fixed Bug #2252

error in the tutorial Similarity check (PNSR and SSIM) on the GPU

samples/cpp/tutorial_code/gpu/gpu-basics-similarity/gpu-basics-similarity.cpp

@@ -325,23 +325,23 @@ Scalar getMSSIM_GPU( const Mat& i1, const Mat& i2)
         gpu::GpuMat sigma1_2, sigma2_2, sigma12;
 
         gpu::GaussianBlur(I1_2, sigma1_2, Size(11, 11), 1.5);
-        sigma1_2 -= mu1_2;
+        gpu::subtract(sigma1_2, mu1_2, sigma1_2); // sigma1_2 -= mu1_2;
 
         gpu::GaussianBlur(I2_2, sigma2_2, Size(11, 11), 1.5);
-        sigma2_2 -= mu2_2;
+        gpu::subtract(sigma2_2, mu2_2, sigma2_2); // sigma2_2 -= mu2_2;
 
         gpu::GaussianBlur(I1_I2, sigma12, Size(11, 11), 1.5);
-        sigma12 -= mu1_mu2;
+        gpu::subtract(sigma12, mu1_mu2, sigma12); // sigma12 -= mu1_mu2;
 
         ///////////////////////////////// FORMULA ////////////////////////////////
         gpu::GpuMat t1, t2, t3;
 
-        t1 = 2 * mu1_mu2 + C1; 
+        mu1_mu2.convertTo(t1, -1, 2, C1); // t1 = 2 * mu1_mu2 + C1;
-        t2 = 2 * sigma12 + C2; 
+        sigma12.convertTo(t2, -1, 2, C2); // t2 = 2 * sigma12 + C2;
         gpu::multiply(t1, t2, t3);        // t3 = ((2*mu1_mu2 + C1).*(2*sigma12 + C2))
 
-        t1 = mu1_2 + mu2_2 + C1; 
+        gpu::addWeighted(mu1_2, 1.0, mu2_2, 1.0, C1, t1);       // t1 = mu1_2 + mu2_2 + C1;
-        t2 = sigma1_2 + sigma2_2 + C2;     
+        gpu::addWeighted(sigma1_2, 1.0, sigma2_2, 1.0, C2, t2); // t2 = sigma1_2 + sigma2_2 + C2;
         gpu::multiply(t1, t2, t1);                              // t1 =((mu1_2 + mu2_2 + C1).*(sigma1_2 + sigma2_2 + C2))
 
         gpu::GpuMat ssim_map;
@@ -373,48 +373,50 @@ Scalar getMSSIM_GPU_optimized( const Mat& i1, const Mat& i2, BufferMSSIM& b)
     gpu::split(b.t2, b.vI2, stream);
     Scalar mssim;
 
+    gpu::GpuMat buf;
+
     for( int i = 0; i < b.gI1.channels(); ++i )
     {
         gpu::multiply(b.vI2[i], b.vI2[i], b.I2_2, stream);        // I2^2
         gpu::multiply(b.vI1[i], b.vI1[i], b.I1_2, stream);        // I1^2
         gpu::multiply(b.vI1[i], b.vI2[i], b.I1_I2, stream);       // I1 * I2
 
-        gpu::GaussianBlur(b.vI1[i], b.mu1, Size(11, 11), 1.5, 0, BORDER_DEFAULT, -1, stream);
+        gpu::GaussianBlur(b.vI1[i], b.mu1, Size(11, 11), buf, 1.5, 0, BORDER_DEFAULT, -1, stream);
-        gpu::GaussianBlur(b.vI2[i], b.mu2, Size(11, 11), 1.5, 0, BORDER_DEFAULT, -1, stream);
+        gpu::GaussianBlur(b.vI2[i], b.mu2, Size(11, 11), buf, 1.5, 0, BORDER_DEFAULT, -1, stream);
 
         gpu::multiply(b.mu1, b.mu1, b.mu1_2, stream);
         gpu::multiply(b.mu2, b.mu2, b.mu2_2, stream);
         gpu::multiply(b.mu1, b.mu2, b.mu1_mu2, stream);
 
-        gpu::GaussianBlur(b.I1_2, b.sigma1_2, Size(11, 11), 1.5, 0, BORDER_DEFAULT, -1, stream);
+        gpu::GaussianBlur(b.I1_2, b.sigma1_2, Size(11, 11), buf, 1.5, 0, BORDER_DEFAULT, -1, stream);
-        gpu::subtract(b.sigma1_2, b.mu1_2, b.sigma1_2, stream);
+        gpu::subtract(b.sigma1_2, b.mu1_2, b.sigma1_2, gpu::GpuMat(), -1, stream);
         //b.sigma1_2 -= b.mu1_2;  - This would result in an extra data transfer operation
 
