OpenCV  3.1.0-dev
Open Source Computer Vision
Classes | Enumerations | Functions

Classes

class  cv::text::BaseOCR
 
class  cv::text::OCRHMMDecoder
 OCRHMMDecoder class provides an interface for OCR using Hidden Markov Models. More...
 
class  cv::text::OCRTesseract
 OCRTesseract class provides an interface with the tesseract-ocr API (v3.02.02) in C++. More...
 

Enumerations

enum  {
  cv::text::OCR_LEVEL_WORD,
  cv::text::OCR_LEVEL_TEXTLINE
}
 
enum  cv::text::decoder_mode { cv::text::OCR_DECODER_VITERBI = 0 }
 

Functions

Ptr< OCRHMMDecoder::ClassifierCallback > cv::text::loadOCRHMMClassifierCNN (const String &filename)
 Allow to implicitly load the default character classifier when creating an OCRHMMDecoder object. More...
 
Ptr< OCRHMMDecoder::ClassifierCallback > cv::text::loadOCRHMMClassifierNM (const String &filename)
 Allow to implicitly load the default character classifier when creating an OCRHMMDecoder object. More...
 

Detailed Description

Enumeration Type Documentation

anonymous enum
Enumerator
OCR_LEVEL_WORD 
OCR_LEVEL_TEXTLINE 
Enumerator
OCR_DECODER_VITERBI 

Function Documentation

Ptr<OCRHMMDecoder::ClassifierCallback> cv::text::loadOCRHMMClassifierCNN ( const String filename)

Allow to implicitly load the default character classifier when creating an OCRHMMDecoder object.

Parameters
filenameThe XML or YAML file with the classifier model (e.g. OCRBeamSearch_CNN_model_data.xml.gz)

The CNN default classifier is based in the scene text recognition method proposed by Adam Coates & Andrew NG in [Coates11a]. The character classifier consists in a Single Layer Convolutional Neural Network and a linear classifier. It is applied to the input image in a sliding window fashion, providing a set of recognitions at each window location.

Ptr<OCRHMMDecoder::ClassifierCallback> cv::text::loadOCRHMMClassifierNM ( const String filename)

Allow to implicitly load the default character classifier when creating an OCRHMMDecoder object.

Parameters
filenameThe XML or YAML file with the classifier model (e.g. OCRHMM_knn_model_data.xml)

The KNN default classifier is based in the scene text recognition method proposed by Lukás Neumann & Jiri Matas in [Neumann11b]. Basically, the region (contour) in the input image is normalized to a fixed size, while retaining the centroid and aspect ratio, in order to extract a feature vector based on gradient orientations along the chain-code of its perimeter. Then, the region is classified using a KNN model trained with synthetic data of rendered characters with different standard font types.