diff --git a/modules/core/include/opencv2/core/mat.hpp b/modules/core/include/opencv2/core/mat.hpp
index 31d182c713..2e927c498c 100644
--- a/modules/core/include/opencv2/core/mat.hpp
+++ b/modules/core/include/opencv2/core/mat.hpp
@@ -1192,8 +1192,8 @@ public:
     /** @overload
     @param m Destination matrix. If it does not have a proper size or type before the operation, it is
     reallocated.
-    @param mask Operation mask. Its non-zero elements indicate which matrix elements need to be copied.
-    The mask has to be of type CV_8U and can have 1 or multiple channels.
+    @param mask Operation mask of the same size as \*this. Its non-zero elements indicate which matrix
+    elements need to be copied. The mask has to be of type CV_8U and can have 1 or multiple channels.
     */
     void copyTo( OutputArray m, InputArray mask ) const;
 
@@ -1229,7 +1229,8 @@ public:
 
     This is an advanced variant of the Mat::operator=(const Scalar& s) operator.
     @param value Assigned scalar converted to the actual array type.
-    @param mask Operation mask of the same size as \*this.
+    @param mask Operation mask of the same size as \*this. Its non-zero elements indicate which matrix
+    elements need to be copied. The mask has to be of type CV_8U and can have 1 or multiple channels
      */
     Mat& setTo(InputArray value, InputArray mask=noArray());
 
diff --git a/modules/core/src/copy.cpp b/modules/core/src/copy.cpp
index e07a75f947..d22e762b1f 100644
--- a/modules/core/src/copy.cpp
+++ b/modules/core/src/copy.cpp
@@ -336,7 +336,7 @@ static bool ipp_copyTo(const Mat &src, Mat &dst, const Mat &mask)
 #ifdef HAVE_IPP_IW
     CV_INSTRUMENT_REGION_IPP()
 
-    if(mask.channels() > 1 && mask.depth() != CV_8U)
+    if(mask.channels() > 1 || mask.depth() != CV_8U)
         return false;
 
     if (src.dims <= 2)
@@ -512,20 +512,23 @@ Mat& Mat::setTo(InputArray _value, InputArray _mask)
     Mat value = _value.getMat(), mask = _mask.getMat();
 
     CV_Assert( checkScalar(value, type(), _value.kind(), _InputArray::MAT ));
-    CV_Assert( mask.empty() || (mask.type() == CV_8U && size == mask.size) );
+    int cn = channels(), mcn = mask.channels();
+    CV_Assert( mask.empty() || (mask.depth() == CV_8U && (mcn == 1 || mcn == cn) && size == mask.size) );
 
     CV_IPP_RUN_FAST(ipp_Mat_setTo_Mat(*this, value, mask), *this)
 
-    size_t esz = elemSize();
+    size_t esz = mcn > 1 ? elemSize1() : elemSize();
     BinaryFunc copymask = getCopyMaskFunc(esz);
 
     const Mat* arrays[] = { this, !mask.empty() ? &mask : 0, 0 };
     uchar* ptrs[2]={0,0};
     NAryMatIterator it(arrays, ptrs);
-    int totalsz = (int)it.size, blockSize0 = std::min(totalsz, (int)((BLOCK_SIZE + esz-1)/esz));
+    int totalsz = (int)it.size*mcn;
+    int blockSize0 = std::min(totalsz, (int)((BLOCK_SIZE + esz-1)/esz));
+    blockSize0 -= blockSize0 % mcn;    // must be divisible without remainder for unrolling and advancing
     AutoBuffer<uchar> _scbuf(blockSize0*esz + 32);
     uchar* scbuf = alignPtr((uchar*)_scbuf, (int)sizeof(double));
-    convertAndUnrollScalar( value, type(), scbuf, blockSize0 );
+    convertAndUnrollScalar( value, type(), scbuf, blockSize0/mcn );
 
     for( size_t i = 0; i < it.nplanes; i++, ++it )
     {
diff --git a/modules/core/test/test_arithm.cpp b/modules/core/test/test_arithm.cpp
index 78c0689852..ae5e4a7728 100644
--- a/modules/core/test/test_arithm.cpp
+++ b/modules/core/test/test_arithm.cpp
@@ -1,4 +1,4 @@
-#include "test_precomp.hpp"
+#include "test_precomp.hpp"
 #include <cmath>
 
