DLLogoDetect Class Reference

DLLogoDetect provides the implementation of the multi-scale logo detection and extraction approach by Zhu and Doermann at ICDAR 2007. It returns the most likely logo candidate on each page whose computed scores are above the specified detection threshold. A higher detection threshold leads to better precision (i.e. higher chance of being really a logo), but may lower the recall. A default detection threshold is used if that parameter is ignored by the user. More...

#include <DLLogoDetect.h>

List of all members.

Public Member Functions

 DLLogoDetect (const char *fname, double threshold=MIN_SCORE)
 DLLogoDetect (const DLImage &srcImage, const char *fname, double threshold=MIN_SCORE)
list< DLLogoCandidatedlGetDetectedLogos ()
bool dlGotLogo ()


Detailed Description

DLLogoDetect provides the implementation of the multi-scale logo detection and extraction approach by Zhu and Doermann at ICDAR 2007. It returns the most likely logo candidate on each page whose computed scores are above the specified detection threshold. A higher detection threshold leads to better precision (i.e. higher chance of being really a logo), but may lower the recall. A default detection threshold is used if that parameter is ignored by the user.

The idea of DLLogoDetect is to robustly classifies and precisely localizes logos using a boosting strategy across multiple image scales. At a coarse scale, a trained Fisher classifier performs an initial classification using features from document context and connected components. Each logo candidate region is further classified at successively finer image scales by a cascade of classifiers, which allows false alarms to be quickly discarded and the detected region to be refined.

We assume that the logo in each document appears on the top one third of the document. If more than one logos are present on a document, the one with highest computed score is selected.


Constructor & Destructor Documentation

DLLogoDetect::DLLogoDetect ( const char *  fname,
double  threshold = MIN_SCORE 
)

Default DLLogoDetect Constructor. Initialize logo detector using the file name specified

Parameters:
fname file name of the source image
threshold detection threshold. A reasonable range of detection threshold is above 600. Higher detection threshold gives better precision, but may lower the recall.

DLLogoDetect::DLLogoDetect ( const DLImage &  srcImage,
const char *  fname,
double  threshold = MIN_SCORE 
)

Default DLLogoDetect Constructorl Initialize logo detector using the supplied DLImage

Parameters:
srcImage source image to process
fname file name of the source image if available
threshold detection threshold. A reasonable range of detection threshold is above 600. Higher detection threshold gives better precision, but may lower the recall.


Member Function Documentation

list<DLLogoCandidate> DLLogoDetect::dlGetDetectedLogos (  )  [inline]

Return the detected logo

Returns:
the detected logo of DLLogoCandidate type. The list is empty is none logo is detected

bool DLLogoDetect::dlGotLogo (  )  [inline]

Check whether any logo is detected on the document page

Returns:
true if at least one logo is detected


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

LogoDetectDOCLIB 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