View Source Evision.Bioinspired.Retina (Evision v0.1.28)

Link to this section Summary

Types

t()

Type that represents an Bioinspired.Retina struct.

Functions

Activate/desactivate the Parvocellular pathway processing (contours information extraction), by default, it is activated

Activate/desactivate the Magnocellular pathway processing (motion information extraction), by default, it is activated

Method which processes an image in the aim to correct its luminance correct backlight problems, enhance details in shadows.

Method which processes an image in the aim to correct its luminance correct backlight problems, enhance details in shadows.

Clears the algorithm state

Clears all retina buffers

Constructors from standardized interfaces : retreive a smart pointer to a Retina instance

Constructors from standardized interfaces : retreive a smart pointer to a Retina instance

Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read

getDefaultName

Retreive retina input buffer size

Accessor of the motion channel of the retina (models peripheral vision).

Accessor of the motion channel of the retina (models peripheral vision).

getMagnoRAW

Retreive retina output buffer size that can be different from the input if a spatial log transformation is applied

Accessor of the details channel of the retina (models foveal vision).

Accessor of the details channel of the retina (models foveal vision).

getParvoRAW

Outputs a string showing the used parameters setup

Reads algorithm parameters from a file storage

Method which allows retina to be applied on an input image,

Activate color saturation as the final step of the color demultiplexing process -> this saturation is a sigmoide function applied to each channel of the demultiplexed image.

Activate color saturation as the final step of the color demultiplexing process -> this saturation is a sigmoide function applied to each channel of the demultiplexed image.

Try to open an XML retina parameters file to adjust current retina instance setup

Try to open an XML retina parameters file to adjust current retina instance setup

Set parameters values for the Inner Plexiform Layer (IPL) magnocellular channel

Set parameters values for the Inner Plexiform Layer (IPL) magnocellular channel

Setup the OPL and IPL parvo channels (see biologocal model)

Setup the OPL and IPL parvo channels (see biologocal model)

Write xml/yml formated parameters information

Link to this section Types

@type t() :: %Evision.Bioinspired.Retina{ref: reference()}

Type that represents an Bioinspired.Retina struct.

  • ref. reference()

    The underlying erlang resource variable.

Link to this section Functions

Link to this function

activateContoursProcessing(self, activate)

View Source
@spec activateContoursProcessing(t(), boolean()) :: t() | {:error, String.t()}

Activate/desactivate the Parvocellular pathway processing (contours information extraction), by default, it is activated

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()

  • activate: bool.

    true if Parvocellular (contours information extraction) output should be activated, false if not... if activated, the Parvocellular output can be retrieved using the Retina::getParvo methods

Python prototype (for reference only):

activateContoursProcessing(activate) -> None
Link to this function

activateMovingContoursProcessing(self, activate)

View Source
@spec activateMovingContoursProcessing(t(), boolean()) :: t() | {:error, String.t()}

Activate/desactivate the Magnocellular pathway processing (motion information extraction), by default, it is activated

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()

  • activate: bool.

    true if Magnocellular output should be activated, false if not... if activated, the Magnocellular output can be retrieved using the getMagno methods

Python prototype (for reference only):

activateMovingContoursProcessing(activate) -> None
Link to this function

applyFastToneMapping(self, inputImage)

View Source
@spec applyFastToneMapping(t(), Evision.Mat.maybe_mat_in()) ::
  Evision.Mat.t() | {:error, String.t()}

Method which processes an image in the aim to correct its luminance correct backlight problems, enhance details in shadows.

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()

  • inputImage: Evision.Mat.t().

    the input image to process (should be coded in float format : CV_32F, CV_32FC1, CV_32F_C3, CV_32F_C4, the 4th channel won't be considered).

Return
  • outputToneMappedImage: Evision.Mat.t().

    the output 8bit/channel tone mapped image (CV_8U or CV_8UC3 format).

