@spec compute(t(), [Evision.Mat.maybe_mat_in()], [[Evision.KeyPoint.t()]]) ::
  {[[Evision.KeyPoint.t()]], [Evision.Mat.t()]} | {:error, String.t()}

@spec compute(t(), Evision.Mat.maybe_mat_in(), [Evision.KeyPoint.t()]) ::
  {[Evision.KeyPoint.t()], Evision.Mat.t()} | {:error, String.t()}

Variant 1:

compute

Positional Arguments

• self: Evision.ORB.t()

• images: [Evision.Mat].

  Image set.

Return

• keypoints: [[Evision.KeyPoint]].

  Input collection of keypoints. Keypoints for which a descriptor cannot be computed are removed. Sometimes new keypoints can be added, for example: SIFT duplicates keypoint with several dominant orientations (for each orientation).

• descriptors: [Evision.Mat].

  Computed descriptors. In the second variant of the method descriptors[i] are descriptors computed for a keypoints[i]. Row j is the keypoints (or keypoints[i]) is the descriptor for keypoint j-th keypoint.

Has overloading in C++

Python prototype (for reference only):

compute(images, keypoints[, descriptors]) -> keypoints, descriptors

Variant 2:

Computes the descriptors for a set of keypoints detected in an image (first variant) or image set (second variant).

Positional Arguments

• self: Evision.ORB.t()

• image: Evision.Mat.

  Image.

Return

• keypoints: [Evision.KeyPoint].

  Input collection of keypoints. Keypoints for which a descriptor cannot be computed are removed. Sometimes new keypoints can be added, for example: SIFT duplicates keypoint with several dominant orientations (for each orientation).

• descriptors: Evision.Mat.t().

  Computed descriptors. In the second variant of the method descriptors[i] are descriptors computed for a keypoints[i]. Row j is the keypoints (or keypoints[i]) is the descriptor for keypoint j-th keypoint.

Python prototype (for reference only):

compute(image, keypoints[, descriptors]) -> keypoints, descriptors

@spec compute(
  t(),
  [Evision.Mat.maybe_mat_in()],
  [[Evision.KeyPoint.t()]],
  [{atom(), term()}, ...] | nil
) :: {[[Evision.KeyPoint.t()]], [Evision.Mat.t()]} | {:error, String.t()}

@spec compute(
  t(),
  Evision.Mat.maybe_mat_in(),
  [Evision.KeyPoint.t()],
  [{atom(), term()}, ...] | nil
) ::
  {[Evision.KeyPoint.t()], Evision.Mat.t()} | {:error, String.t()}

Variant 1:

compute

Positional Arguments

• self: Evision.ORB.t()

• images: [Evision.Mat].

  Image set.

Return

• keypoints: [[Evision.KeyPoint]].

  Input collection of keypoints. Keypoints for which a descriptor cannot be computed are removed. Sometimes new keypoints can be added, for example: SIFT duplicates keypoint with several dominant orientations (for each orientation).

• descriptors: [Evision.Mat].

  Computed descriptors. In the second variant of the method descriptors[i] are descriptors computed for a keypoints[i]. Row j is the keypoints (or keypoints[i]) is the descriptor for keypoint j-th keypoint.

Has overloading in C++

Python prototype (for reference only):

compute(images, keypoints[, descriptors]) -> keypoints, descriptors

Variant 2:

Computes the descriptors for a set of keypoints detected in an image (first variant) or image set (second variant).

Positional Arguments

• self: Evision.ORB.t()

• image: Evision.Mat.

  Image.

Return

• keypoints: [Evision.KeyPoint].

  Input collection of keypoints. Keypoints for which a descriptor cannot be computed are removed. Sometimes new keypoints can be added, for example: SIFT duplicates keypoint with several dominant orientations (for each orientation).

• descriptors: Evision.Mat.t().

  Computed descriptors. In the second variant of the method descriptors[i] are descriptors computed for a keypoints[i]. Row j is the keypoints (or keypoints[i]) is the descriptor for keypoint j-th keypoint.

Python prototype (for reference only):

compute(image, keypoints[, descriptors]) -> keypoints, descriptors

@spec create() :: t() | {:error, String.t()}

The ORB constructor

Keyword Arguments

• nfeatures: integer().

  The maximum number of features to retain.

• scaleFactor: float.

