DLSignatureDetect Class Reference

DLSignatureDetectDOCLIB implements a multi-scale signature detection and segmentation approach. The detection algorithm works in one of the two modes specified by the user. It can either detect signatures by looking at the entire document image, or detect signatures by exploring document context. When using document context, it effectively estimate statistics of machine printed text lines and use them to locate the region below the main body of the document text, where signatures typically appear. Using document context is more effective for machine printed documents. More...

#include <DLSignatureDetect.h>

List of all members.

Public Types

enum  PARAMETERSET { DL_ENGLISH_PRINT = 1, DL_ARABIC_HANDWRITING = 2 }
 Parameter sets used for signature detection. More...

Public Member Functions

 DLSignatureDetect (const char *fname, PARAMETERSET parameterSet=DL_ENGLISH_PRINT, double resizeRatio=2.0, bool useContext=true)
 DLSignatureDetect (const DLImage &srcImage, const char *fname, PARAMETERSET parameterSet=DL_ENGLISH_PRINT, double resizeRatio=2.0, bool useContext=true)
 ~DLSignatureDetect ()
list
< DLSignatureCandidate
dlGetDetectedSignatures ()
bool dlGotSignatures ()

Classes

struct  DLSignatureDetectParameters
 struct for storing the language and dataset dependent parameters for signature detection


Detailed Description

DLSignatureDetectDOCLIB implements a multi-scale signature detection and segmentation approach. The detection algorithm works in one of the two modes specified by the user. It can either detect signatures by looking at the entire document image, or detect signatures by exploring document context. When using document context, it effectively estimate statistics of machine printed text lines and use them to locate the region below the main body of the document text, where signatures typically appear. Using document context is more effective for machine printed documents.

The idea of this signature detection approach is to capture the structural saliency of a signature by measuring its dynamic curvature without recovering the tempo information. Once the most salient part of the signature is identified, contour grouping is performed to obtain a complete and segmented signature. As tested in large real world datasets, this approach is robust under large intra-class variations that typically exhibited on unconstrained handwritting, and it is very effective across language differences.


Member Enumeration Documentation

enum DLSignatureDetect::PARAMETERSET

Parameter sets used for signature detection.

Enumerator:
DL_ENGLISH_PRINT 
DL_ARABIC_HANDWRITING 


Constructor & Destructor Documentation

DLSignatureDetect::DLSignatureDetect ( const char *  fname,
PARAMETERSET  parameterSet = DL_ENGLISH_PRINT,
double  resizeRatio = 2.0,
bool  useContext = true 
)

Default DLSignatureDetect Constructor. Initialize signature detector using the input image file

Parameters:
fname file name of the source image
parameterSet trained parameter sets used for signature detection. Refer to enumerator DLSIGNATUREDETECT_PARAMETERS for the list of currently supported set
resizeRatio double the base factor for computing the initial coarest image scale
useContext bool type argument specifying whether to use document context for signature detection

DLSignatureDetect::DLSignatureDetect ( const DLImage &  srcImage,
const char *  fname,
PARAMETERSET  parameterSet = DL_ENGLISH_PRINT,
double  resizeRatio = 2.0,
bool  useContext = true 
)

DLSignatureDetect Constructor. Initialize signature detector using an DLImage

Parameters:
srcImage DLImage of the source image
fname file name of the source image
parameterSet trained parameter sets used for signature detection. Refer to enumerator DLSIGNATUREDETECT_PARAMETERS for the list of currently supported set
resizeRatio double the base factor for computing the initial coarest image scale
useContext bool type argument specifying whether to use document context for signature detection

DLSignatureDetect::~DLSignatureDetect (  ) 

DLSignatureDetect Destructor


Member Function Documentation

list<DLSignatureCandidate> DLSignatureDetect::dlGetDetectedSignatures (  )  [inline]

Return the list of detected signatures

Returns:
list <DLSignatureCandidate> the list of detected signature candidates

bool DLSignatureDetect::dlGotSignatures (  )  [inline]

Check whether any signature is detected on the document page

Returns:
true if at least one signature is detected


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

SignatureDetectDOCLIB Library is an add-on of DOCLIB. DOCLIB is being developed under contract by a collaboration between:
The Laboratory for Language and Media Processing
Unviersity of Maryland, College Park
and
Booz | Allen | Hamilton

All Rights Reserved, 2003-2007