mirror of
https://github.com/opencv/opencv_contrib.git
synced 2025-10-20 21:40:49 +08:00
Modified the class heirarchy
This commit is contained in:
sghoshcvc
@@ -716,10 +716,6 @@ public:
|
||||
/** @brief produces a class confidence row-vector given an image
|
||||
*/
|
||||
CV_WRAP virtual void classify(InputArray image, OutputArray classProbabilities) = 0;
|
||||
/** @brief produces a list of bounding box given an image
|
||||
*/
|
||||
|
||||
CV_WRAP virtual void detect(InputArray image, OutputArray classProbabilities) = 0;
|
||||
|
||||
/** @brief produces a matrix containing class confidence row-vectors given an collection of images
|
||||
*/
|
||||
|
||||
@@ -65,7 +65,7 @@ namespace text
|
||||
//detection scenario
|
||||
class CV_EXPORTS_W BaseDetector
|
||||
{
|
||||
public:
|
||||
public:
|
||||
virtual ~BaseDetector() {};
|
||||
|
||||
virtual void run(Mat& image,
|
||||
@@ -78,6 +78,118 @@ class CV_EXPORTS_W BaseDetector
|
||||
std::vector<float>* component_confidences=NULL,
|
||||
int component_level=0) = 0;
|
||||
|
||||
};
|
||||
/** A virtual class for different models of text detection (including CNN based deep models)
|
||||
*/
|
||||
|
||||
class CV_EXPORTS_W TextRegionDetector
|
||||
{
|
||||
protected:
|
||||
/** Stores input and output size
|
||||
*/
|
||||
//netGeometry inputGeometry_;
|
||||
//netGeometry outputGeometry_;
|
||||
Size inputGeometry_;
|
||||
Size outputGeometry_;
|
||||
int inputChannelCount_;
|
||||
int outputChannelCount_;
|
||||
|
||||
public:
|
||||
virtual ~TextRegionDetector() {}
|
||||
|
||||
/** @brief produces a list of Bounding boxes and an estimate of text-ness confidence of Bounding Boxes
|
||||
*/
|
||||
CV_WRAP virtual void detect(InputArray image, OutputArray bboxProb ) = 0;
|
||||
|
||||
|
||||
/** @brief simple getter method returning the size (height, width) of the input sample
|
||||
*/
|
||||
CV_WRAP virtual Size getInputGeometry(){return this->inputGeometry_;}
|
||||
|
||||
/** @brief simple getter method returning the shape of the oputput
|
||||
* Any text detector should output a number of text regions alongwith a score of text-ness
|
||||
* From the shape it can be inferred the number of text regions and number of returned value
|
||||
* for each region
|
||||
*/
|
||||
CV_WRAP virtual Size getOutputGeometry(){return this->outputGeometry_;}
|
||||
|
||||
|
||||
|
||||
};
|
||||
|
||||
/** Generic structure of Deep CNN based Text Detectors
|
||||
* */
|
||||
class CV_EXPORTS_W DeepCNNTextDetector : public TextRegionDetector
|
||||
{
|
||||
/** @brief Class that uses a pretrained caffe model for text detection.
|
||||
* Any text detection should
|
||||
* This network is described in detail in:
|
||||
* Minghui Liao et al.: TextBoxes: A Fast Text Detector with a Single Deep Neural Network
|
||||
* https://arxiv.org/abs/1611.06779
|
||||
*/
|
||||
protected:
|
||||
/** all deep CNN based text detectors have a preprocessor (normally)
|
||||
*/
|
||||
Ptr<ImagePreprocessor> preprocessor_;
|
||||
/** @brief all image preprocessing is handled here including whitening etc.
|
||||
*
|
||||
* @param input the image to be preprocessed for the classifier. If the depth
|
||||
* is CV_U8 values should be in [0,255] otherwise values are assumed to be in [0,1]
|
||||
*
|
||||
* @param output reference to the image to be fed to the classifier, the preprocessor will
|
||||
* resize the image to the apropriate size and convert it to the apropriate depth\
|
||||
*
|
||||
* The method preprocess should never be used externally, it is up to classify and classifyBatch
|
||||
* methods to employ it.