  Pyramid decimation ratio, greater than 1. scaleFactor==2 means the classical pyramid, where each next level has 4x less pixels than the previous, but such a big scale factor will degrade feature matching scores dramatically. On the other hand, too close to 1 scale factor will mean that to cover certain scale range you will need more pyramid levels and so the speed will suffer.

• nlevels: integer().

  The number of pyramid levels. The smallest level will have linear size equal to input_image_linear_size/pow(scaleFactor, nlevels - firstLevel).

• edgeThreshold: integer().

  This is size of the border where the features are not detected. It should roughly match the patchSize parameter.

• firstLevel: integer().

  The level of pyramid to put source image to. Previous layers are filled with upscaled source image.

• wTA_K: integer().

  The number of points that produce each element of the oriented BRIEF descriptor. The default value 2 means the BRIEF where we take a random point pair and compare their brightnesses, so we get 0/1 response. Other possible values are 3 and 4. For example, 3 means that we take 3 random points (of course, those point coordinates are random, but they are generated from the pre-defined seed, so each element of BRIEF descriptor is computed deterministically from the pixel rectangle), find point of maximum brightness and output index of the winner (0, 1 or 2). Such output will occupy 2 bits, and therefore it will need a special variant of Hamming distance, denoted as NORM_HAMMING2 (2 bits per bin). When WTA_K=4, we take 4 random points to compute each bin (that will also occupy 2 bits with possible values 0, 1, 2 or 3).

• scoreType: ORB_ScoreType.

  The default HARRIS_SCORE means that Harris algorithm is used to rank features (the score is written to KeyPoint::score and is used to retain best nfeatures features); FAST_SCORE is alternative value of the parameter that produces slightly less stable keypoints, but it is a little faster to compute.

• patchSize: integer().

  size of the patch used by the oriented BRIEF descriptor. Of course, on smaller pyramid layers the perceived image area covered by a feature will be larger.

• fastThreshold: integer().

  the fast threshold

Return

• retval: Evision.ORB.t()

Python prototype (for reference only):

create([, nfeatures[, scaleFactor[, nlevels[, edgeThreshold[, firstLevel[, WTA_K[, scoreType[, patchSize[, fastThreshold]]]]]]]]]) -> retval

@spec create(Keyword.t()) :: any() | {:error, String.t()}

@spec create(
  [
    edgeThreshold: term(),
    fastThreshold: term(),
    firstLevel: term(),
    nfeatures: term(),
    nlevels: term(),
    patchSize: term(),
    scaleFactor: term(),
    scoreType: term(),
    wTA_K: term()
  ]
  | nil
) :: t() | {:error, String.t()}

The ORB constructor

Keyword Arguments

• nfeatures: integer().

  The maximum number of features to retain.

• scaleFactor: float.

  Pyramid decimation ratio, greater than 1. scaleFactor==2 means the classical pyramid, where each next level has 4x less pixels than the previous, but such a big scale factor will degrade feature matching scores dramatically. On the other hand, too close to 1 scale factor will mean that to cover certain scale range you will need more pyramid levels and so the speed will suffer.

• nlevels: integer().

  The number of pyramid levels. The smallest level will have linear size equal to input_image_linear_size/pow(scaleFactor, nlevels - firstLevel).

• edgeThreshold: integer().

  This is size of the border where the features are not detected. It should roughly match the patchSize parameter.

• firstLevel: integer().

  The level of pyramid to put source image to. Previous layers are filled with upscaled source image.

• wTA_K: integer().

  The number of points that produce each element of the oriented BRIEF descriptor. The default value 2 means the BRIEF where we take a random point pair and compare their brightnesses, so we get 0/1 response. Other possible values are 3 and 4. For example, 3 means that we take 3 random points (of course, those point coordinates are random, but they are generated from the pre-defined seed, so each element of BRIEF descriptor is computed deterministically from the pixel rectangle), find point of maximum brightness and output index of the winner (0, 1 or 2). Such output will occupy 2 bits, and therefore it will need a special variant of Hamming distance, denoted as NORM_HAMMING2 (2 bits per bin). When WTA_K=4, we take 4 random points to compute each bin (that will also occupy 2 bits with possible values 0, 1, 2 or 3).

• scoreType: ORB_ScoreType.

