keystoneml.nodes.images

DaisyExtractor

class DaisyExtractor extends Transformer[Image, DenseMatrix[Float]]

Computes DAISY feature descriptors as specified in [1]. Returns the features at a regular spaced grid.

[1] Engin Tola, Vincent Lepetit, and Pascal Fua, "DAISY: An Efficient Dense Descriptor Applied to Wide-Baseline Stereo." IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 32, No. 5, 2010.

Based on code by Ben Recht <brecht@cs.berkeley.edu>

Linear Supertypes
Transformer[Image, DenseMatrix[Float]], Chainable[Image, DenseMatrix[Float]], TransformerOperator, Serializable, Serializable, Operator, AnyRef, Any
Ordering
  1. Alphabetic
  2. By inheritance
Inherited
  1. DaisyExtractor
  2. Transformer
  3. Chainable
  4. TransformerOperator
  5. Serializable
  6. Serializable
  7. Operator
  8. AnyRef
  9. Any
  1. Hide All
  2. Show all
Learn more about member selection
Visibility
  1. Public
  2. All

Instance Constructors

  1. new DaisyExtractor(daisyT: Int = 8, daisyQ: Int = 3, daisyR: Int = 7, daisyH: Int = 8, pixelBorder: Int = 16, stride: Int = 4, patchSize: Int = 24)

    daisyT

    Number of histograms at a single layer

    daisyQ

    Number of convolved orientations layers with different sigmas

    daisyR

    Distance from the center pixel to the outer most grid point

    daisyH

    Number of bins in the histogram

    pixelBorder

    Starting offset for keypoints

    stride

    Stride for keypoints on the grid

    patchSize

    Size of neighborhood to consider for constructing patches

Value Members

  1. final def !=(arg0: AnyRef): Boolean

    Definition Classes
    AnyRef
  2. final def !=(arg0: Any): Boolean

    Definition Classes
    Any
  3. final def ##(): Int

    Definition Classes
    AnyRef → Any
  4. final def ==(arg0: AnyRef): Boolean

    Definition Classes
    AnyRef
  5. final def ==(arg0: Any): Boolean

    Definition Classes
    Any
  6. final def andThen[C, L](est: LabelEstimator[DenseMatrix[Float], C, L], data: PipelineDataset[Image], labels: PipelineDataset[L]): Pipeline[Image, C]

    Chains a label estimator onto the end of this pipeline, producing a new pipeline.

    Chains a label estimator onto the end of this pipeline, producing a new pipeline. If this pipeline has already been executed, it will not need to be fit again.

    est

    The estimator to chain onto the end of this pipeline

    data

    The training data to use (the estimator will be fit on the result of passing this data through the current pipeline)

    labels

    The labels to use when fitting the LabelEstimator. Must be zippable with the training data.

    Definition Classes
    Chainable
  7. final def andThen[C, L](est: LabelEstimator[DenseMatrix[Float], C, L], data: RDD[Image], labels: PipelineDataset[L]): Pipeline[Image, C]

    Chains a label estimator onto the end of this pipeline, producing a new pipeline.

    Chains a label estimator onto the end of this pipeline, producing a new pipeline. If this pipeline has already been executed, it will not need to be fit again.

    est

    The estimator to chain onto the end of this pipeline

    data

    The training data to use (the estimator will be fit on the result of passing this data through the current pipeline)

    labels

    The labels to use when fitting the LabelEstimator. Must be zippable with the training data.

    Definition Classes
    Chainable
  8. final def andThen[C, L](est: LabelEstimator[DenseMatrix[Float], C, L], data: PipelineDataset[Image], labels: RDD[L]): Pipeline[Image, C]

    Chains a label estimator onto the end of this pipeline, producing a new pipeline.

    Chains a label estimator onto the end of this pipeline, producing a new pipeline. If this pipeline has already been executed, it will not need to be fit again.

    est

    The estimator to chain onto the end of this pipeline

    data

    The training data to use (the estimator will be fit on the result of passing this data through the current pipeline)

    labels

    The labels to use when fitting the LabelEstimator. Must be zippable with the training data.

    Definition Classes
    Chainable
  9. final def andThen[C, L](est: LabelEstimator[DenseMatrix[Float], C, L], data: RDD[Image], labels: RDD[L]): Pipeline[Image, C]

    Chains a label estimator onto the end of this pipeline, producing a new pipeline.

    Chains a label estimator onto the end of this pipeline, producing a new pipeline. If this pipeline has already been executed, it will not need to be fit again.

    est

    The estimator to chain onto the end of this pipeline

    data

    The training data to use (the estimator will be fit on the result of passing this data through the current pipeline)

    labels

    The labels to use when fitting the LabelEstimator. Must be zippable with the training data.

