Package org.anchoranalysis.image.inference.bean.segment.instance

Class SuppressNonMaximum<T extends InferenceModel>

Object

AnchorBean<SegmentStackIntoObjectsPooled<T>>

InitializableBean<SegmentStackIntoObjectsPooled<T>,ImageInitialization>

ImageBean<SegmentStackIntoObjectsPooled<T>>

SegmentationBean<SegmentStackIntoObjectsPooled<T>>

SegmentStackIntoObjectsPooled<T>

SuppressNonMaximum<T>

Type Parameters:

T - model-type

public class SuppressNonMaximum<T extends InferenceModel>
extends SegmentStackIntoObjectsPooled<T>

Applies a segmentation procedure followed by non-maximum suppression.

Author:

Owen Feehan

Constructor Summary

Constructors

Constructor	Description
SuppressNonMaximum()
SuppressNonMaximum(SegmentStackIntoObjectsPooled<T> segment)	Creates with a particular segmentation algorithm as an input.
SuppressNonMaximum(SegmentStackIntoObjectsPooled<T> segment, ReduceElements<ObjectMask> reduce, boolean separateEachLabel)	Creates a new SuppressNonMaximum instance.

Method Summary

Modifier and Type	Method	Description
ConcurrentModelPool<T>	createModelPool(ConcurrencyPlan plan, Logger logger)	Creates the model pool (to be used by multiple threads).
ReduceElements<ObjectMask>	getReduce()	The algorithm for reducing the number of object-masks.
SegmentStackIntoObjectsPooled<T>	getSegment()	The segmentation algorithm that is applied as an input to non-maximum suppression.
boolean	isSeparateEachLabel()	If true, each label is reduced separately. if false, all labels are reduced together.
SegmentedObjects	segment(Stack stack, ConcurrentModelPool<T> modelPool, ExecutionTimeRecorder executionTimeRecorder)	Segments a stack to produce an object-collection.
void	setReduce(ReduceElements<ObjectMask> reduce)	The algorithm for reducing the number of object-masks.
void	setSegment(SegmentStackIntoObjectsPooled<T> segment)	The segmentation algorithm that is applied as an input to non-maximum suppression.
void	setSeparateEachLabel(boolean separateEachLabel)	If true, each label is reduced separately. if false, all labels are reduced together.

Methods inherited from class org.anchoranalysis.image.inference.bean.segment.instance.SegmentStackIntoObjectsPooled

resolve, segment

Methods inherited from class org.anchoranalysis.bean.initializable.InitializableBean

getInitialization, getLogger, getPropertyInitializer, initialize, initializeRecursive, initRecursiveWithInitializer, isInitialized, onInitialization

Methods inherited from class org.anchoranalysis.bean.AnchorBean

checkMisconfigured, describeBean, describeChildren, duplicateBean, fields, findFieldsOfClass, getBeanName, getLocalPath, localise, toString

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Constructor Details

SuppressNonMaximum

public SuppressNonMaximum(SegmentStackIntoObjectsPooled<T> segment)

Creates with a particular segmentation algorithm as an input.

Parameters:

segment - the segmentation algorithm to use, before applying non-maximum suppression.

SuppressNonMaximum

public SuppressNonMaximum()

SuppressNonMaximum

public SuppressNonMaximum(SegmentStackIntoObjectsPooled<T> segment,
 ReduceElements<ObjectMask> reduce,
 boolean separateEachLabel)

Creates a new SuppressNonMaximum instance.

Parameters:

segment - The segmentation algorithm that is applied as an input to non-maximum suppression.

reduce - The algorithm for reducing the number of object-masks.

separateEachLabel - If true, each label is reduced separately. if false, all labels are reduced together.

Method Details

createModelPool

public ConcurrentModelPool<T> createModelPool(ConcurrencyPlan plan,
 Logger logger)
                                       throws CreateModelFailedException

Description copied from class: SegmentStackIntoObjectsPooled

Creates the model pool (to be used by multiple threads).

Specified by:

createModelPool in class SegmentStackIntoObjectsPooled<T extends InferenceModel>

Parameters:

plan - the number and types of processors available for concurrent execution.

logger - the logger.

Returns:

the newly created model pool.

Throws:

CreateModelFailedException - if a model cannot be created.

segment

public SegmentedObjects segment(Stack stack,
 ConcurrentModelPool<T> modelPool,
 ExecutionTimeRecorder executionTimeRecorder)
                         throws SegmentationFailedException

Description copied from class: SegmentStackIntoObjectsPooled

Segments a stack to produce an object-collection.

Any created objects will always exist inside the stack's Extent.

Specified by:

segment in class SegmentStackIntoObjectsPooled<T extends InferenceModel>

Parameters:

stack - the stack to segment.

modelPool - the pool of model instances which can each be used for inference (in parallel).

executionTimeRecorder - measures execution-times of particular operations.

Returns:

a collection of objects with corresponding confidence scores.

Throws:

SegmentationFailedException - if anything goes wrong during the segmentation.

getSegment

public SegmentStackIntoObjectsPooled<T> getSegment()

The segmentation algorithm that is applied as an input to non-maximum suppression.

setSegment

public void setSegment(SegmentStackIntoObjectsPooled<T> segment)

The segmentation algorithm that is applied as an input to non-maximum suppression.

getReduce

public ReduceElements<ObjectMask> getReduce()

The algorithm for reducing the number of object-masks.

setReduce

public void setReduce(ReduceElements<ObjectMask> reduce)

The algorithm for reducing the number of object-masks.

isSeparateEachLabel

public boolean isSeparateEachLabel()

If true, each label is reduced separately. if false, all labels are reduced together.

setSeparateEachLabel

public void setSeparateEachLabel(boolean separateEachLabel)

If true, each label is reduced separately. if false, all labels are reduced together.