  The default HARRIS_SCORE means that Harris algorithm is used to rank features (the score is written to KeyPoint::score and is used to retain best nfeatures features); FAST_SCORE is alternative value of the parameter that produces slightly less stable keypoints, but it is a little faster to compute.

• patchSize: integer().

  size of the patch used by the oriented BRIEF descriptor. Of course, on smaller pyramid layers the perceived image area covered by a feature will be larger.

• fastThreshold: integer().

  the fast threshold

Return

• retval: Evision.ORB.t()

Python prototype (for reference only):

create([, nfeatures[, scaleFactor[, nlevels[, edgeThreshold[, firstLevel[, WTA_K[, scoreType[, patchSize[, fastThreshold]]]]]]]]]) -> retval

@spec defaultNorm(Keyword.t()) :: any() | {:error, String.t()}

@spec defaultNorm(t()) :: integer() | {:error, String.t()}

defaultNorm

Positional Arguments

• self: Evision.ORB.t()

Return

• retval: integer()

Python prototype (for reference only):

defaultNorm() -> retval

@spec descriptorSize(Keyword.t()) :: any() | {:error, String.t()}

@spec descriptorSize(t()) :: integer() | {:error, String.t()}

descriptorSize

Positional Arguments

• self: Evision.ORB.t()

Return

• retval: integer()

Python prototype (for reference only):

descriptorSize() -> retval

@spec descriptorType(Keyword.t()) :: any() | {:error, String.t()}

@spec descriptorType(t()) :: integer() | {:error, String.t()}

descriptorType

Positional Arguments

• self: Evision.ORB.t()

Return

• retval: integer()

Python prototype (for reference only):

descriptorType() -> retval

@spec detect(t(), [Evision.Mat.maybe_mat_in()]) ::
  [[Evision.KeyPoint.t()]] | {:error, String.t()}

@spec detect(t(), Evision.Mat.maybe_mat_in()) ::
  [Evision.KeyPoint.t()] | {:error, String.t()}

Variant 1:

detect

Positional Arguments

• self: Evision.ORB.t()

• images: [Evision.Mat].

  Image set.

Keyword Arguments

• masks: [Evision.Mat].

  Masks for each input image specifying where to look for keypoints (optional). masks[i] is a mask for images[i].

Return

• keypoints: [[Evision.KeyPoint]].

  The detected keypoints. In the second variant of the method keypoints[i] is a set of keypoints detected in images[i] .

Has overloading in C++

Python prototype (for reference only):

detect(images[, masks]) -> keypoints

Variant 2:

Detects keypoints in an image (first variant) or image set (second variant).

Positional Arguments

• self: Evision.ORB.t()

• image: Evision.Mat.

  Image.

Keyword Arguments

• mask: Evision.Mat.

  Mask specifying where to look for keypoints (optional). It must be a 8-bit integer matrix with non-zero values in the region of interest.

Return

• keypoints: [Evision.KeyPoint].

  The detected keypoints. In the second variant of the method keypoints[i] is a set of keypoints detected in images[i] .

Python prototype (for reference only):

detect(image[, mask]) -> keypoints

@spec detect(t(), [Evision.Mat.maybe_mat_in()], [{:masks, term()}] | nil) ::
  [[Evision.KeyPoint.t()]] | {:error, String.t()}

@spec detect(t(), Evision.Mat.maybe_mat_in(), [{:mask, term()}] | nil) ::
  [Evision.KeyPoint.t()] | {:error, String.t()}

Variant 1:

detect

Positional Arguments

• self: Evision.ORB.t()

• images: [Evision.Mat].

  Image set.

Keyword Arguments

• masks: [Evision.Mat].

  Masks for each input image specifying where to look for keypoints (optional). masks[i] is a mask for images[i].

Return

• keypoints: [[Evision.KeyPoint]].

  The detected keypoints. In the second variant of the method keypoints[i] is a set of keypoints detected in images[i] .

Has overloading in C++

Python prototype (for reference only):

detect(images[, masks]) -> keypoints

Variant 2:

Detects keypoints in an image (first variant) or image set (second variant).

Positional Arguments

• self: Evision.ORB.t()

• image: Evision.Mat.

  Image.

Keyword Arguments

• mask: Evision.Mat.

  Mask specifying where to look for keypoints (optional). It must be a 8-bit integer matrix with non-zero values in the region of interest.