|
||||
*/
|
||||
virtual void preprocess(const Mat& input,Mat& output);
|
||||
public:
|
||||
virtual ~DeepCNNTextDetector() {};
|
||||
|
||||
/** @brief Constructs a DeepCNNTextDetector object from a caffe pretrained model
|
||||
*
|
||||
* @param archFilename is the path to the prototxt file containing the deployment model architecture description.
|
||||
*
|
||||
* @param weightsFilename is the path to the pretrained weights of the model in binary fdorm.
|
||||
*
|
||||
* @param preprocessor is a pointer to the instance of a ImagePreprocessor implementing the preprocess_ protecteed method;
|
||||
*
|
||||
* @param minibatchSz the maximum number of samples that can processed in parallel. In practice this parameter
|
||||
* has an effect only when computing in the GPU and should be set with respect to the memory available in the GPU.
|
||||
*
|
||||
* @param backEnd integer parameter selecting the coputation framework. For now OCR_HOLISTIC_BACKEND_CAFFE is
|
||||
* the only option
|
||||
*/
|
||||
CV_WRAP static Ptr<DeepCNNTextDetector> create(String archFilename,String weightsFilename,Ptr<ImagePreprocessor> preprocessor,int minibatchSz=100,int backEnd=OCR_HOLISTIC_BACKEND_CAFFE);
|
||||
|
||||
/** @brief Constructs a DeepCNNTextDetector intended to be used for text area detection.
|
||||
*
|
||||
* This method loads a pretrained classifier and couples with a preprocessor that preprocess the image with mean subtraction of ()
|
||||
* The architecture and models weights can be downloaded from:
|
||||
* https://github.com/sghoshcvc/TextBox-Models.git (size is around 100 MB)
|
||||
|
||||
* @param archFilename is the path to the prototxt file containing the deployment model architecture description.
|
||||
* When employing OCR_HOLISTIC_BACKEND_CAFFE this is the path to the deploy ".prototxt".
|
||||
*
|
||||
* @param weightsFilename is the path to the pretrained weights of the model. When employing
|
||||
* OCR_HOLISTIC_BACKEND_CAFFE this is the path to the ".caffemodel" file.
|
||||
*
|
||||
* @param backEnd integer parameter selecting the coputation framework. For now OCR_HOLISTIC_BACKEND_CAFFE is
|
||||
* the only option
|
||||
*/
|
||||
CV_WRAP static Ptr<DeepCNNTextDetector> createTextBoxNet(String archFilename,String weightsFilename,int backEnd=OCR_HOLISTIC_BACKEND_CAFFE);
|
||||
friend class ImagePreprocessor;
|
||||
|
||||
};
|
||||
|
||||
/** @brief textDetector class provides the functionallity of text bounding box detection.
|
||||
* A TextRegionDetector is employed to find bounding boxes of text
|
||||
* words given an input image.
|
||||
*
|
||||
* This class implements the logic of providing text bounding boxes in a vector of rects given an TextRegionDetector
|
||||
* The TextRegionDetector can be any text detector
|
||||
*
|
||||
*/
|
||||
|
||||
class CV_EXPORTS_W textDetector : public BaseDetector
|
||||
{
|
||||
@@ -127,7 +239,7 @@ public:
|
||||
|
||||
/** @brief simple getter for the preprocessing functor
|
||||
*/
|
||||
CV_WRAP virtual Ptr<TextImageClassifier> getClassifier()=0;
|
||||
CV_WRAP virtual Ptr<TextRegionDetector> getClassifier()=0;
|
||||
|
||||
/** @brief Creates an instance of the textDetector class.
|
||||
|
||||
@@ -135,7 +247,7 @@ public:
|
||||
|
||||
|
||||
*/
|
||||
CV_WRAP static Ptr<textDetector> create(Ptr<TextImageClassifier> classifierPtr);
|
||||
CV_WRAP static Ptr<textDetector> create(Ptr<TextRegionDetector> classifierPtr);
|
||||
|
||||
|
||||
/** @brief Creates an instance of the textDetector class and implicitly also a DeepCNN classifier.
