CVB++ 14.1
Cvb::ShapeFinder2 Namespace Reference

Namespace for the ShapeFinder2 package. More...

Namespaces

namespace  Filter
 Namespace for collection of filter functions from the ShapeFinder2 package.
 

Classes

class  Classifier
 ShapeFinder2 classifier object. More...
 
class  ClassifierFactory
 ShapeFinder2 classifier factory object. More...
 
class  SearchResult
 Search result as returned by the classifier. More...
 

Typedefs

using ClassifierPtr = std::shared_ptr< Classifier >
 ShapeFinder classifier object.
 

Enumerations

enum class  ContrastMode { Normal = 0 , Inverse = 1 }
 Normal contrast features. More...
 
enum class  PrecisionMode { NoCorrelation = 0 , CorrelationCoarse = 1 , CorrelationFine = 2 }
 Controls precision over accuracy for ShapeFinder 1 type searches. More...
 
enum class  GradientType { Roberts = 0 , Sobel = 1 }
 Type of Gradient used for feature extraction. More...
 
enum class  CudaStatus { Default = 0 , ForceDisable = 1 }
 ShapeFinder2 CUDA status enum. More...
 

Detailed Description

Namespace for the ShapeFinder2 package.

Online Manual
Common Vision Blox-Tool ShapeFinder
Example
ShapeFinder2/QtShapeFinder2
Remarks
CMake users: Link to imported target CVB::CvbShapeFinder2

Enumeration Type Documentation

◆ ContrastMode

enum class ContrastMode
strong

Normal contrast features.

Enumerator
Normal 

Normal contrast features.

Inverse 

Inverted contrast features.

◆ CudaStatus

enum class CudaStatus
strong

ShapeFinder2 CUDA status enum.

Enumerator
Default 

Use CUDA if available.

ForceDisable 

User disabled CUDA.

◆ GradientType

enum class GradientType
strong

Type of Gradient used for feature extraction.

Enumerator
Roberts 

Roberts edge filter.

Sobel 

Sobel edge filter.

◆ PrecisionMode

enum class PrecisionMode
strong

Controls precision over accuracy for ShapeFinder 1 type searches.

Enumerator
NoCorrelation 

In the NoCorrelation mode, only the ShapeFinder edge model will be searched.

CorrelationCoarse 

In the CorrelationCoarse mode, after the initial edge model search a correlation and hill climbing will be performed on the preliminary result using the coarse layer of the model.

CorrelationFine 

In the CorrelationFine mode, after the initial edge model search a correlation and hill climbing will be performed on the preliminary result using the fine layer of the model.