opencv/opencv_contrib
1
0
Fork 0
mirror of https://github.com/opencv/opencv_contrib.git synced 2025-10-18 08:44:11 +08:00
Code Issues Releases Wiki Activity

text: improve DL-based samples

Browse Source
This commit is contained in:
Vladislav Sovrasov
2017-10-30 15:33:12 +03:00
parent 27961cd8cc
commit fd2e37da56
4 changed files with 81 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
modules/text/include/opencv2/text/textDetector.hpp
View File

@@ -54,9 +54,15 @@ public:
@param modelArchFilename the relative or absolute path to the prototxt file describing the classifiers architecture.
@param modelWeightsFilename the relative or absolute path to the file containing the pretrained weights of the model in caffe-binary form.
@param detectMultiscale if true, multiple scales of the input image will be used as network input
@param detectionSizes a list of sizes for multiscale detection. The values`[(300,300),(700,500),(700,300),(700,700),(1600,1600)]` are
recommended in @cite LiaoSBWL17 to achieve the best quality.
*/
CV_WRAP static Ptr<TextDetectorCNN> create(const String& modelArchFilename, const String& modelWeightsFilename, bool detectMultiscale = false);
static Ptr<TextDetectorCNN> create(const String& modelArchFilename, const String& modelWeightsFilename,
std::vector<Size> detectionSizes);
/**
@overload
*/
CV_WRAP static Ptr<TextDetectorCNN> create(const String& modelArchFilename, const String& modelWeightsFilename);
};
//! @}

66
modules/text/samples/text_recognition_cnn.cpp
View File

@@ -1,6 +1,7 @@
#include <opencv2/text.hpp>
#include <opencv2/highgui.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/dnn.hpp>
#include <iostream>
#include <fstream>
@@ -29,22 +30,27 @@ bool fileExists (const string& filename)
return f.good();
}
void textbox_draw(Mat src, vector<Rect>& groups, vector<float>& probs, float thres)
void textbox_draw(Mat src, std::vector<Rect>& groups, std::vector<float>& probs, std::vector<int>& indexes)
{
for (size_t i = 0; i < groups.size(); i++)
for (size_t i = 0; i < indexes.size(); i++)
{
if(probs[i] > thres)
if (src.type() == CV_8UC3)
{
if (src.type() == CV_8UC3)
{
rectangle(src, groups[i], Scalar( 0, 255, 255 ), 2, LINE_AA);
String label = format("%.2f", probs[i]);
cout << "text box: " << groups[i] << " confidence: " << probs[i] << "\n";
putText(src, label, groups.at(i).tl(), FONT_HERSHEY_PLAIN, 1, Scalar( 0,0,255 ), 1, LINE_AA);
}
else
rectangle(src, groups[i], Scalar( 255 ), 3, 8 );
Rect currrentBox = groups[indexes[i]];
rectangle(src, currrentBox, Scalar( 0, 255, 255 ), 2, LINE_AA);
String label = format("%.2f", probs[indexes[i]]);
std::cout << "text box: " << currrentBox << " confidence: " << probs[indexes[i]] << "\n";