|
||||
|
||||
@@ -459,53 +459,53 @@ protected:
|
||||
#endif
|
||||
}
|
||||
|
||||
void process_(Mat inputImage, Mat &outputMat)
|
||||
{
|
||||
// do forward pass and stores the output in outputMat
|
||||
//Process one image
|
||||
CV_Assert(this->minibatchSz_==1);
|
||||
//CV_Assert(outputMat.isContinuous());
|
||||
// void process_(Mat inputImage, Mat &outputMat)
|
||||
// {
|
||||
// // do forward pass and stores the output in outputMat
|
||||
// //Process one image
|
||||
// CV_Assert(this->minibatchSz_==1);
|
||||
// //CV_Assert(outputMat.isContinuous());
|
||||
|
||||
#ifdef HAVE_CAFFE
|
||||
net_->input_blobs()[0]->Reshape(1, this->channelCount_,this->inputGeometry_.height,this->inputGeometry_.width);
|
||||
net_->Reshape();
|
||||
float* inputBuffer=net_->input_blobs()[0]->mutable_cpu_data();
|
||||
float* inputData=inputBuffer;
|
||||
//#ifdef HAVE_CAFFE
|
||||
// net_->input_blobs()[0]->Reshape(1, this->channelCount_,this->inputGeometry_.height,this->inputGeometry_.width);
|
||||
// net_->Reshape();
|
||||
// float* inputBuffer=net_->input_blobs()[0]->mutable_cpu_data();
|
||||
// float* inputData=inputBuffer;
|
||||
|
||||
std::vector<Mat> input_channels;
|
||||
Mat preprocessed;
|
||||
// if the image have multiple color channels the input layer should be populated accordingly
|
||||
for (int channel=0;channel < this->channelCount_;channel++){
|
||||
// std::vector<Mat> input_channels;
|
||||
// Mat preprocessed;
|
||||
// // if the image have multiple color channels the input layer should be populated accordingly
|
||||
// for (int channel=0;channel < this->channelCount_;channel++){
|
||||
|
||||
cv::Mat netInputWraped(this->inputGeometry_.height, this->inputGeometry_.width, CV_32FC1, inputData);
|
||||
input_channels.push_back(netInputWraped);
|
||||
//input_data += width * height;
|
||||
inputData+=(this->inputGeometry_.height*this->inputGeometry_.width);
|
||||
}
|
||||
this->preprocess(inputImage,preprocessed);
|
||||
split(preprocessed, input_channels);
|
||||
// cv::Mat netInputWraped(this->inputGeometry_.height, this->inputGeometry_.width, CV_32FC1, inputData);
|
||||
// input_channels.push_back(netInputWraped);
|
||||
// //input_data += width * height;
|
||||
// inputData+=(this->inputGeometry_.height*this->inputGeometry_.width);
|
||||
// }
|
||||
// this->preprocess(inputImage,preprocessed);
|
||||
// split(preprocessed, input_channels);
|
||||
|
||||
//preprocessed.copyTo(netInputWraped);
|
||||
// //preprocessed.copyTo(netInputWraped);
|
||||
|
||||
|
||||
this->net_->Forward();
|
||||
const float* outputNetData=net_->output_blobs()[0]->cpu_data();
|
||||
// const float* outputNetData1=net_->output_blobs()[1]->cpu_data();
|
||||
// this->net_->Forward();
|
||||
// const float* outputNetData=net_->output_blobs()[0]->cpu_data();
|
||||
// // const float* outputNetData1=net_->output_blobs()[1]->cpu_data();
|
||||
|
||||
|
||||
|
||||
|
||||
this->outputGeometry_ = Size(net_->output_blobs()[0]->width(),net_->output_blobs()[0]->height());
