Reworked HolisticWordspotter to work with dnn module

Author: mshabunin

modules/text/CMakeLists.txt

@@ -1,5 +1,5 @@
 set(the_description "Text Detection and Recognition")
-ocv_define_module(text opencv_ml opencv_imgproc opencv_core opencv_features2d OPTIONAL opencv_highgui WRAP python java)
+ocv_define_module(text opencv_ml opencv_imgproc opencv_core opencv_features2d opencv_dnn OPTIONAL opencv_highgui WRAP python java)
 
 if(NOT CMAKE_CROSSCOMPILING OR OPENCV_FIND_TESSERACT)
   set(CMAKE_MODULE_PATH ${CMAKE_MODULE_PATH} ${CMAKE_CURRENT_SOURCE_DIR}/cmake)
@@ -22,62 +22,3 @@ ocv_include_directories(${CMAKE_CURRENT_BINARY_DIR})
 ocv_add_testdata(samples/ contrib/text
     FILES_MATCHING PATTERN "*.xml" PATTERN "*.xml.gz" REGEX "scenetext[0-9]+.jpg"
 )
-
-
-#Principal source from which adaptation came is the cnn_3dobj module
-find_package(Caffe)
-
-if(Caffe_FOUND)
-  message(STATUS "Caffe:   YES")
-  set(HAVE_CAFFE 1)
-else()
-  message(STATUS "Caffe:   NO")
-endif()
-
-find_package(Protobuf)
-if(Protobuf_FOUND)
-  message(STATUS "Protobuf:   YES")
-  set(HAVE_PROTOBUF 1)
-else()
-  message(STATUS "Protobuf:   NO")
-endif()
-
-find_package(Glog)
-if(Glog_FOUND)
-  message(STATUS "Glog:   YES")
-  set(HAVE_GLOG 1)
-else()
-  message(STATUS "Glog:   NO")
-endif()
-
-if(HAVE_CAFFE)
-message(STATUS "HAVE CAFFE!!!")
-configure_file(${CMAKE_CURRENT_SOURCE_DIR}/text_config.hpp.in
-               ${CMAKE_CURRENT_SOURCE_DIR}/include/opencv2/text_config.hpp @ONLY)
-
-
-include_directories(${CMAKE_CURRENT_BINARY_DIR})
-
-if(${Caffe_FOUND})
-
-  include_directories(${Caffe_INCLUDE_DIR})
-  #taken from caffe's cmake
-  find_package(HDF5 COMPONENTS HL REQUIRED)
-  include_directories(SYSTEM ${HDF5_INCLUDE_DIRS} ${HDF5_HL_INCLUDE_DIR})
-  list(APPEND Caffe_LINKER_LIBS ${HDF5_LIBRARIES})
-  find_package(Boost 1.46 REQUIRED COMPONENTS system thread filesystem)
-  include_directories(SYSTEM ${Boost_INCLUDE_DIR})
-  include_directories(SYSTEM /usr/local/cuda-7.5/targets/x86_64-linux/include/)
-  list(APPEND Caffe_LINKER_LIBS ${Boost_LIBRARIES})
-
-endif()
-
-
-if(${Caffe_FOUND})
-  #taken from caffe's cmake
-  target_link_libraries(opencv_text ${Caffe_LIBS} ${Glog_LIBS} ${Protobuf_LIBS} ${HDF5_LIBRARIES} ${Boost_LIBRARIES})
-endif()
-endif()
-
-configure_file(${CMAKE_CURRENT_SOURCE_DIR}/text_config.hpp.in
-               ${CMAKE_BINARY_DIR}/text_config.hpp @ONLY)

modules/text/FindCaffe.cmake

@@ -46,10 +46,6 @@
 
 #include <vector>
 #include <string>
-#include <iostream>
-#include <sstream>
-
-
 
 namespace cv
 {
@@ -540,107 +536,24 @@ at each window location.
 
