EAST: An Efficient and Accurate Scene Text Detector (https://arxiv.org/abs/1704.03155v2)

modules/dnn/src/nms.cpp

@@ -8,6 +8,8 @@
 #include "precomp.hpp"
 #include "nms.inl.hpp"
 
+#include <opencv2/imgproc.hpp>
+
 namespace cv
 {
 namespace dnn
@@ -28,6 +30,28 @@ void NMSBoxes(const std::vector<Rect>& bboxes, const std::vector<float>& scores,
     NMSFast_(bboxes, scores, score_threshold, nms_threshold, eta, top_k, indices, rectOverlap);
 }
 
+static inline float rotatedRectIOU(const RotatedRect& a, const RotatedRect& b)
+{
+    std::vector<Point2f> inter, hull;
+    int res = rotatedRectangleIntersection(a, b, inter);
+    if (inter.empty() || res == INTERSECT_NONE)
+        return 0.0f;
+    if (res == INTERSECT_FULL)
+        return 1.0f;
+    convexHull(inter, hull);
+    float interArea = contourArea(hull);
+    return interArea / (a.size.area() + b.size.area() - interArea);
+}
+
+void NMSBoxes(const std::vector<RotatedRect>& bboxes, const std::vector<float>& scores,
+              const float score_threshold, const float nms_threshold,
+              std::vector<int>& indices, const float eta, const int top_k)
+{
+    CV_Assert(bboxes.size() == scores.size(), score_threshold >= 0,
+        nms_threshold >= 0, eta > 0);
+    NMSFast_(bboxes, scores, score_threshold, nms_threshold, eta, top_k, indices, rotatedRectIOU);
+}
+
 CV__DNN_EXPERIMENTAL_NS_END
 }// dnn
 }// cv

modules/dnn/src/tensorflow/tf_graph_simplifier.cpp

@@ -538,6 +538,37 @@ public:
     }
 };
 
+// In case of resizing by factor.
+class ResizeBilinearSubgraph : public Subgraph
+{
+public:
+    ResizeBilinearSubgraph()
+    {
+        int input = addNodeToMatch("");
+
+        int shape = addNodeToMatch("Shape", input);
+        int stack = addNodeToMatch("Const");
+        int stack_1 = addNodeToMatch("Const");
+        int stack_2 = addNodeToMatch("Const");
+        int strided_slice = addNodeToMatch("StridedSlice", shape, stack, stack_1, stack_2);
+        int factorY = addNodeToMatch("Const");
+        int mul = addNodeToMatch("Mul", strided_slice, factorY);
+
+        shape = addNodeToMatch("Shape", input);
+        stack = addNodeToMatch("Const");
+        stack_1 = addNodeToMatch("Const");
+        stack_2 = addNodeToMatch("Const");
+        strided_slice = addNodeToMatch("StridedSlice", shape, stack, stack_1, stack_2);
+        int factorX = addNodeToMatch("Const");
+        int mul_1 = addNodeToMatch("Mul", strided_slice, factorX);
+
+        int pack = addNodeToMatch("Pack", mul, mul_1);
+
+        addNodeToMatch("ResizeBilinear", input, pack);
+        setFusedNode("ResizeBilinear", input, factorY, factorX);
+    }
+};
+
 void simplifySubgraphs(tensorflow::GraphDef& net)
 {
     std::vector<Ptr<Subgraph> > subgraphs;
@@ -551,6 +582,7 @@ void simplifySubgraphs(tensorflow::GraphDef& net)
     subgraphs.push_back(Ptr<Subgraph>(new L2NormalizeSubgraph()));
     subgraphs.push_back(Ptr<Subgraph>(new DeconvolutionValidKerasSubgraph()));
     subgraphs.push_back(Ptr<Subgraph>(new DeconvolutionSameKerasSubgraph()));
+    subgraphs.push_back(Ptr<Subgraph>(new ResizeBilinearSubgraph()));
 
     int numNodes = net.node_size();
     std::vector<int> matchedNodesIds;

modules/dnn/src/tensorflow/tf_importer.cpp

@@ -767,6 +767,26 @@ void TFImporter::populateNet(Net dstNet)
                 }
             }
         }
+        else if (type == "Sub")
+        {
+            bool haveConst = false;
+            for(int ii = 0; !haveConst && ii < layer.input_size(); ++ii)
+            {
+                Pin input = parsePin(layer.input(ii));
+                haveConst = value_id.find(input.name) != value_id.end();
+            }
+            CV_Assert(haveConst);
+
+            layerParams.blobs.resize(1);
+            blobFromTensor(getConstBlob(layer, value_id), layerParams.blobs[0]);
+            layerParams.blobs[0] *= -1;
+
+            int id = dstNet.addLayer(name, "Shift", layerParams);
+            layer_id[name] = id;
+
+            // one input only
+            connect(layer_id, dstNet, parsePin(layer.input(0)), id, 0);
+        }
         else if (type == "MatMul")
         {
             CV_Assert(layer.input_size() == 2);