|
||||
int outputSz = this->outputSize_ * this->outputGeometry_.height * this->outputGeometry_.width;
|
||||
outputMat.create(this->outputGeometry_.height , this->outputGeometry_.width,CV_32FC1);
|
||||
float*outputMatData=(float*)(outputMat.data);
|
||||
// this->outputGeometry_ = Size(net_->output_blobs()[0]->width(),net_->output_blobs()[0]->height());
|
||||
// int outputSz = this->outputSize_ * this->outputGeometry_.height * this->outputGeometry_.width;
|
||||
// outputMat.create(this->outputGeometry_.height , this->outputGeometry_.width,CV_32FC1);
|
||||
// float*outputMatData=(float*)(outputMat.data);
|
||||
|
||||
memcpy(outputMatData,outputNetData,sizeof(float)*outputSz);
|
||||
// memcpy(outputMatData,outputNetData,sizeof(float)*outputSz);
|
||||
|
||||
|
||||
|
||||
#endif
|
||||
}
|
||||
//#endif
|
||||
// }
|
||||
|
||||
|
||||
|
||||
@@ -587,15 +587,15 @@ public:
|
||||
inputImageList.push_back(image.getMat());
|
||||
classifyBatch(inputImageList,classProbabilities);
|
||||
}
|
||||
void detect(InputArray image, OutputArray Bbox_prob)
|
||||
{
|
||||
// void detect(InputArray image, OutputArray Bbox_prob)
|
||||
// {
|
||||
|
||||
Bbox_prob.create(this->outputGeometry_,CV_32F); // dummy initialization is it needed
|
||||
Mat outputMat = Bbox_prob.getMat();
|
||||
process_(image.getMat(),outputMat);
|
||||
//copy back to outputArray
|
||||
outputMat.copyTo(Bbox_prob);
|
||||
}
|
||||
// Bbox_prob.create(this->outputGeometry_,CV_32F); // dummy initialization is it needed
|
||||
// Mat outputMat = Bbox_prob.getMat();
|
||||
// process_(image.getMat(),outputMat);
|
||||
// //copy back to outputArray
|
||||
// outputMat.copyTo(Bbox_prob);
|
||||
// }
|
||||
|
||||
void classifyBatch(InputArrayOfArrays inputImageList, OutputArray classProbabilities)
|
||||
{
|
||||
|
||||
@@ -23,6 +23,8 @@
|
||||
namespace cv { namespace text {
|
||||
|
||||
|
||||
|
||||
|
||||
class textDetectImpl: public textDetector{
|
||||
private:
|
||||
struct NetOutput{
|
||||
@@ -60,9 +62,9 @@ private:
|
||||
};
|
||||
protected:
|
||||
|
||||
Ptr<TextImageClassifier> classifier_;
|
||||
Ptr<TextRegionDetector> classifier_;
|
||||
public:
|
||||
textDetectImpl(Ptr<TextImageClassifier> classifierPtr):classifier_(classifierPtr)
|
||||
textDetectImpl(Ptr<TextRegionDetector> classifierPtr):classifier_(classifierPtr)
|
||||
{
|
||||
|
||||
}
|
||||
@@ -131,13 +133,13 @@ public:
|
||||
|
||||
|
||||
|
||||
Ptr<TextImageClassifier> getClassifier()
|
||||
Ptr<TextRegionDetector> getClassifier()
|
||||
{
|
||||
return this->classifier_;
|
||||
}
|
||||
};
|
||||
|
||||
Ptr<textDetector> textDetector::create(Ptr<TextImageClassifier> classifierPtr)
|
||||
Ptr<textDetector> textDetector::create(Ptr<TextRegionDetector> classifierPtr)
|
||||
{
|
||||
return Ptr<textDetector>(new textDetectImpl(classifierPtr));
|
||||
}
|
||||
@@ -155,7 +157,7 @@ Ptr<textDetector> textDetector::create(String modelArchFilename, String modelWei
|
||||
textbox_mean.at<uchar>(0,2)=123;
