Class cv::text::TextDetectorCNN#

TextDetectorCNN class provides the functionallity of text bounding box detection. This class is representing to find bounding boxes of text words given an input image. This class uses OpenCV dnn module to load pre-trained model described in [184]. The original repository with the modified SSD Caffe version: . Model can be downloaded from DropBox. Modified .prototxt file with the model description can be found in opencv_contrib/modules/text/samples/textbox.prototxt.

#include <opencv2/text/textDetector.hpp>

Collaboration diagram for cv::text::TextDetectorCNN:

cv::text::TextDetectorCNN Node1 cv::text::TextDetectorCNN   + detect() + create() + create() Node2 cv::text::TextDetector   + ~TextDetector() + detect() Node2->Node1

cv::text::TextDetectorCNN Node1 cv::text::TextDetectorCNN   + detect() + create() + create() Node2 cv::text::TextDetector   + ~TextDetector() + detect() Node2->Node1

Public Member Functions#

Public Member Functions inherited from cv::text::TextDetector

Return

Name

Description

~TextDetector()

void

detect(
    InputArray inputImage,
    std::vector< Rect > & Bbox,
    std::vector< float > & confidence )

Method that provides a quick and simple interface to detect text inside an image.

Detailed Description#

TextDetectorCNN class provides the functionallity of text bounding box detection. This class is representing to find bounding boxes of text words given an input image. This class uses OpenCV dnn module to load pre-trained model described in [184]. The original repository with the modified SSD Caffe version: MhLiao/TextBoxes. Model can be downloaded from DropBox. Modified .prototxt file with the model description can be found in opencv_contrib/modules/text/samples/textbox.prototxt.

Member Function Documentation#

detect()#

void cv::text::TextDetectorCNN::detect(
InputArray inputImage,
std::vector< Rect > & Bbox,
std::vector< float > & confidence )

Python:

cv.text.TextDetectorCNN.detect(inputImage) -> Bbox, confidence

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Parameters

  • inputImage — an image expected to be a CV_U8C3 of any size

  • Bbox — a vector of Rect that will store the detected word bounding box

  • confidence — a vector of float that will be updated with the confidence the classifier has for the selected bounding box

create()#

static Ptr< TextDetectorCNN > cv::text::TextDetectorCNN::create(
const String & modelArchFilename,
const String & modelWeightsFilename )

Python:

cv.text.TextDetectorCNN.create(modelArchFilename, modelWeightsFilename) -> retval

cv.text.TextDetectorCNN_create(modelArchFilename, modelWeightsFilename) -> retval

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

create()#

static Ptr< TextDetectorCNN > cv::text::TextDetectorCNN::create(
const String & modelArchFilename,
const String & modelWeightsFilename,
std::vector< Size > detectionSizes )

Python:

cv.text.TextDetectorCNN.create(modelArchFilename, modelWeightsFilename) -> retval

cv.text.TextDetectorCNN_create(modelArchFilename, modelWeightsFilename) -> retval

Creates an instance of the TextDetectorCNN class using the provided parameters.

Parameters

  • modelArchFilename — the relative or absolute path to the prototxt file describing the classifiers architecture.

  • modelWeightsFilename — the relative or absolute path to the file containing the pretrained weights of the model in caffe-binary form.

  • detectionSizes — a list of sizes for multiscale detection. The values[(300,300),(700,500),(700,300),(700,700),(1600,1600)] are recommended in [184] to achieve the best quality.

Source file#

The documentation for this class was generated from the following file: