Package boofcv.abst.scene.ann

Class FeatureSceneRecognitionNearestNeighbor<TD extends TupleDesc<TD>>

java.lang.Object

boofcv.abst.scene.ann.FeatureSceneRecognitionNearestNeighbor<TD>

All Implemented Interfaces:

FeatureSceneRecognition<TD>, VerbosePrint

public class FeatureSceneRecognitionNearestNeighbor<TD extends TupleDesc<TD>>
extends Object
implements FeatureSceneRecognition<TD>

Wrapper around RecognitionNearestNeighborInvertedFile for FeatureSceneRecognition.

Nested Class Summary

Nested classes/interfaces inherited from interface boofcv.abst.scene.FeatureSceneRecognition

FeatureSceneRecognition.Features<TD extends TupleDesc<TD>>

Field Summary

Fields

Modifier and Type	Field	Description
int	minimumForThread	Performance tuning.

Constructor Summary

Constructors

Constructor	Description
FeatureSceneRecognitionNearestNeighbor(ConfigRecognitionNearestNeighbor config, Factory<TD> factory)

Method Summary

Modifier and Type	Method	Description
void	addImage(String id, FeatureSceneRecognition.Features<TD> features)	Adds a new image to the database
void	clearDatabase()	Removes all images from the database.
Class<TD>	getDescriptorType()	The image data type which can be processed
List<String>	getImageIds(@Nullable List<String> storage)	Returns a list of image IDs in the database
int	getQueryWord(int featureIdx)	Returns a single word which describes this image feature.
void	getQueryWords(int featureIdx, DogArray_I32 words)	Used to retrieve all the words a feature is associated with.
int	getTotalWords()	Returns the number of unique words.
void	learnModel(Iterator<FeatureSceneRecognition.Features<TD>> images)	Learns a model using the already extracted image features
int	lookupWord(TD description)
void	lookupWords(TD description, DogArray_I32 words)
boolean	query(FeatureSceneRecognition.Features<TD> query, @Nullable BoofLambdas.Filter<String> filter, int limit, DogArray<SceneRecognition.Match> matches)	Finds the best matches in the database to the query image.
void	setDictionary(List<TD> dictionary)	Replaces the old dictionary with the new dictionary.
void	setVerbose(@Nullable PrintStream out, @Nullable Set<String> config)

Methods inherited from class java.lang.Object

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

Field Details

minimumForThread

public int minimumForThread

Performance tuning. If less than this number of features a single thread algorithm will be used

Constructor Details

FeatureSceneRecognitionNearestNeighbor

public FeatureSceneRecognitionNearestNeighbor(ConfigRecognitionNearestNeighbor config,
 Factory<TD> factory)

Method Details

learnModel

public void learnModel(Iterator<FeatureSceneRecognition.Features<TD>> images)

Description copied from interface: FeatureSceneRecognition

Learns a model using the already extracted image features

Specified by:

learnModel in interface FeatureSceneRecognition<TD extends TupleDesc<TD>>

clearDatabase

public void clearDatabase()

Description copied from interface: FeatureSceneRecognition

Removes all images from the database. The model is not modified

Specified by:

clearDatabase in interface FeatureSceneRecognition<TD extends TupleDesc<TD>>

addImage

public void addImage(String id,
 FeatureSceneRecognition.Features<TD> features)

Description copied from interface: FeatureSceneRecognition

Adds a new image to the database

Specified by:

addImage in interface FeatureSceneRecognition<TD extends TupleDesc<TD>>

Parameters:

id - The unique ID for this image

features - All the features in this image

getImageIds

public List<String> getImageIds(@Nullable
 @Nullable List<String> storage)

Description copied from interface: FeatureSceneRecognition

Returns a list of image IDs in the database

Specified by:

getImageIds in interface FeatureSceneRecognition<TD extends TupleDesc<TD>>

Parameters:

storage - (Optional) Storage for the list of images. If null a new instance is created

Returns:

List of all the image IDs.

query

public boolean query(FeatureSceneRecognition.Features<TD> query,
 @Nullable BoofLambdas.Filter<String> filter,
 int limit,
 DogArray<SceneRecognition.Match> matches)

Description copied from interface: FeatureSceneRecognition

Finds the best matches in the database to the query image. The filter can (optionally) be used to remove matches which are not of interest, i.e. too close in time.

Specified by:

query in interface FeatureSceneRecognition<TD extends TupleDesc<TD>>

Parameters:

query - (Input) Features in the query image

filter - (Input) Filter results by ID. true = keep, false = reject. Null means no filter.

limit - (Input) The maximum number of results it will return. If ≤ 0 then all matches are returned.

matches - (Output) Set of matches found in best first order. List is always cleared

Returns:

true if at least one valid match was found or false if no valid matches could be found. If false that means matches is empty. This is strictly a convenience.

setDictionary

public void setDictionary(List<TD> dictionary)

Replaces the old dictionary with the new dictionary.

Parameters:

dictionary - Dictionary of words

getQueryWord

public int getQueryWord(int featureIdx)

Description copied from interface: FeatureSceneRecognition

Returns a single word which describes this image feature. If multiple words describe a feature in its internal implementation then there is some ambiguity resolving logic.

Specified by:

getQueryWord in interface FeatureSceneRecognition<TD extends TupleDesc<TD>>

Parameters:

featureIdx - (Input) Index of the feature in the query.

Returns:

The word's ID. If no word is associated with this feature then -1 is returned.

getQueryWords

public void getQueryWords(int featureIdx,
 DogArray_I32 words)

Description copied from interface: FeatureSceneRecognition

Used to retrieve all the words a feature is associated with. If the internal implementation is hierarchical then words it passes through on the way a leaf could go in the words list.

Specified by:

getQueryWords in interface FeatureSceneRecognition<TD extends TupleDesc<TD>>

Parameters:

featureIdx - (Input) Index of the feature in the query.

words - (Output) Storage for all the words the feature is associated with

lookupWord

public int lookupWord(TD description)

Specified by:

lookupWord in interface FeatureSceneRecognition<TD extends TupleDesc<TD>>

lookupWords

public void lookupWords(TD description,
 DogArray_I32 words)

Specified by:

lookupWords in interface FeatureSceneRecognition<TD extends TupleDesc<TD>>

getTotalWords

public int getTotalWords()

Description copied from interface: FeatureSceneRecognition

Returns the number of unique words. it's assumed that the word ID's will occupy 0 to this value.

Specified by:

getTotalWords in interface FeatureSceneRecognition<TD extends TupleDesc<TD>>

getDescriptorType

public Class<TD> getDescriptorType()

Description copied from interface: FeatureSceneRecognition

The image data type which can be processed

Specified by:

getDescriptorType in interface FeatureSceneRecognition<TD extends TupleDesc<TD>>

setVerbose

public void setVerbose(@Nullable
 @Nullable PrintStream out,
 @Nullable
 @Nullable Set<String> config)

Specified by:

setVerbose in interface VerbosePrint