|
||||
preprocessor->set_mean(textbox_mean);
|
||||
// create a pointer to text box detector(textDetector)
|
||||
Ptr<TextImageClassifier> classifierPtr(DeepCNN::create(modelArchFilename,modelWeightsFilename,preprocessor,1));
|
||||
Ptr<TextRegionDetector> classifierPtr(DeepCNNTextDetector::create(modelArchFilename,modelWeightsFilename,preprocessor,1));
|
||||
return Ptr<textDetector>(new textDetectImpl(classifierPtr));
|
||||
}
|
||||
|
||||
|
||||
343
modules/text/src/text_detectorCNN.cpp
Normal file
343
modules/text/src/text_detectorCNN.cpp
Normal file
@@ -0,0 +1,343 @@
|
||||
#include "precomp.hpp"
|
||||
#include "opencv2/imgproc.hpp"
|
||||
#include "opencv2/core.hpp"
|
||||
|
||||
|
||||
|
||||
#include <iostream>
|
||||
#include <fstream>
|
||||
#include <sstream>
|
||||
#include <queue>
|
||||
#include <algorithm>
|
||||
#include <iosfwd>
|
||||
#include <memory>
|
||||
#include <string>
|
||||
#include <utility>
|
||||
#include <vector>
|
||||
|
||||
|
||||
#ifdef HAVE_CAFFE
|
||||
#include "caffe/caffe.hpp"
|
||||
#endif
|
||||
namespace cv { namespace text {
|
||||
|
||||
inline bool fileExists (String filename) {
|
||||
std::ifstream f(filename.c_str());
|
||||
return f.good();
|
||||
}
|
||||
|
||||
//************************************************************************************
|
||||
//****************** TextImageClassifier *****************************************
|
||||
//************************************************************************************
|
||||
|
||||
//void TextImageClassifier::preprocess(const Mat& input,Mat& output)
|
||||
//{
|
||||
// this->preprocessor_->preprocess_(input,output,this->inputGeometry_,this->channelCount_);
|
||||
//}
|
||||
|
||||
//void TextImageClassifier::setPreprocessor(Ptr<ImagePreprocessor> ptr)
|
||||
//{
|
||||
// CV_Assert(!ptr.empty());
|
||||
// preprocessor_=ptr;
|
||||
//}
|
||||
|
||||
//Ptr<ImagePreprocessor> TextImageClassifier::getPreprocessor()
|
||||
//{
|
||||
// return preprocessor_;
|
||||
//}
|
||||
|
||||
|
||||
class DeepCNNTextDetectorCaffeImpl: public DeepCNNTextDetector{
|
||||
protected:
|
||||
|
||||
|
||||
void process_(Mat inputImage, Mat &outputMat)
|
||||
{
|
||||
// do forward pass and stores the output in outputMat
|
||||
//Process one image
|
||||
// CV_Assert(this->outputGeometry_.batchSize==1);
|
||||
//CV_Assert(outputMat.isContinuous());
|
||||
|
||||
#ifdef HAVE_CAFFE
|
||||
net_->input_blobs()[0]->Reshape(1, this->inputChannelCount_,this->inputGeometry_.height,this->inputGeometry_.width);
|
||||
net_->Reshape();
|
||||
float* inputBuffer=net_->input_blobs()[0]->mutable_cpu_data();
|
||||
float* inputData=inputBuffer;
|
||||
|
||||
std::vector<Mat> input_channels;
|
||||
Mat preprocessed;
|
||||
// if the image have multiple color channels the input layer should be populated accordingly
|
||||
for (int channel=0;channel < this->inputChannelCount_;channel++){
|
||||
|
||||
cv::Mat netInputWraped(this->inputGeometry_.height, this->inputGeometry_.width, CV_32FC1, inputData);