 using namespace cv;
@@ -15,7 +15,7 @@ const int ARITHM_MAX_SIZE_LOG = 10;
 
 struct BaseElemWiseOp
 {
-    enum { FIX_ALPHA=1, FIX_BETA=2, FIX_GAMMA=4, REAL_GAMMA=8, SUPPORT_MASK=16, SCALAR_OUTPUT=32 };
+    enum { FIX_ALPHA=1, FIX_BETA=2, FIX_GAMMA=4, REAL_GAMMA=8, SUPPORT_MASK=16, SCALAR_OUTPUT=32, SUPPORT_MULTICHANNELMASK=64 };
     BaseElemWiseOp(int _ninputs, int _flags, double _alpha, double _beta,
                    Scalar _gamma=Scalar::all(0), int _context=1)
     : ninputs(_ninputs), flags(_flags), alpha(_alpha), beta(_beta), gamma(_gamma), context(_context) {}
@@ -467,7 +467,7 @@ struct CmpSOp : public BaseElemWiseOp
 
 struct CopyOp : public BaseElemWiseOp
 {
-    CopyOp() : BaseElemWiseOp(1, FIX_ALPHA+FIX_BETA+FIX_GAMMA+SUPPORT_MASK, 1, 1, Scalar::all(0)) {  }
+    CopyOp() : BaseElemWiseOp(1, FIX_ALPHA+FIX_BETA+FIX_GAMMA+SUPPORT_MASK+SUPPORT_MULTICHANNELMASK, 1, 1, Scalar::all(0)) {  }
     void op(const vector<Mat>& src, Mat& dst, const Mat& mask)
     {
         src[0].copyTo(dst, mask);
@@ -489,7 +489,7 @@ struct CopyOp : public BaseElemWiseOp
 
 struct SetOp : public BaseElemWiseOp
 {
-    SetOp() : BaseElemWiseOp(0, FIX_ALPHA+FIX_BETA+SUPPORT_MASK, 1, 1, Scalar::all(0)) {}
+    SetOp() : BaseElemWiseOp(0, FIX_ALPHA+FIX_BETA+SUPPORT_MASK+SUPPORT_MULTICHANNELMASK, 1, 1, Scalar::all(0)) {}
     void op(const vector<Mat>&, Mat& dst, const Mat& mask)
     {
         dst.setTo(gamma, mask);
@@ -1394,7 +1394,8 @@ TEST_P(ElemWiseTest, accuracy)
         op->getRandomSize(rng, size);
         int type = op->getRandomType(rng);
         int depth = CV_MAT_DEPTH(type);
-        bool haveMask = (op->flags & cvtest::BaseElemWiseOp::SUPPORT_MASK) != 0 && rng.uniform(0, 4) == 0;
+        bool haveMask = ((op->flags & cvtest::BaseElemWiseOp::SUPPORT_MASK) != 0
+                || (op->flags & cvtest::BaseElemWiseOp::SUPPORT_MULTICHANNELMASK) != 0) && rng.uniform(0, 4) == 0;
 
         double minval=0, maxval=0;
         op->getValueRange(depth, minval, maxval);
@@ -1403,8 +1404,12 @@ TEST_P(ElemWiseTest, accuracy)
         for( i = 0; i < ninputs; i++ )
             src[i] = cvtest::randomMat(rng, size, type, minval, maxval, true);
         Mat dst0, dst, mask;
-        if( haveMask )
-            mask = cvtest::randomMat(rng, size, CV_8U, 0, 2, true);
+        if( haveMask ) {
+            bool multiChannelMask = (op->flags & cvtest::BaseElemWiseOp::SUPPORT_MULTICHANNELMASK) != 0
+                    && rng.uniform(0, 2) == 0;
+            int masktype = CV_8UC(multiChannelMask ? CV_MAT_CN(type) : 1);
+            mask = cvtest::randomMat(rng, size, masktype, 0, 2, true);
+        }
 
         if( (haveMask || ninputs == 0) && !(op->flags & cvtest::BaseElemWiseOp::SCALAR_OUTPUT))
         {
diff --git a/modules/ts/src/ts_func.cpp b/modules/ts/src/ts_func.cpp
index 5d229cf89d..be9bcf5549 100644
--- a/modules/ts/src/ts_func.cpp
+++ b/modules/ts/src/ts_func.cpp
@@ -353,26 +353,38 @@ void copy(const Mat& src, Mat& dst, const Mat& mask, bool invertMask)
         return;
     }
 
