CVB.Net 14.1
Stemmer.Cvb.ShapeFinder2 Namespace Reference

Classes

class  Classifier
 ShapeFinder2 classifier object. More...
 
class  ClassifierFactory
 Object that aggregates the learning parameters and produces a ShapeFinder2 classifier More...
 
class  Filter
 Filter functions exported and used by the ShapeFinder library. More...
 
class  NamespaceDoc
 The namespace and assembly Stemmer.Cvb.ShapeFinder2 contains the classes and definitions needed for using the ShapeFinder 2 functionality from SF.dll. More...
 
struct  SearchResult
 A single ShapeFinder2 search result. More...
 

Enumerations

enum  ContrastMode { Normal = 0 , Inverse = 1 }
 Contrast mode for feature extraction. More...
 
enum  PrecisionMode { NoCorrelation = 0 , CorrelationCoarse = 1 , CorrelationFine = 2 }
 Search mode to be used. More...
 
enum  CudaStatus { Default , ForceDisable }
 Shapefinder2 CUDA status enum. More...
 

Enumeration Type Documentation

◆ ContrastMode

Contrast mode for feature extraction.

Enumerator
Normal 

Normal contrast features.

Inverse 

Inverted contrast features.

◆ CudaStatus

enum CudaStatus

Shapefinder2 CUDA status enum.

Enumerator
Default 

Use CUDA if available

ForceDisable 

User disabled CUDA

◆ PrecisionMode

Search mode to be used.

Enumerator
NoCorrelation 

In the NoCorrelation mode, only the ShapeFinder edge model will be searched. Not subsequent additional correlation step will be carried out to improve result accuracy. Results in this mode are pixel- accurate only. This search mode is the fastest available.

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. This usually improves the overall result quality and allows for sub-pixel accurate results. As the correlations will be calculate on the coarse layer this mode is a trade-off between speed and accuracy.

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. This usually improves the overall result quality and allows for sub-pixel accurate results.