|
||||
input_channels.push_back(netInputWraped);
|
||||
//input_data += width * height;
|
||||
inputData+=(this->inputGeometry_.height*this->inputGeometry_.width);
|
||||
}
|
||||
this->preprocess(inputImage,preprocessed);
|
||||
split(preprocessed, input_channels);
|
||||
|
||||
//preprocessed.copyTo(netInputWraped);
|
||||
|
||||
|
||||
this->net_->Forward();
|
||||
const float* outputNetData=net_->output_blobs()[0]->cpu_data();
|
||||
// const float* outputNetData1=net_->output_blobs()[1]->cpu_data();
|
||||
|
||||
|
||||
|
||||
|
||||
this->outputGeometry_.height = net_->output_blobs()[0]->height();
|
||||
this->outputGeometry_.width = net_->output_blobs()[0]->width();
|
||||
this->outputChannelCount_ = net_->output_blobs()[0]->channels();
|
||||
int outputSz = this->outputChannelCount_ * this->outputGeometry_.height * this->outputGeometry_.width;
|
||||
outputMat.create(this->outputGeometry_.height , this->outputGeometry_.width,CV_32FC1);
|
||||
float*outputMatData=(float*)(outputMat.data);
|
||||
|
||||
memcpy(outputMatData,outputNetData,sizeof(float)*outputSz);
|
||||
|
||||
|
||||
|
||||
#endif
|
||||
}
|
||||
|
||||
|
||||
|
||||
#ifdef HAVE_CAFFE
|
||||
Ptr<caffe::Net<float> > net_;
|
||||
#endif
|
||||
//Size inputGeometry_;
|
||||
int minibatchSz_;//The existence of the assignment operator mandates this to be nonconst
|
||||
//int outputSize_;
|
||||
public:
|
||||
DeepCNNTextDetectorCaffeImpl(const DeepCNNTextDetectorCaffeImpl& dn):
|
||||
minibatchSz_(dn.minibatchSz_){
|
||||
outputGeometry_=dn.outputGeometry_;
|
||||
inputGeometry_=dn.inputGeometry_;
|
||||
//Implemented to supress Visual Studio warning "assignment operator could not be generated"
|
||||
#ifdef HAVE_CAFFE
|
||||
this->net_=dn.net_;
|
||||
#endif
|
||||
}
|
||||
DeepCNNTextDetectorCaffeImpl& operator=(const DeepCNNTextDetectorCaffeImpl &dn)
|
||||
{
|
||||
#ifdef HAVE_CAFFE
|
||||
this->net_=dn.net_;
|
||||
#endif
|
||||
this->setPreprocessor(dn.preprocessor_);
|
||||
this->inputGeometry_=dn.inputGeometry_;
|
||||
this->inputChannelCount_=dn.inputChannelCount_;
|
||||
this->outputChannelCount_ = dn.outputChannelCount_;
|
||||
// this->minibatchSz_=dn.minibatchSz_;
|
||||
//this->outputGeometry_=dn.outputSize_;
|
||||
this->preprocessor_=dn.preprocessor_;
|
||||
this->outputGeometry_=dn.outputGeometry_;
|
||||
return *this;
|
||||
//Implemented to supress Visual Studio warning "assignment operator could not be generated"
|
||||
}
|
||||
|
||||
DeepCNNTextDetectorCaffeImpl(String modelArchFilename, String modelWeightsFilename,Ptr<ImagePreprocessor> preprocessor, int maxMinibatchSz)
|
||||
:minibatchSz_(maxMinibatchSz)
|
||||
{
|
||||
|
||||
CV_Assert(this->minibatchSz_>0);
|
||||
CV_Assert(fileExists(modelArchFilename));
|
||||
CV_Assert(fileExists(modelWeightsFilename));
|
||||
CV_Assert(!preprocessor.empty());
|
||||
this->setPreprocessor(preprocessor);
|
||||
#ifdef HAVE_CAFFE
|
||||
this->net_.reset(new caffe::Net<float>(modelArchFilename, caffe::TEST));
