EInterestPointLocator Class
EasyLocate tool - interest point version.
The EInterestPointLocator locates and classifies objects (or defects). With this class, an object is defined by its position it and a label (see ELocatorObject class). The tool must be trained using a dataset with annotated objects.
The minimum size resolution supported by the tool is 128. The maximum size of the image supported is 500 000 pixels.
The tool has 5 main parameters:
- The object size (EInterestPointLocator::ObjectSize) to indicate an approximate size for the interest point that you want to detect.
- A detection threshold (ELocatorBase::DetectionThreshold) to accept or reject predicted objects based on their score.
- The maximum number of objects in an image (ELocatorBase::MaxNumberOfObjects)
- The maximum proximity or the minimum distance between predicted objects with the same label (EInterestPointLocator::SameLabelMinDistance, ELocatorBase::SameLabelMaxObjectProximity).
- The maximum proximity or the minimum distance between predicted objects regardless of their label (EInterestPointLocator::AbsoluteMinDistance, ELocatorBase::AbsoluteMaxObjectProximity).
The proximity is defined as max(0, EInterestPointLocator::ObjectSize - d) / (EInterestPointLocator::ObjectSize + d) where d is the manhattan distance.
Except for the EInterestPointLocator::ObjectSize, all the parameters can be changed before and after training the tool.
Base Class:ELocatorBase
Namespace: Euresys::Open_eVision::EasyDeepLearning
Methods
This value must be between 0 and EInterestPointLocator::ObjectSize. It is internally converted to ELocatorBase::AbsoluteMaxObjectProximity. Default value: 0.
This value must be between 0 and EInterestPointLocator::ObjectSize. It is internally converted to ELocatorBase::SameLabelMaxObjectProximity. Default value: EInterestPointLocator::ObjectSize / 3.
This value must be between 0 and EInterestPointLocator::ObjectSize. It is internally converted to ELocatorBase::AbsoluteMaxObjectProximity. Default value: 0.
This value must be between 0 and EInterestPointLocator::ObjectSize. It is internally converted to ELocatorBase::SameLabelMaxObjectProximity. Default value: EInterestPointLocator::ObjectSize / 3.
EInterestPointLocator Class
EasyLocate tool - interest point version.
The EInterestPointLocator locates and classifies objects (or defects). With this class, an object is defined by its position it and a label (see ELocatorObject class). The tool must be trained using a dataset with annotated objects.
The minimum size resolution supported by the tool is 128. The maximum size of the image supported is 500 000 pixels.
The tool has 5 main parameters:
- The object size (EInterestPointLocator::ObjectSize) to indicate an approximate size for the interest point that you want to detect.
- A detection threshold (ELocatorBase::DetectionThreshold) to accept or reject predicted objects based on their score.
- The maximum number of objects in an image (ELocatorBase::MaxNumberOfObjects)
- The maximum proximity or the minimum distance between predicted objects with the same label (EInterestPointLocator::SameLabelMinDistance, ELocatorBase::SameLabelMaxObjectProximity).
- The maximum proximity or the minimum distance between predicted objects regardless of their label (EInterestPointLocator::AbsoluteMinDistance, ELocatorBase::AbsoluteMaxObjectProximity).
The proximity is defined as max(0, EInterestPointLocator::ObjectSize - d) / (EInterestPointLocator::ObjectSize + d) where d is the manhattan distance.
Except for the EInterestPointLocator::ObjectSize, all the parameters can be changed before and after training the tool.
Base Class:ELocatorBase
Namespace: Euresys.Open_eVision.EasyDeepLearning
Properties
This value must be between 0 and EInterestPointLocator::ObjectSize. It is internally converted to ELocatorBase::AbsoluteMaxObjectProximity. Default value: 0.
This value must be between 0 and EInterestPointLocator::ObjectSize. It is internally converted to ELocatorBase::SameLabelMaxObjectProximity. Default value: EInterestPointLocator::ObjectSize / 3.
Methods