This method is designed to perform High Dynamic Range image tone mapping (compress >8bit/pixel images to 8bit/pixel). This is a simplified version of the Retina Parvocellular model (simplified version of the run/getParvo methods call) since it does not include the spatio-temporal filter modelling the Outer Plexiform Layer of the retina that performs spectral whitening and many other stuff. However, it works great for tone mapping and in a faster way. Check the demos and experiments section to see examples and the way to perform tone mapping using the original retina model and the method.

Python prototype (for reference only):

applyFastToneMapping(inputImage[, outputToneMappedImage]) -> outputToneMappedImage
Link to this function

applyFastToneMapping(self, inputImage, opts)

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

Method which processes an image in the aim to correct its luminance correct backlight problems, enhance details in shadows.

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()

  • inputImage: Evision.Mat.t().

    the input image to process (should be coded in float format : CV_32F, CV_32FC1, CV_32F_C3, CV_32F_C4, the 4th channel won't be considered).

Return
  • outputToneMappedImage: Evision.Mat.t().

    the output 8bit/channel tone mapped image (CV_8U or CV_8UC3 format).

This method is designed to perform High Dynamic Range image tone mapping (compress >8bit/pixel images to 8bit/pixel). This is a simplified version of the Retina Parvocellular model (simplified version of the run/getParvo methods call) since it does not include the spatio-temporal filter modelling the Outer Plexiform Layer of the retina that performs spectral whitening and many other stuff. However, it works great for tone mapping and in a faster way. Check the demos and experiments section to see examples and the way to perform tone mapping using the original retina model and the method.

Python prototype (for reference only):

applyFastToneMapping(inputImage[, outputToneMappedImage]) -> outputToneMappedImage
@spec clear(t()) :: t() | {:error, String.t()}

Clears the algorithm state

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()

Python prototype (for reference only):

clear() -> None
@spec clearBuffers(t()) :: t() | {:error, String.t()}

Clears all retina buffers

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()

(equivalent to opening the eyes after a long period of eye close ;o) whatchout the temporal transition occuring just after this method call.

Python prototype (for reference only):

clearBuffers() -> None
@spec create({number(), number()}) :: t() | {:error, String.t()}

create

Positional Arguments
  • inputSize: Size
Return
  • retval: Retina

Has overloading in C++

Python prototype (for reference only):

create(inputSize) -> retval
Link to this function

create(inputSize, colorMode)

View Source
@spec create(
  {number(), number()},
  boolean()
) :: t() | {:error, String.t()}

Constructors from standardized interfaces : retreive a smart pointer to a Retina instance

Positional Arguments
  • inputSize: Size.

    the input frame size

  • colorMode: bool.

    the chosen processing mode : with or without color processing

Keyword Arguments
  • colorSamplingMethod: int.

    specifies which kind of color sampling will be used :

    • cv::bioinspired::RETINA_COLOR_RANDOM: each pixel position is either R, G or B in a random choice
    • cv::bioinspired::RETINA_COLOR_DIAGONAL: color sampling is RGBRGBRGB..., line 2 BRGBRGBRG..., line 3, GBRGBRGBR...
    • cv::bioinspired::RETINA_COLOR_BAYER: standard bayer sampling
  • useRetinaLogSampling: bool.

    activate retina log sampling, if true, the 2 following parameters can be used

  • reductionFactor: float.

    only usefull if param useRetinaLogSampling=true, specifies the reduction factor of the output frame (as the center (fovea) is high resolution and corners can be underscaled, then a reduction of the output is allowed without precision leak

  • samplingStrength: float.

    only usefull if param useRetinaLogSampling=true, specifies the strength of the log scale that is applied

Return
  • retval: Retina

Python prototype (for reference only):

create(inputSize, colorMode[, colorSamplingMethod[, useRetinaLogSampling[, reductionFactor[, samplingStrength]]]]) -> retval
Link to this function

create(inputSize, colorMode, opts)

View Source
@spec create({number(), number()}, boolean(), [{atom(), term()}, ...] | nil) ::
  t() | {:error, String.t()}

Constructors from standardized interfaces : retreive a smart pointer to a Retina instance