-        gpu::GaussianBlur(b.I2_2, b.sigma2_2, Size(11, 11), 1.5, 0, BORDER_DEFAULT, -1, stream);
+        gpu::GaussianBlur(b.I2_2, b.sigma2_2, Size(11, 11), buf, 1.5, 0, BORDER_DEFAULT, -1, stream);
-        gpu::subtract(b.sigma2_2, b.mu2_2, b.sigma2_2, stream);
+        gpu::subtract(b.sigma2_2, b.mu2_2, b.sigma2_2, gpu::GpuMat(), -1, stream);
         //b.sigma2_2 -= b.mu2_2;
 
-        gpu::GaussianBlur(b.I1_I2, b.sigma12, Size(11, 11), 1.5, 0, BORDER_DEFAULT, -1, stream);
+        gpu::GaussianBlur(b.I1_I2, b.sigma12, Size(11, 11), buf, 1.5, 0, BORDER_DEFAULT, -1, stream);
-        gpu::subtract(b.sigma12, b.mu1_mu2, b.sigma12, stream);
+        gpu::subtract(b.sigma12, b.mu1_mu2, b.sigma12, gpu::GpuMat(), -1, stream);
         //b.sigma12 -= b.mu1_mu2;
 
         //here too it would be an extra data transfer due to call of operator*(Scalar, Mat)
-        gpu::multiply(b.mu1_mu2, 2, b.t1, stream); //b.t1 = 2 * b.mu1_mu2 + C1; 
+        gpu::multiply(b.mu1_mu2, 2, b.t1, 1, -1, stream); //b.t1 = 2 * b.mu1_mu2 + C1;
-        gpu::add(b.t1, C1, b.t1, stream);
+        gpu::add(b.t1, C1, b.t1, gpu::GpuMat(), -1, stream);
-        gpu::multiply(b.sigma12, 2, b.t2, stream); //b.t2 = 2 * b.sigma12 + C2; 
+        gpu::multiply(b.sigma12, 2, b.t2, 1, -1, stream); //b.t2 = 2 * b.sigma12 + C2;
-        gpu::add(b.t2, C2, b.t2, stream);     
+        gpu::add(b.t2, C2, b.t2, gpu::GpuMat(), -12, stream);
 
-        gpu::multiply(b.t1, b.t2, b.t3, stream);     // t3 = ((2*mu1_mu2 + C1).*(2*sigma12 + C2))
+        gpu::multiply(b.t1, b.t2, b.t3, 1, -1, stream);     // t3 = ((2*mu1_mu2 + C1).*(2*sigma12 + C2))
 
-        gpu::add(b.mu1_2, b.mu2_2, b.t1, stream);
+        gpu::add(b.mu1_2, b.mu2_2, b.t1, gpu::GpuMat(), -1, stream);
-        gpu::add(b.t1, C1, b.t1, stream);
+        gpu::add(b.t1, C1, b.t1, gpu::GpuMat(), -1, stream);
 
-        gpu::add(b.sigma1_2, b.sigma2_2, b.t2, stream);
+        gpu::add(b.sigma1_2, b.sigma2_2, b.t2, gpu::GpuMat(), -1, stream);
-        gpu::add(b.t2, C2, b.t2, stream);
+        gpu::add(b.t2, C2, b.t2, gpu::GpuMat(), -1, stream);
 
 
-        gpu::multiply(b.t1, b.t2, b.t1, stream);     // t1 =((mu1_2 + mu2_2 + C1).*(sigma1_2 + sigma2_2 + C2))        
+        gpu::multiply(b.t1, b.t2, b.t1, 1, -1, stream);     // t1 =((mu1_2 + mu2_2 + C1).*(sigma1_2 + sigma2_2 + C2))
-        gpu::divide(b.t3, b.t1, b.ssim_map, stream);      // ssim_map =  t3./t1;
+        gpu::divide(b.t3, b.t1, b.ssim_map, 1, -1, stream);      // ssim_map =  t3./t1;
 
         stream.waitForCompletion();
 
@@ -424,3 +426,4 @@ Scalar getMSSIM_GPU_optimized( const Mat& i1, const Mat& i2, BufferMSSIM& b)
     }
     return mssim;
 }
+