Return

• keypoints: [Evision.KeyPoint].

  The detected keypoints. In the second variant of the method keypoints[i] is a set of keypoints detected in images[i] .

Python prototype (for reference only):

detect(image[, mask]) -> keypoints

@spec detectAndCompute(t(), Evision.Mat.maybe_mat_in(), Evision.Mat.maybe_mat_in()) ::
  {[Evision.KeyPoint.t()], Evision.Mat.t()} | {:error, String.t()}

detectAndCompute

Positional Arguments

• self: Evision.ORB.t()
• image: Evision.Mat
• mask: Evision.Mat

Keyword Arguments

• useProvidedKeypoints: bool.

Return

• keypoints: [Evision.KeyPoint]
• descriptors: Evision.Mat.t().

Detects keypoints and computes the descriptors

Python prototype (for reference only):

detectAndCompute(image, mask[, descriptors[, useProvidedKeypoints]]) -> keypoints, descriptors

@spec detectAndCompute(
  t(),
  Evision.Mat.maybe_mat_in(),
  Evision.Mat.maybe_mat_in(),
  [{:useProvidedKeypoints, term()}] | nil
) :: {[Evision.KeyPoint.t()], Evision.Mat.t()} | {:error, String.t()}

detectAndCompute

Positional Arguments

• self: Evision.ORB.t()
• image: Evision.Mat
• mask: Evision.Mat

Keyword Arguments

• useProvidedKeypoints: bool.

Return

• keypoints: [Evision.KeyPoint]
• descriptors: Evision.Mat.t().

Detects keypoints and computes the descriptors

Python prototype (for reference only):

detectAndCompute(image, mask[, descriptors[, useProvidedKeypoints]]) -> keypoints, descriptors

@spec empty(Keyword.t()) :: any() | {:error, String.t()}

@spec empty(t()) :: boolean() | {:error, String.t()}

empty

Positional Arguments

• self: Evision.ORB.t()

Return

• retval: bool

Python prototype (for reference only):

empty() -> retval

@spec getDefaultName(Keyword.t()) :: any() | {:error, String.t()}

@spec getDefaultName(t()) :: binary() | {:error, String.t()}

getDefaultName

Positional Arguments

• self: Evision.ORB.t()

Return

• retval: String

Python prototype (for reference only):

getDefaultName() -> retval

@spec getEdgeThreshold(Keyword.t()) :: any() | {:error, String.t()}

@spec getEdgeThreshold(t()) :: integer() | {:error, String.t()}

getEdgeThreshold

Positional Arguments

• self: Evision.ORB.t()

Return

• retval: integer()

Python prototype (for reference only):

getEdgeThreshold() -> retval

@spec getFastThreshold(Keyword.t()) :: any() | {:error, String.t()}

@spec getFastThreshold(t()) :: integer() | {:error, String.t()}

getFastThreshold

Positional Arguments

• self: Evision.ORB.t()

Return

• retval: integer()

Python prototype (for reference only):

getFastThreshold() -> retval

@spec getFirstLevel(Keyword.t()) :: any() | {:error, String.t()}

@spec getFirstLevel(t()) :: integer() | {:error, String.t()}

getFirstLevel

Positional Arguments

• self: Evision.ORB.t()

Return

• retval: integer()

Python prototype (for reference only):

getFirstLevel() -> retval

@spec getMaxFeatures(Keyword.t()) :: any() | {:error, String.t()}

@spec getMaxFeatures(t()) :: integer() | {:error, String.t()}

getMaxFeatures

Positional Arguments

• self: Evision.ORB.t()

Return

• retval: integer()

Python prototype (for reference only):

getMaxFeatures() -> retval

@spec getNLevels(Keyword.t()) :: any() | {:error, String.t()}

@spec getNLevels(t()) :: integer() | {:error, String.t()}

getNLevels

Positional Arguments

• self: Evision.ORB.t()

Return

• retval: integer()

Python prototype (for reference only):

getNLevels() -> retval

@spec getPatchSize(Keyword.t()) :: any() | {:error, String.t()}

@spec getPatchSize(t()) :: integer() | {:error, String.t()}

getPatchSize

Positional Arguments

• self: Evision.ORB.t()

Return

• retval: integer()