int baseLine = 0;
Size labelSize = getTextSize(label, FONT_HERSHEY_PLAIN, 1, 1, &baseLine);
int yLeftBottom = std::max(currrentBox.y, labelSize.height);
rectangle(src, Point(currrentBox.x, yLeftBottom - labelSize.height),
Point(currrentBox.x + labelSize.width, yLeftBottom + baseLine), Scalar( 255, 255, 255 ), FILLED);
putText(src, label, Point(currrentBox.x, yLeftBottom), FONT_HERSHEY_PLAIN, 1, Scalar( 0,0,0 ), 1, LINE_AA);
}
else
rectangle(src, groups[i], Scalar( 255 ), 3, 8 );
}
}
@@ -73,33 +79,41 @@ int main(int argc, const char * argv[])
cout << "Starting Text Box Demo" << endl;
Ptr<text::TextDetectorCNN> textSpotter =
text::TextDetectorCNN::create(modelArch, moddelWeights, false);
text::TextDetectorCNN::create(modelArch, moddelWeights);
vector<Rect> bbox;
vector<float> outProbabillities;
textSpotter->detect(image, bbox, outProbabillities);
std::vector<int> indexes;
cv::dnn::NMSBoxes(bbox, outProbabillities, 0.4f, 0.5f, indexes);
float prob_threshold = 0.6f;
Mat image_copy = image.clone();
textbox_draw(image_copy, bbox, outProbabillities, prob_threshold);
textbox_draw(image_copy, bbox, outProbabillities, indexes);
imshow("Text detection", image_copy);
image_copy = image.clone();
Ptr<text::OCRHolisticWordRecognizer> wordSpotter =
text::OCRHolisticWordRecognizer::create("dictnet_vgg_deploy.prototxt", "dictnet_vgg.caffemodel", "dictnet_vgg_labels.txt");
for(size_t i = 0; i < bbox.size(); i++)
for(size_t i = 0; i < indexes.size(); i++)
{
if(outProbabillities[i] > prob_threshold)
{
Mat wordImg;
cvtColor(image(bbox[i]), wordImg, COLOR_BGR2GRAY);
string word;
vector<float> confs;
wordSpotter->run(wordImg, word, NULL, NULL, &confs);
rectangle(image_copy, bbox[i], Scalar(0, 255, 255), 1, LINE_AA);
putText(image_copy, word, bbox[i].tl(), FONT_HERSHEY_PLAIN, 1, Scalar(0, 0, 255), 1, LINE_AA);
}
Mat wordImg;
cvtColor(image(bbox[indexes[i]]), wordImg, COLOR_BGR2GRAY);
string word;
vector<float> confs;
wordSpotter->run(wordImg, word, NULL, NULL, &confs);
Rect currrentBox = bbox[indexes[i]];
rectangle(image_copy, currrentBox, Scalar( 0, 255, 255 ), 2, LINE_AA);
int baseLine = 0;
Size labelSize = getTextSize(word, FONT_HERSHEY_PLAIN, 1, 1, &baseLine);
int yLeftBottom = std::max(currrentBox.y, labelSize.height);
rectangle(image_copy, Point(currrentBox.x, yLeftBottom - labelSize.height),
Point(currrentBox.x + labelSize.width, yLeftBottom + baseLine), Scalar( 255, 255, 255 ), FILLED);
putText(image_copy, word, Point(currrentBox.x, yLeftBottom), FONT_HERSHEY_PLAIN, 1, Scalar( 0,0,0 ), 1, LINE_AA);
}
imshow("Text recognition", image_copy);
cout << "Recognition finished. Press any key to exit.\n";

