OCRTesseract class provides an interface with the tesseract-ocr API (v3.02.02) in C++.
More...
#include "ocr.hpp"
|
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=0) CV_OVERRIDE |
| Recognize text using the tesseract-ocr API. More...
|
|
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=0) CV_OVERRIDE |
|
String | run (InputArray image, int min_confidence, int component_level=0) |
|
String | run (InputArray image, InputArray mask, int min_confidence, int component_level=0) |
|
virtual void | setWhiteList (const String &char_whitelist)=0 |
|
virtual | ~BaseOCR () |
|
OCRTesseract class provides an interface with the tesseract-ocr API (v3.02.02) in C++.
Notice that it is compiled only when tesseract-ocr is correctly installed.
- Note
-
§ create()
static Ptr<OCRTesseract> cv::text::OCRTesseract::create |
( |
const char * |
datapath = NULL , |
|
|
const char * |
language = NULL , |
|
|
const char * |
char_whitelist = NULL , |
|
|
int |
oem = OEM_DEFAULT , |
|
|
int |
psmode = PSM_AUTO |
|
) |
| |
|
static |
Python: |
---|
| retval | = | cv.text.OCRTesseract_create( | [, datapath[, language[, char_whitelist[, oem[, psmode]]]]] | ) |
Creates an instance of the OCRTesseract class. Initializes Tesseract.
- Parameters
-
datapath | the name of the parent directory of tessdata ended with "/", or NULL to use the system's default directory. |
language | an ISO 639-3 code or NULL will default to "eng". |
char_whitelist | specifies the list of characters used for recognition. NULL defaults to "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ". |
oem | tesseract-ocr offers different OCR Engine Modes (OEM), by default tesseract::OEM_DEFAULT is used. See the tesseract-ocr API documentation for other possible values. |
psmode | tesseract-ocr offers different Page Segmentation Modes (PSM) tesseract::PSM_AUTO (fully automatic layout analysis) is used. See the tesseract-ocr API documentation for other possible values. |
§ run() [1/4]
virtual void cv::text::OCRTesseract::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 = 0 |
|
) |
| |
|
virtual |
Python: |
---|
| retval | = | cv.text_OCRTesseract.run( | image, min_confidence[, component_level] | ) |
| retval | = | cv.text_OCRTesseract.run( | image, mask, min_confidence[, component_level] | ) |
Recognize text using the tesseract-ocr API.
Takes image on input and returns recognized text in the output_text parameter. Optionally provides also the Rects for individual text elements found (e.g. words), and the list of those text elements with their confidence values.
- Parameters
-
image | Input image CV_8UC1 or CV_8UC3 |
output_text | Output text of the tesseract-ocr. |
component_rects | If provided the method will output a list of Rects for the individual text elements found (e.g. words or text lines). |
component_texts | If provided the method will output a list of text strings for the recognition of individual text elements found (e.g. words or text lines). |
component_confidences | If provided the method will output a list of confidence values for the recognition of individual text elements found (e.g. words or text lines). |
component_level | OCR_LEVEL_WORD (by default), or OCR_LEVEL_TEXTLINE. |
Implements cv::text::BaseOCR.
§ run() [2/4]
virtual void cv::text::OCRTesseract::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 = 0 |
|
) |
| |
|
virtual |
Python: |
---|
| retval | = | cv.text_OCRTesseract.run( | image, min_confidence[, component_level] | ) |
| retval | = | cv.text_OCRTesseract.run( | image, mask, min_confidence[, component_level] | ) |
§ run() [3/4]
String cv::text::OCRTesseract::run |
( |
InputArray |
image, |
|
|
int |
min_confidence, |
|
|
int |
component_level = 0 |
|
) |
| |
Python: |
---|
| retval | = | cv.text_OCRTesseract.run( | image, min_confidence[, component_level] | ) |
| retval | = | cv.text_OCRTesseract.run( | image, mask, min_confidence[, component_level] | ) |
§ run() [4/4]
Python: |
---|
| retval | = | cv.text_OCRTesseract.run( | image, min_confidence[, component_level] | ) |
| retval | = | cv.text_OCRTesseract.run( | image, mask, min_confidence[, component_level] | ) |
§ setWhiteList()
virtual void cv::text::OCRTesseract::setWhiteList |
( |
const String & |
char_whitelist | ) |
|
|
pure virtual |
Python: |
---|
| None | = | cv.text_OCRTesseract.setWhiteList( | char_whitelist | ) |
The documentation for this class was generated from the following file:
- /build/master-contrib_docs-lin64/opencv_contrib/modules/text/include/opencv2/text/ocr.hpp