Positional Arguments
  • inputSize: Size.

    the input frame size

  • colorMode: bool.

    the chosen processing mode : with or without color processing

Keyword Arguments
  • colorSamplingMethod: int.

    specifies which kind of color sampling will be used :

    • cv::bioinspired::RETINA_COLOR_RANDOM: each pixel position is either R, G or B in a random choice
    • cv::bioinspired::RETINA_COLOR_DIAGONAL: color sampling is RGBRGBRGB..., line 2 BRGBRGBRG..., line 3, GBRGBRGBR...
    • cv::bioinspired::RETINA_COLOR_BAYER: standard bayer sampling
  • useRetinaLogSampling: bool.

    activate retina log sampling, if true, the 2 following parameters can be used

  • reductionFactor: float.

    only usefull if param useRetinaLogSampling=true, specifies the reduction factor of the output frame (as the center (fovea) is high resolution and corners can be underscaled, then a reduction of the output is allowed without precision leak

  • samplingStrength: float.

    only usefull if param useRetinaLogSampling=true, specifies the strength of the log scale that is applied

Return
  • retval: Retina

Python prototype (for reference only):

create(inputSize, colorMode[, colorSamplingMethod[, useRetinaLogSampling[, reductionFactor[, samplingStrength]]]]) -> retval
@spec empty(t()) :: boolean() | {:error, String.t()}

Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()
Return
  • retval: bool

Python prototype (for reference only):

empty() -> retval
@spec getDefaultName(t()) :: binary() | {:error, String.t()}

getDefaultName

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()
Return

Returns the algorithm string identifier. This string is used as top level xml/yml node tag when the object is saved to a file or string.

Python prototype (for reference only):

getDefaultName() -> retval
@spec getInputSize(t()) :: {number(), number()} | {:error, String.t()}

Retreive retina input buffer size

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()
Return
  • retval: Size

@return the retina input buffer size

Python prototype (for reference only):

getInputSize() -> retval
@spec getMagno(t()) :: Evision.Mat.t() | {:error, String.t()}

Accessor of the motion channel of the retina (models peripheral vision).

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()
Return
  • retinaOutput_magno: Evision.Mat.t().the output buffer (reallocated if necessary), format can be :
    • a Mat, this output is rescaled for standard 8bits image processing use in OpenCV
    • RAW methods actually return a 1D matrix (encoding is M1, M2,... Mn), this output is the original retina filter model output, without any quantification or rescaling.

Warning, getMagnoRAW methods return buffers that are not rescaled within range [0;255] while the non RAW method allows a normalized matrix to be retrieved. @see getMagnoRAW

Python prototype (for reference only):

getMagno([, retinaOutput_magno]) -> retinaOutput_magno
@spec getMagno(t(), [{atom(), term()}, ...] | nil) ::
  Evision.Mat.t() | {:error, String.t()}

Accessor of the motion channel of the retina (models peripheral vision).

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()
Return
  • retinaOutput_magno: Evision.Mat.t().the output buffer (reallocated if necessary), format can be :
    • a Mat, this output is rescaled for standard 8bits image processing use in OpenCV
    • RAW methods actually return a 1D matrix (encoding is M1, M2,... Mn), this output is the original retina filter model output, without any quantification or rescaling.

Warning, getMagnoRAW methods return buffers that are not rescaled within range [0;255] while the non RAW method allows a normalized matrix to be retrieved. @see getMagnoRAW

Python prototype (for reference only):

getMagno([, retinaOutput_magno]) -> retinaOutput_magno
@spec getMagnoRAW(t()) :: Evision.Mat.t() | {:error, String.t()}

getMagnoRAW

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()
Return
  • retval: Evision.Mat.t()

Has overloading in C++

Python prototype (for reference only):

getMagnoRAW() -> retval
@spec getOutputSize(t()) :: {number(), number()} | {:error, String.t()}

Retreive retina output buffer size that can be different from the input if a spatial log transformation is applied

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()
Return
  • retval: Size

@return the retina output buffer size

Python prototype (for reference only):

getOutputSize() -> retval
@spec getParvo(t()) :: Evision.Mat.t() | {:error, String.t()}

Accessor of the details channel of the retina (models foveal vision).

