Text_recognize

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

列挙型
enum	{ OCR_LEVEL_WORD , OCR_LEVEL_TEXTLINE }
enum	cv::text::page_seg_mode {   PSM_OSD_ONLY , PSM_AUTO_OSD , PSM_AUTO_ONLY , PSM_AUTO ,   PSM_SINGLE_COLUMN , PSM_SINGLE_BLOCK_VERT_TEXT , PSM_SINGLE_BLOCK , PSM_SINGLE_LINE ,   PSM_SINGLE_WORD , PSM_CIRCLE_WORD , PSM_SINGLE_CHAR }
	Tesseract.PageSegMode Enumeration
enum	cv::text::ocr_engine_mode { OEM_TESSERACT_ONLY , OEM_CUBE_ONLY , OEM_TESSERACT_CUBE_COMBINED , OEM_DEFAULT }
	Tesseract.OcrEngineMode Enumeration
enum	decoder_mode { OCR_DECODER_VITERBI = 0 }
enum	classifier_type { OCR_KNN_CLASSIFIER = 0 , OCR_CNN_CLASSIFIER = 1 }

関数
CV_EXPORTS_W Ptr< OCRHMMDecoder::ClassifierCallback >	cv::text::loadOCRHMMClassifierNM (const String &filename)
	Allow to implicitly load the default character classifier when creating an OCRHMMDecoder object. [詳解]
CV_EXPORTS_W Ptr< OCRHMMDecoder::ClassifierCallback >	cv::text::loadOCRHMMClassifierCNN (const String &filename)
	Allow to implicitly load the default character classifier when creating an OCRHMMDecoder object. [詳解]
CV_EXPORTS_W Ptr< OCRHMMDecoder::ClassifierCallback >	cv::text::loadOCRHMMClassifier (const String &filename, int classifier)
	Allow to implicitly load the default character classifier when creating an OCRHMMDecoder object. [詳解]

詳解

関数詳解

loadOCRHMMClassifier()

CV_EXPORTS_W Ptr< OCRHMMDecoder::ClassifierCallback > cv::text::loadOCRHMMClassifier	(	const String &	filename,
		int	classifier
	)

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

引数

filename	The XML or YAML file with the classifier model (e.g. OCRBeamSearch_CNN_model_data.xml.gz)
classifier	Can be one of classifier_type enum values.

loadOCRHMMClassifierCNN()

CV_EXPORTS_W Ptr< OCRHMMDecoder::ClassifierCallback > cv::text::loadOCRHMMClassifierCNN

(

const String &

filename

)

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

引数

filename

The 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.

非推奨:

use loadOCRHMMClassifier instead

loadOCRHMMClassifierNM()

CV_EXPORTS_W Ptr< OCRHMMDecoder::ClassifierCallback > cv::text::loadOCRHMMClassifierNM

(

const String &

filename

)

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

引数

filename

The 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.

非推奨:

loadOCRHMMClassifier instead