Python prototype (for reference only):

getPatchSize() -> retval

@spec getScaleFactor(Keyword.t()) :: any() | {:error, String.t()}

@spec getScaleFactor(t()) :: number() | {:error, String.t()}

getScaleFactor

Positional Arguments

• self: Evision.ORB.t()

Return

• retval: double

Python prototype (for reference only):

getScaleFactor() -> retval

@spec getScoreType(Keyword.t()) :: any() | {:error, String.t()}

@spec getScoreType(t()) :: Evision.ORB.ScoreType.enum() | {:error, String.t()}

getScoreType

Positional Arguments

• self: Evision.ORB.t()

Return

• retval: ORB::ScoreType

Python prototype (for reference only):

getScoreType() -> retval

@spec getWTA_K(Keyword.t()) :: any() | {:error, String.t()}

@spec getWTA_K(t()) :: integer() | {:error, String.t()}

getWTA_K

Positional Arguments

• self: Evision.ORB.t()

Return

• retval: integer()

Python prototype (for reference only):

getWTA_K() -> retval

@spec read(t(), Evision.FileNode.t()) :: t() | {:error, String.t()}

@spec read(t(), binary()) :: t() | {:error, String.t()}

Variant 1:

read

Positional Arguments

• self: Evision.ORB.t()
• arg1: Evision.FileNode

Python prototype (for reference only):

read(arg1) -> None

Variant 2:

read

Positional Arguments

• self: Evision.ORB.t()
• fileName: String

Python prototype (for reference only):

read(fileName) -> None

@spec setEdgeThreshold(t(), integer()) :: t() | {:error, String.t()}

setEdgeThreshold

Positional Arguments

• self: Evision.ORB.t()
• edgeThreshold: integer()

Python prototype (for reference only):

setEdgeThreshold(edgeThreshold) -> None

@spec setFastThreshold(t(), integer()) :: t() | {:error, String.t()}

setFastThreshold

Positional Arguments

• self: Evision.ORB.t()
• fastThreshold: integer()

Python prototype (for reference only):

setFastThreshold(fastThreshold) -> None

@spec setFirstLevel(t(), integer()) :: t() | {:error, String.t()}

setFirstLevel

Positional Arguments

• self: Evision.ORB.t()
• firstLevel: integer()

Python prototype (for reference only):

setFirstLevel(firstLevel) -> None

@spec setMaxFeatures(t(), integer()) :: t() | {:error, String.t()}

setMaxFeatures

Positional Arguments

• self: Evision.ORB.t()
• maxFeatures: integer()

Python prototype (for reference only):

setMaxFeatures(maxFeatures) -> None

@spec setNLevels(t(), integer()) :: t() | {:error, String.t()}

setNLevels

Positional Arguments

• self: Evision.ORB.t()
• nlevels: integer()

Python prototype (for reference only):

setNLevels(nlevels) -> None

@spec setPatchSize(t(), integer()) :: t() | {:error, String.t()}

setPatchSize

Positional Arguments

• self: Evision.ORB.t()
• patchSize: integer()

Python prototype (for reference only):

setPatchSize(patchSize) -> None

@spec setScaleFactor(t(), number()) :: t() | {:error, String.t()}

setScaleFactor

Positional Arguments

• self: Evision.ORB.t()
• scaleFactor: double

Python prototype (for reference only):

setScaleFactor(scaleFactor) -> None

@spec setScoreType(t(), Evision.ORB.ScoreType.enum()) :: t() | {:error, String.t()}

setScoreType

Positional Arguments

• self: Evision.ORB.t()
• scoreType: ORB_ScoreType

Python prototype (for reference only):

setScoreType(scoreType) -> None

@spec setWTA_K(t(), integer()) :: t() | {:error, String.t()}

setWTA_K

Positional Arguments

• self: Evision.ORB.t()
• wta_k: integer()

Python prototype (for reference only):

setWTA_K(wta_k) -> None

@spec write(t(), binary()) :: t() | {:error, String.t()}

write

Positional Arguments

• self: Evision.ORB.t()
• fileName: String

Python prototype (for reference only):

write(fileName) -> None

@spec write(t(), Evision.FileStorage.t(), binary()) :: t() | {:error, String.t()}

write

Positional Arguments

• self: Evision.ORB.t()
• fs: Evision.FileStorage
• name: String

Python prototype (for reference only):

write(fs, name) -> None