 CV_EXPORTS_W Ptr<OCRBeamSearchDecoder::ClassifierCallback> loadOCRBeamSearchClassifierCNN(const String& filename);
 
-//! @}
-
-
-
-//Classifiers should provide diferent backends
-//For the moment only caffe is implemeted
-enum{
-    OCR_HOLISTIC_BACKEND_NONE,
-    OCR_HOLISTIC_BACKEND_CAFFE
-};
-
-
-/** @brief Abstract class that implements the classifcation of text images.
- *
- * The interface is generic enough to describe any image classifier. And allows
- * to take advantage of compouting in batches. While word classifiers are the default
- * networks, any image classifers should work.
- *
- */
-class CV_EXPORTS_W TextImageClassifier
-{
-protected:
-    Size inputSz_;
-    int channelCount_;
-    /** @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(Mat& input,Mat& output)=0;
-public:
-    virtual ~TextImageClassifier() {}
-    /** @brief produces a class confidence row-vector given an image
-     */
-    CV_WRAP virtual void classify(InputArray image, OutputArray classProbabilities) = 0;
-    /** @brief produces a matrix containing class confidence row-vectors given an collection of images
-     */
-    CV_WRAP virtual void classifyBatch(InputArrayOfArrays image, OutputArray classProbabilities) = 0;
-    /** @brief simple getter method returning the size of the oputput row-vector
-     */
-    CV_WRAP virtual int getOutputSize()=0;
-    /** @brief simple getter method returning the size of the minibatches for this classifier.
-     * If not applicabe this method should return 1
-     */
-    CV_WRAP virtual int getMinibatchSize()=0;
-    /** @brief simple getter method returning a value describing the framework beeing employed to implement the classifier
-     */
-    CV_WRAP virtual int getBackend(){return OCR_HOLISTIC_BACKEND_NONE;}
-};
-
-class CV_EXPORTS_W DictNet:public TextImageClassifier
-{
-    /** @brief Class that uses a pretrained caffe model for word classification.
-     *
-     * This network is described in detail in:
-     * Max Jaderberg et al.: Reading Text in the Wild with Convolutional Neural Networks, IJCV 2015
-     * http://arxiv.org/abs/1412.1842
-     */
-public:
-    virtual ~DictNet() {};
-
-    CV_WRAP virtual bool usingGpu()=0;
-    /** @brief Constructs a DictNet 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. This file can be
-     * very large, up to 2GB.
-     *
-     * @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 useGpu boolean flag setting GPU or CPU computation
-     *
-     * @param backEnd integer parameter selecting the coputation framework. For now OCR_HOLISTIC_BACKEND_CAFFE is
-     * the only option
-     */
-    CV_WRAP static Ptr<DictNet> create(String archFilename,String weightsFilename,int minibatchSz=100,bool useGpu=0,int backEnd=OCR_HOLISTIC_BACKEND_CAFFE);
-};
-
-
 
 /** @brief OCRHolisticWordRecognizer class provides the functionallity of segmented wordspotting.
- * Given a predefined vocabulary , a TextImageClassifier is employed to select the most probable
+ * Given a predefined vocabulary , a DictNet is employed to select the most probable
  * word given an input image.
  *
- * This class implements the logic of providing transcriptions given a vocabulary and and an image
- * classifer.
+ * DictNet is described in detail in:
+ * Max Jaderberg et al.: Reading Text in the Wild with Convolutional Neural Networks, IJCV 2015
+ * http://arxiv.org/abs/1412.1842
  */
-class CV_EXPORTS_W OCRHolisticWordRecognizer : public BaseOCR
+class CV_EXPORTS OCRHolisticWordRecognizer : public BaseOCR
 {
 public:
-    virtual void run(Mat& image, std::string& output_text, std::vector<Rect>* component_rects=NULL,
-                     std::vector<std::string>* component_texts=NULL, std::vector<float>* component_confidences=NULL,
-                     int component_level=OCR_LEVEL_WORD)=0;
+    virtual void run(Mat& image,
+                     std::string& output_text,
+                     std::vector<Rect>* component_rects = NULL,
+                     std::vector<std::string>* component_texts = NULL,
+                     std::vector<float>* component_confidences = NULL,
+                     int component_level = OCR_LEVEL_WORD) = 0;
 
     /** @brief Recognize text using a segmentation based word-spotting/classifier cnn.
 
