVector<TBOX>* boxes) {
   Pix* distorted = pixCopy(nullptr, const_cast<Pix*>(pix));
   // Things to do to synthetic training data.
-  if (invert && randomizer->SignedRand(1.0) < 0)
-    pixInvert(distorted, distorted);
   if ((white_noise || smooth_noise) && randomizer->SignedRand(1.0) > 0.0) {
     // TODO(rays) Cook noise in a more thread-safe manner than rand().
     // Attempt to make the sequences reproducible.
@@ -210,6 +215,8 @@ Pix* PrepareDistortedPix(const Pix* pix, bool perspective, bool invert,
         (*boxes)[b].set_right((*boxes)[b].left() + 1);
     }
   }
+  if (invert && randomizer->SignedRand(1.0) < -0.9)
+    pixInvert(distorted, distorted);
   return distorted;
 }
 

src/training/text2image.cpp

@@ -74,6 +74,28 @@ BOOL_PARAM_FLAG(rotate_image, true, "Rotate the image in a random way.");
 // Degradation to apply to the image.
 INT_PARAM_FLAG(exposure, 0, "Exposure level in photocopier");
 
+// Distort the rendered image by various means according to the bool flags.
+BOOL_PARAM_FLAG(distort_image, false,
+                "Degrade rendered image with noise, blur, invert.");
+
+// Distortion to apply to the image.
+BOOL_PARAM_FLAG(invert, true, "Invert the image");
+
+// Distortion to apply to the image.
+BOOL_PARAM_FLAG(white_noise, true, "Add  Gaussian Noise");
+
+// Distortion to apply to the image.
+BOOL_PARAM_FLAG(smooth_noise, true, "Smoothen Noise");
+
+// Distortion to apply to the image.
+BOOL_PARAM_FLAG(blur, true, "Blur the image");
+
+// Distortion to apply to the image.
+//BOOL_PARAM_FLAG(perspective, false, "Generate Perspective Distortion");
+
+// Distortion to apply to the image.
+//INT_PARAM_FLAG(box_reduction, 0, "Integer reduction factor box_scale");
+
 // Output image resolution.
 INT_PARAM_FLAG(resolution, 300, "Pixels per inch");
 
@@ -619,6 +641,12 @@ static int Main() {
           pix = DegradeImage(pix, FLAGS_exposure, &randomizer,
                              FLAGS_rotate_image ? &rotation : nullptr);
         }
+        if (FLAGS_distort_image) {
+         //Todo: perspective is set to false and box_reduction to 1.
+          pix = PrepareDistortedPix(pix, false, FLAGS_invert,
+                             FLAGS_white_noise, FLAGS_smooth_noise, FLAGS_blur,
+                             1, &randomizer, nullptr);
+        }
         render.RotatePageBoxes(rotation);
 
         if (pass == 0) {