|
||||
CV_Assert(net_->num_inputs()==1);
|
||||
CV_Assert(net_->num_outputs()==1);
|
||||
CV_Assert(this->net_->input_blobs()[0]->channels()==1
|
||||
||this->net_->input_blobs()[0]->channels()==3);
|
||||
// this->channelCount_=this->net_->input_blobs()[0]->channels();
|
||||
|
||||
|
||||
|
||||
this->net_->CopyTrainedLayersFrom(modelWeightsFilename);
|
||||
|
||||
caffe::Blob<float>* inputLayer = this->net_->input_blobs()[0];
|
||||
|
||||
this->inputGeometry_.height = inputLayer->height();
|
||||
this->inputGeometry_.width = inputLayer->width();
|
||||
this->inputChannelCount_ = inputLayer->channels();
|
||||
//this->inputGeometry_.batchSize =1;
|
||||
|
||||
inputLayer->Reshape(this->minibatchSz_,this->inputChannelCount_,this->inputGeometry_.height, this->inputGeometry_.width);
|
||||
net_->Reshape();
|
||||
this->outputChannelCount_ = net_->output_blobs()[0]->channels();
|
||||
//this->outputGeometry_.batchSize =1;
|
||||
this->outputGeometry_.height =net_->output_blobs()[0]->height();
|
||||
this->outputGeometry_.width = net_->output_blobs()[0]->width();
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
#else
|
||||
CV_Error(Error::StsError,"Caffe not available during compilation!");
|
||||
#endif
|
||||
}
|
||||
|
||||
|
||||
void detect(InputArray image, OutputArray Bbox_prob)
|
||||
{
|
||||
Size outSize = Size(this->outputGeometry_.height,outputGeometry_.width);
|
||||
Bbox_prob.create(outSize,CV_32F); // dummy initialization is it needed
|
||||
Mat outputMat = Bbox_prob.getMat();
|
||||
process_(image.getMat(),outputMat);
|
||||
//copy back to outputArray
|
||||
outputMat.copyTo(Bbox_prob);
|
||||
}
|
||||
|
||||
|
||||
|
||||
//int getOutputSize()
|
||||
//{
|
||||
// return this->outputSize_;
|
||||
//}
|
||||
Size getOutputGeometry()
|
||||
{
|
||||
return this->outputGeometry_;
|
||||
}
|
||||
Size getinputGeometry()
|
||||
{
|
||||
return this->inputGeometry_;
|
||||
}
|
||||
|
||||
int getMinibatchSize()
|
||||
{
|
||||
return this->minibatchSz_;
|
||||
}
|
||||
|
||||
int getBackend()
|
||||
{
|
||||
return OCR_HOLISTIC_BACKEND_CAFFE;
|
||||
}
|
||||
void setPreprocessor(Ptr<ImagePreprocessor> ptr)
|
||||
{
|
||||
CV_Assert(!ptr.empty());
|
||||
preprocessor_=ptr;
|
||||
}
|
||||
|
||||
Ptr<ImagePreprocessor> getPreprocessor()
|
||||
{
|
||||
return preprocessor_;
|
||||
}
|
||||
};
|
||||
|
||||
|
||||
Ptr<DeepCNNTextDetector> DeepCNNTextDetector::create(String archFilename,String weightsFilename,Ptr<ImagePreprocessor> preprocessor,int minibatchSz,int backEnd)
|
||||
{
|
||||
if(preprocessor.empty())
|
||||
{
|
||||
// create a custom preprocessor with rawval
|
||||
Ptr<ImagePreprocessor> preprocessor=ImagePreprocessor::createImageCustomPreprocessor(255);
|
||||
// set the mean for the preprocessor
|
||||
|
||||
Mat textbox_mean(1,3,CV_8U);
|
||||
textbox_mean.at<uchar>(0,0)=104;
|
||||
textbox_mean.at<uchar>(0,1)=117;
|
||||
textbox_mean.at<uchar>(0,2)=123;
|
||||
preprocessor->set_mean(textbox_mean);