@@ -665,68 +578,24 @@ class CV_EXPORTS_W OCRHolisticWordRecognizer : public BaseOCR
 
     @param component_level must be OCR_LEVEL_WORD.
      */
-
-    virtual void run(Mat& image, Mat& mask, std::string& output_text, std::vector<Rect>* component_rects=NULL,
-                     std::vector<std::string>* component_texts=NULL, std::vector<float>* component_confidences=NULL,
-                     int component_level=OCR_LEVEL_WORD)=0;
-
-
-    /**
-    @brief Method that provides a quick and simple interface to a single word image classifcation
-
-    @param inputImage an image expected to be a CV_U8C1 or CV_U8C3 of any size assumed to contain a single word
-
-    @param transcription an opencv string that will store the detected word transcription
-
-    @param confidence a double that will be updated with the confidence the classifier has for the selected word
-    */
-    CV_WRAP virtual void recogniseImage(InputArray inputImage,CV_OUT String& transcription,CV_OUT double& confidence)=0;
-
-    /**
-    @brief Method that provides a quick and simple interface to a multiple word image classifcation taking advantage
-    the classifiers parallel capabilities.
-
-    @param inputImageList an list of images expected to be a CV_U8C1 or CV_U8C3 each image can be of any size and is assumed
-    to contain a single word.
-
-    @param transcriptions a vector of opencv strings that will store the detected word transcriptions, one for each
-    input image
-
-    @param confidences a vector of double that will be updated with the confidence the classifier has for each of the
-    selected words.
-    */
-    CV_WRAP virtual void recogniseImageBatch(InputArrayOfArrays inputImageList,CV_OUT std::vector<String>& transcriptions,CV_OUT std::vector<double>& confidences)=0;
-
-
-    /**
-    @brief simple getted for the vocabulary employed
-    */
-    CV_WRAP virtual const std::vector<String>& getVocabulary()=0;
-
+    virtual void run(Mat& image,
+                     Mat& mask,
+                     std::string& output_text,
+                     std::vector<Rect>* component_rects = NULL,
+                     std::vector<std::string>* component_texts = NULL,
+                     std::vector<float>* component_confidences = NULL,
+                     int component_level = OCR_LEVEL_WORD) = 0;
 
     /** @brief Creates an instance of the OCRHolisticWordRecognizer class.
-
-    @param classifierPtr an instance of TextImageClassifier, normaly a DictNet instance
-    @param vocabullaryFilename the relative or absolute path to the file containing all words in the vocabulary. Each text line
-    in the file is assumed to be a single word. The number of words in the vocabulary must be exactly the same as the outputSize
-    of the classifier.
      */
-    CV_WRAP static Ptr<OCRHolisticWordRecognizer> create(Ptr<TextImageClassifier> classifierPtr,String vocabullaryFilename);
-    /** @brief Creates an instance of the OCRHolisticWordRecognizer class and implicitly also a DictNet classifier.
-
-    @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 vocabullaryFilename the relative or absolute path to the file containing all words in the vocabulary. Each text line
-    in the file is assumed to be a single word. The number of words in the vocabulary must be exactly the same as the outputSize
-    of the classifier.
-    */
-    CV_WRAP static Ptr<OCRHolisticWordRecognizer> create(String modelArchFilename, String modelWeightsFilename, String vocabullaryFilename);
-
+    static Ptr<OCRHolisticWordRecognizer> create(const std::string &archFilename,
+                                                 const std::string &weightsFilename,
+                                                 const std::string &wordsFilename);
 };
 
+//! @}
 
-}
-}
+}} // cv::text::
 
 
 #endif // _OPENCV_TEXT_OCR_HPP_