-    CV_Assert( src.size == mask.size && mask.type() == CV_8U );
+    int mcn = mask.channels();
+    CV_Assert( src.size == mask.size && mask.depth() == CV_8U
+               && (mcn == 1 || mcn == src.channels()) );
 
     const Mat *arrays[]={&src, &dst, &mask, 0};
     Mat planes[3];
 
     NAryMatIterator it(arrays, planes);
-    size_t j, k, elemSize = src.elemSize(), total = planes[0].total();
+    size_t j, k, elemSize = src.elemSize(), maskElemSize = mask.elemSize(), total = planes[0].total();
     size_t i, nplanes = it.nplanes;
+    size_t elemSize1 = src.elemSize1();
 
     for( i = 0; i < nplanes; i++, ++it)
     {
         const uchar* sptr = planes[0].ptr();
         uchar* dptr = planes[1].ptr();
         const uchar* mptr = planes[2].ptr();
-
-        for( j = 0; j < total; j++, sptr += elemSize, dptr += elemSize )
+        for( j = 0; j < total; j++, sptr += elemSize, dptr += elemSize, mptr += maskElemSize )
         {
-            if( (mptr[j] != 0) ^ invertMask )
-                for( k = 0; k < elemSize; k++ )
-                    dptr[k] = sptr[k];
+            if( mcn == 1)
+            {
+                if( (mptr[0] != 0) ^ invertMask )
+                    for( k = 0; k < elemSize; k++ )
+                        dptr[k] = sptr[k];
+            }
+            else
+            {
+                for( int c = 0; c < mcn; c++ )
+                    if( (mptr[c] != 0) ^ invertMask )
+                        for( k = 0; k < elemSize1; k++ )
+                            dptr[k + c * elemSize1] = sptr[k + c * elemSize1];
+            }
         }
     }
 }
@@ -414,25 +426,37 @@ void set(Mat& dst, const Scalar& gamma, const Mat& mask)
         return;
     }
 
-    CV_Assert( dst.size == mask.size && mask.type() == CV_8U );
+    int cn = dst.channels(), mcn = mask.channels();
+    CV_Assert( dst.size == mask.size && (mcn == 1 || mcn == cn) );
 
     const Mat *arrays[]={&dst, &mask, 0};
     Mat planes[2];
 
     NAryMatIterator it(arrays, planes);
-    size_t j, k, elemSize = dst.elemSize(), total = planes[0].total();
+    size_t j, k, elemSize = dst.elemSize(), maskElemSize = mask.elemSize(), total = planes[0].total();
     size_t i, nplanes = it.nplanes;
+    size_t elemSize1 = dst.elemSize1();
 
     for( i = 0; i < nplanes; i++, ++it)
     {
         uchar* dptr = planes[0].ptr();
         const uchar* mptr = planes[1].ptr();
 
-        for( j = 0; j < total; j++, dptr += elemSize )
+        for( j = 0; j < total; j++, dptr += elemSize, mptr += maskElemSize )
         {
-            if( mptr[j] )
-                for( k = 0; k < elemSize; k++ )
-                    dptr[k] = gptr[k];
+            if( mcn == 1)
+            {
+                if( mptr[0] )
+                    for( k = 0; k < elemSize; k++ )
+                        dptr[k] = gptr[k];
+            }
+            else
+            {
+                for( int c = 0; c < mcn; c++ )
+                    if( mptr[c] )
+                        for( k = 0; k < elemSize1; k++ )
+                            dptr[k + c * elemSize1] = gptr[k + c * elemSize1];
+            }
         }
     }
 }