|
||||
}
|
||||
switch(backEnd){
|
||||
case OCR_HOLISTIC_BACKEND_CAFFE:
|
||||
|
||||
return Ptr<DeepCNNTextDetector>(new DeepCNNTextDetectorCaffeImpl(archFilename, weightsFilename,preprocessor, minibatchSz));
|
||||
break;
|
||||
case OCR_HOLISTIC_BACKEND_NONE:
|
||||
default:
|
||||
CV_Error(Error::StsError,"DeepCNN::create backend not implemented");
|
||||
return Ptr<DeepCNNTextDetector>();
|
||||
break;
|
||||
}
|
||||
return Ptr<DeepCNNTextDetector>();
|
||||
|
||||
}
|
||||
|
||||
|
||||
Ptr<DeepCNNTextDetector> DeepCNNTextDetector::createTextBoxNet(String archFilename,String weightsFilename,int backEnd)
|
||||
{
|
||||
|
||||
// create a custom preprocessor with rawval
|
||||
Ptr<ImagePreprocessor> preprocessor=ImagePreprocessor::createImageCustomPreprocessor(255);
|
||||
// set the mean for the preprocessor
|
||||
|
||||
Mat textbox_mean(1,3,CV_8U);
|
||||
textbox_mean.at<uchar>(0,0)=104;
|
||||
textbox_mean.at<uchar>(0,1)=117;
|
||||
textbox_mean.at<uchar>(0,2)=123;
|
||||
preprocessor->set_mean(textbox_mean);
|
||||
switch(backEnd){
|
||||
case OCR_HOLISTIC_BACKEND_CAFFE:
|
||||
return Ptr<DeepCNNTextDetector>(new DeepCNNTextDetectorCaffeImpl(archFilename, weightsFilename,preprocessor, 100));
|
||||
break;
|
||||
case OCR_HOLISTIC_BACKEND_NONE:
|
||||
default:
|
||||
CV_Error(Error::StsError,"DeepCNN::create backend not implemented");
|
||||
return Ptr<DeepCNNTextDetector>();
|
||||
break;
|
||||
}
|
||||
return Ptr<DeepCNNTextDetector>();
|
||||
|
||||
}
|
||||
|
||||
void DeepCNNTextDetector::preprocess(const Mat& input,Mat& output)
|
||||
{
|
||||
Size inputHtWd = Size(this->inputGeometry_.height,this->inputGeometry_.width);
|
||||
this->preprocessor_->preprocess(input,output,inputHtWd,this->inputChannelCount_);
|
||||
}
|
||||
|
||||
//namespace cnn_config{
|
||||
//namespace caffe_backend{
|
||||
|
||||
//#ifdef HAVE_CAFFE
|
||||
|
||||
//bool getCaffeGpuMode()
|
||||
//{
|
||||
// return caffe::Caffe::mode()==caffe::Caffe::GPU;
|
||||
//}
|
||||
|
||||
//void setCaffeGpuMode(bool useGpu)
|
||||
//{
|
||||
// if(useGpu)
|
||||
// {
|
||||
// caffe::Caffe::set_mode(caffe::Caffe::GPU);
|
||||
// }else
|
||||
// {
|
||||
// caffe::Caffe::set_mode(caffe::Caffe::CPU);
|
||||
// }
|
||||
//}
|
||||
|
||||
//bool getCaffeAvailable()
|
||||
//{
|
||||
// return true;
|
||||
//}
|
||||
|
||||
//#else
|
||||
|
||||
//bool getCaffeGpuMode()
|
||||
//{
|
||||
// CV_Error(Error::StsError,"Caffe not available during compilation!");
|
||||
// return 0;
|
||||
//}
|
||||
|
||||
//void setCaffeGpuMode(bool useGpu)
|
||||
//{
|
||||
// CV_Error(Error::StsError,"Caffe not available during compilation!");
|
||||
// CV_Assert(useGpu==1);//Compilation directives force
|
||||
//}
|
||||
|
||||
//bool getCaffeAvailable(){
|
||||
// return 0;
|
||||
//}
|
||||
|
||||
//#endif
|
||||
|
||||
//}//namespace caffe
|
||||
//}//namespace cnn_config
|
||||
|
||||
} } //namespace text namespace cv
|
||||
|
||||
Reference in New Issue
Block a user