$extrastylesheet
Olena  User documentation 2.1
An Image Processing Platform
 All Classes Namespaces Functions Variables Typedefs Enumerations Enumerator Friends Groups Pages
Processing

Functions

template<typename I , typename J >
document< typename
mln::trait::ch_value< I,
def::lbl_type >::ret
scribo::toolchain::content_in_doc (const Image< I > &input, const Image< J > &input_preproc, bool denoise, bool find_line_seps=true, bool find_whitespace_seps=true, bool enable_ocr=true, const std::string &language=std::string("eng"), bool verbose=false)
template<typename I , typename J >
document< typename
mln::trait::ch_value< I,
def::lbl_type >::ret
scribo::toolchain::content_in_hdoc (const Image< I > &input, const Image< J > &input_preproc, bool denoise, bool find_line_seps=true, bool find_whitespace_seps=true, bool enable_ocr=true, const std::string &language=std::string("eng"))
template<typename I >
line_set< typename
mln::trait::ch_value< I,
def::lbl_type >::ret
scribo::toolchain::text_in_doc (const Image< I > &input, bool denoise, const std::string &language=std::string("eng"), bool find_line_seps=true, bool find_whitespace_seps=true, bool verbose=false)

Detailed Description

Classical processing toolchains for document image.

Function Documentation

template<typename I , typename J >
document<typename mln::trait::ch_value< I , def::lbl_type >::ret> scribo::toolchain::content_in_doc ( const Image< I > &  input,
const Image< J > &  input_preproc,
bool  denoise,
bool  find_line_seps = true,
bool  find_whitespace_seps = true,
bool  enable_ocr = true,
const std::string &  language = std::string("eng"),
bool  verbose = false 
)

Analyse and extract document image content.

Parameters
[in]inputA RGB image.
[in]input_preprocA Binary image.
[in]denoiseRemove too small components (<= 2 pixels).
[in]find_line_sepsEnable/Disable lookup for vertical/horizontal separators.
[in]find_whitespace_sepsEnable/Disable lookup for vertical alignments and whitespaces. Helps finding text layout.
[in]enable_ocrEnable/Disable text recognition.
[in]languageMain language used in the input document. (OCR settings)
[in]verboseEnable/Disable debug information printed on std::cout.
Returns
A document structure.
template<typename I , typename J >
document<typename mln::trait::ch_value< I , def::lbl_type >::ret> scribo::toolchain::content_in_hdoc ( const Image< I > &  input,
const Image< J > &  input_preproc,
bool  denoise,
bool  find_line_seps = true,
bool  find_whitespace_seps = true,
bool  enable_ocr = true,
const std::string &  language = std::string("eng") 
)

Analyse and extract content in a historical/degraded document.

Parameters
[in]inputA RGB image.
[in]input_preprocA Binary image.
[in]denoiseRemove too small components (<= 2 pixels).
[in]find_line_sepsEnable/Disable lookup for vertical/horizontal separators.
[in]find_whitespace_sepsEnable/Disable lookup for vertical alignments and whitespaces. Helps finding text layout.
[in]enable_ocrEnable/Disable text recognition.
[in]languageMain language used in the input document. (OCR settings)
Returns
A document structure.
template<typename I >
line_set<typename mln::trait::ch_value< I , def::lbl_type >::ret> scribo::toolchain::text_in_doc ( const Image< I > &  input,
bool  denoise,
const std::string &  language = std::string("eng"),
bool  find_line_seps = true,
bool  find_whitespace_seps = true,
bool  verbose = false 
)

Extract text lines from a document image.

Parameters
[in]inputA RGB image.
[in]denoiseRemove too small components (<= 2 pixels).
[in]languageMain language used in the input document. (OCR settings)
[in]find_line_sepsEnable/Disable lookup for vertical/horizontal separators.
[in]find_whitespace_sepsEnable/Disable lookup for vertical alignments and whitespaces. Helps finding text layout.
[in]verboseEnable/Disable debug information printed on std::cout.
Returns
A line set including text information and recognized text.