    Definition Classes
    Chainable
  10. final def andThen[C](est: Estimator[DenseMatrix[Float], C], data: PipelineDataset[Image]): Pipeline[Image, C]

    Chains an estimator onto the end of this pipeline, producing a new pipeline.

    Chains an estimator onto the end of this pipeline, producing a new pipeline. If this pipeline has already been executed, it will not need to be fit again.

    est

    The estimator to chain onto the end of this pipeline

    data

    The training data to use (the estimator will be fit on the result of passing this data through the current pipeline)

    Definition Classes
    Chainable
  11. final def andThen[C](est: Estimator[DenseMatrix[Float], C], data: RDD[Image]): Pipeline[Image, C]

    Chains an estimator onto the end of this pipeline, producing a new pipeline.

    Chains an estimator onto the end of this pipeline, producing a new pipeline. If this pipeline has already been executed, it will not need to be fit again.

    est

    The estimator to chain onto the end of this pipeline

    data

    The training data to use (the estimator will be fit on the result of passing this data through the current pipeline)

    Definition Classes
    Chainable
  12. final def andThen[C](next: Chainable[DenseMatrix[Float], C]): Pipeline[Image, C]

    Chains a pipeline onto the end of this one, producing a new pipeline.

    Chains a pipeline onto the end of this one, producing a new pipeline. If either this pipeline or the following has already been executed, it will not need to be fit again.

    next

    the pipeline to chain

    Definition Classes
    Chainable
  13. def apply(in: Image): DenseMatrix[Float]

    Computes daisy features of an image.

    Computes daisy features of an image.

    in

    Image

    returns

    Daisy features.

    Definition Classes
    DaisyExtractorTransformer
  14. def apply(in: RDD[Image]): RDD[DenseMatrix[Float]]

    The application of this Transformer to an RDD of input items.

    The application of this Transformer to an RDD of input items. This method may optionally be overridden by ML developers.

    in

    The bulk RDD input to pass into this transformer

    returns

    The bulk RDD output for the given input

    Definition Classes
    Transformer
  15. final def asInstanceOf[T0]: T0

    Definition Classes
    Any
  16. def clone(): AnyRef

    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  17. val convThreshold: Double

  18. val daisyFeatureSize: Int

  19. val daisyH: Int

    Number of bins in the histogram

  20. val daisyQ: Int

    Number of convolved orientations layers with different sigmas

  21. val daisyR: Int

    Distance from the center pixel to the outer most grid point

  22. val daisySigmaSq: IndexedSeq[Double]

  23. val daisySigmaSqDiff: IndexedSeq[Double]

  24. val daisyT: Int

    Number of histograms at a single layer

  25. final def eq(arg0: AnyRef): Boolean

    Definition Classes
    AnyRef
  26. def equals(arg0: Any): Boolean

    Definition Classes
    AnyRef → Any
  27. def execute(deps: Seq[Expression]): Expression

    Definition Classes
    TransformerOperator → Operator
  28. val featureThreshold: Double

  29. val filter1: Array[Double]

  30. val filter2: Array[Double]

  31. def finalize(): Unit

    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  32. val g: Array[Array[Double]]

  33. final def getClass(): Class[_]

    Definition Classes
    AnyRef → Any
  34. def hashCode(): Int

    Definition Classes
    AnyRef → Any
  35. final def isInstanceOf[T0]: Boolean

    Definition Classes
    Any
  36. def label: String

    Definition Classes
    Operator
  37. final def ne(arg0: AnyRef): Boolean

    Definition Classes
    AnyRef
  38. def normalize(x: DenseVector[Double]): DenseVector[Double]

  39. final def notify(): Unit

    Definition Classes
    AnyRef
  40. final def notifyAll(): Unit

    Definition Classes
    AnyRef
  41. val patchSize: Int

    Size of neighborhood to consider for constructing patches

  42. val pixelBorder: Int

    Starting offset for keypoints

  43. val stride: Int

    Stride for keypoints on the grid

  44. final def synchronized[T0](arg0: ⇒ T0): T0

    Definition Classes
    AnyRef
  45. val tDaisy: IndexedSeq[Int]

  46. def toPipeline: Pipeline[Image, DenseMatrix[Float]]

    A method that converts this object into a Pipeline.

    A method that converts this object into a Pipeline. Must be implemented by anything that extends Chainable.

    Definition Classes
    TransformerChainable
  47. def toString(): String

    Definition Classes
    AnyRef → Any
  48. final def wait(): Unit

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  49. final def wait(arg0: Long, arg1: Int): Unit

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  50. final def wait(arg0: Long): Unit

    Definition Classes
    AnyRef
    Annotations
    @throws( ... )

Inherited from Transformer[Image, DenseMatrix[Float]]

Inherited from Chainable[Image, DenseMatrix[Float]]

Inherited from TransformerOperator

Inherited from Serializable

Inherited from Serializable

Inherited from Operator

Inherited from AnyRef

Inherited from Any

Ungrouped