39
modules/text/samples/textbox_demo.cpp
View File

@@ -1,6 +1,7 @@
#include <opencv2/text.hpp>
#include <opencv2/highgui.hpp>
#include <opencv2/imgproc.hpp>
#include <opencv2/dnn.hpp>
#include <sstream>
#include <iostream>
@@ -27,22 +28,27 @@ bool fileExists (const std::string& filename)
return f.good();
}
void textbox_draw(Mat src, std::vector<Rect>& groups, std::vector<float>& probs, float thres)
void textbox_draw(Mat src, std::vector<Rect>& groups, std::vector<float>& probs, std::vector<int>& indexes)
{
for (size_t i = 0; i < groups.size(); i++)
for (size_t i = 0; i < indexes.size(); i++)
{
if(probs[i] > thres)
if (src.type() == CV_8UC3)
{
if (src.type() == CV_8UC3)
{
rectangle(src, groups[i], Scalar( 0, 255, 255 ), 2, LINE_AA);
String label = format("%.2f", probs[i]);
std::cout << "text box: " << groups[i] << " confidence: " << probs[i] << "\n";
putText(src, label, groups.at(i).tl(), FONT_HERSHEY_PLAIN, 1, Scalar( 0,0,255 ), 1, LINE_AA);
}
else
rectangle(src, groups[i], Scalar( 255 ), 3, 8 );
Rect currrentBox = groups[indexes[i]];
rectangle(src, currrentBox, Scalar( 0, 255, 255 ), 2, LINE_AA);
String label = format("%.2f", probs[indexes[i]]);
std::cout << "text box: " << currrentBox << " confidence: " << probs[indexes[i]] << "\n";
int baseLine = 0;
Size labelSize = getTextSize(label, FONT_HERSHEY_PLAIN, 1, 1, &baseLine);
int yLeftBottom = std::max(currrentBox.y, labelSize.height);
rectangle(src, Point(currrentBox.x, yLeftBottom - labelSize.height),
Point(currrentBox.x + labelSize.width, yLeftBottom + baseLine), Scalar( 255, 255, 255 ), FILLED);
putText(src, label, Point(currrentBox.x, yLeftBottom), FONT_HERSHEY_PLAIN, 1, Scalar( 0,0,0 ), 1, LINE_AA);
}
else
rectangle(src, groups[i], Scalar( 255 ), 3, 8 );
}
}
@@ -62,7 +68,7 @@ int main(int argc, const char * argv[])
if (!fileExists(modelArch) || !fileExists(moddelWeights))
{
std::cout<<getHelpStr(argv[0]);
std::cout << getHelpStr(argv[0]);
std::cout << "Model files not found in the current directory. Aborting!" << std::endl;
exit(1);
}
@@ -71,13 +77,16 @@ int main(int argc, const char * argv[])
std::cout << "Starting Text Box Demo" << std::endl;
Ptr<text::TextDetectorCNN> textSpotter =
text::TextDetectorCNN::create(modelArch, moddelWeights, false);
text::TextDetectorCNN::create(modelArch, moddelWeights);
std::vector<Rect> bbox;
std::vector<float> outProbabillities;
textSpotter->detect(image, bbox, outProbabillities);
textbox_draw(image, bbox, outProbabillities, 0.5f);
std::vector<int> indexes;
cv::dnn::NMSBoxes(bbox, outProbabillities, 0.3f, 0.4f, indexes);
textbox_draw(image, bbox, outProbabillities, indexes);
imshow("TextBox Demo",image);
std::cout << "Done!" << std::endl << std::endl;

24
modules/text/src/text_detectorCNN.cpp
View File

@@ -23,8 +23,6 @@ protected:
Net net_;
std::vector<Size> sizes_;
int inputChannelCount_;
bool detectMultiscale_;
void getOutputs(const float* buffer,int nbrTextBoxes,int nCol,
std::vector<Rect>& Bbox, std::vector<float>& confidence, Size inputShape)
@@ -54,21 +52,12 @@ protected:
}
public:
TextDetectorCNNImpl(const String& modelArchFilename, const String& modelWeightsFilename, bool detectMultiscale) :
detectMultiscale_(detectMultiscale)
TextDetectorCNNImpl(const String& modelArchFilename, const String& modelWeightsFilename, std::vector<Size> detectionSizes) :
sizes_(detectionSizes)
{
net_ = readNetFromCaffe(modelArchFilename, modelWeightsFilename);
CV_Assert(!net_.empty());
inputChannelCount_ = 3;
sizes_.push_back(Size(700, 700));
if(detectMultiscale_)
{
sizes_.push_back(Size(300, 300));
sizes_.push_back(Size(700,500));
sizes_.push_back(Size(700,300));
sizes_.push_back(Size(1600,1600));
}
}
void detect(InputArray inputImage_, std::vector<Rect>& Bbox, std::vector<float>& confidence)
@@ -92,9 +81,14 @@ public:
}
};
Ptr<TextDetectorCNN> TextDetectorCNN::create(const String &modelArchFilename, const String &modelWeightsFilename, bool detectMultiscale)
Ptr<TextDetectorCNN> TextDetectorCNN::create(const String &modelArchFilename, const String &modelWeightsFilename, std::vector<Size> detectionSizes)
{
return makePtr<TextDetectorCNNImpl>(modelArchFilename, modelWeightsFilename, detectMultiscale);
return makePtr<TextDetectorCNNImpl>(modelArchFilename, modelWeightsFilename, detectionSizes);
}
Ptr<TextDetectorCNN> TextDetectorCNN::create(const String &modelArchFilename, const String &modelWeightsFilename)
{
return create(modelArchFilename, modelWeightsFilename, std::vector<Size>(1, Size(300, 300)));
}
} //namespace text
} //namespace cv