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()
Return
  • retinaOutput_parvo: Evision.Mat.t().the output buffer (reallocated if necessary), format can be :
    • a Mat, this output is rescaled for standard 8bits image processing use in OpenCV
    • RAW methods actually return a 1D matrix (encoding is R1, R2, ... Rn, G1, G2, ..., Gn, B1, B2, ...Bn), this output is the original retina filter model output, without any quantification or rescaling.

Warning, getParvoRAW methods return buffers that are not rescaled within range [0;255] while the non RAW method allows a normalized matrix to be retrieved. @see getParvoRAW

Python prototype (for reference only):

getParvo([, retinaOutput_parvo]) -> retinaOutput_parvo
@spec getParvo(t(), [{atom(), term()}, ...] | nil) ::
  Evision.Mat.t() | {:error, String.t()}

Accessor of the details channel of the retina (models foveal vision).

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()
Return
  • retinaOutput_parvo: Evision.Mat.t().the output buffer (reallocated if necessary), format can be :
    • a Mat, this output is rescaled for standard 8bits image processing use in OpenCV
    • RAW methods actually return a 1D matrix (encoding is R1, R2, ... Rn, G1, G2, ..., Gn, B1, B2, ...Bn), this output is the original retina filter model output, without any quantification or rescaling.

Warning, getParvoRAW methods return buffers that are not rescaled within range [0;255] while the non RAW method allows a normalized matrix to be retrieved. @see getParvoRAW

Python prototype (for reference only):

getParvo([, retinaOutput_parvo]) -> retinaOutput_parvo
@spec getParvoRAW(t()) :: Evision.Mat.t() | {:error, String.t()}

getParvoRAW

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()
Return
  • retval: Evision.Mat.t()

Has overloading in C++

Python prototype (for reference only):

getParvoRAW() -> retval
@spec printSetup(t()) :: binary() | {:error, String.t()}

Outputs a string showing the used parameters setup

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()
Return

@return a string which contains formated parameters information

Python prototype (for reference only):

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

Reads algorithm parameters from a file storage

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()
  • fn_: Evision.FileNode.t()

Python prototype (for reference only):

read(fn_) -> None
@spec run(t(), Evision.Mat.maybe_mat_in()) :: t() | {:error, String.t()}

Method which allows retina to be applied on an input image,

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()

  • inputImage: Evision.Mat.t().

    the input Mat image to be processed, can be gray level or BGR coded in any format (from 8bit to 16bits)

after run, encapsulated retina module is ready to deliver its outputs using dedicated acccessors, see getParvo and getMagno methods

Python prototype (for reference only):

run(inputImage) -> None
@spec save(t(), binary()) :: t() | {:error, String.t()}

save

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()
  • filename: String

Saves the algorithm to a file. In order to make this method work, the derived class must implement Algorithm::write(FileStorage& fs).

Python prototype (for reference only):

save(filename) -> None
Link to this function

setColorSaturation(self)

View Source
@spec setColorSaturation(t()) :: t() | {:error, String.t()}

Activate color saturation as the final step of the color demultiplexing process -> this saturation is a sigmoide function applied to each channel of the demultiplexed image.

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()
Keyword Arguments
  • saturateColors: bool.

    boolean that activates color saturation (if true) or desactivate (if false)

  • colorSaturationValue: float.

    the saturation factor : a simple factor applied on the chrominance buffers

Python prototype (for reference only):

setColorSaturation([, saturateColors[, colorSaturationValue]]) -> None
Link to this function

setColorSaturation(self, opts)

View Source
@spec setColorSaturation(t(), [{atom(), term()}, ...] | nil) ::
  t() | {:error, String.t()}

Activate color saturation as the final step of the color demultiplexing process -> this saturation is a sigmoide function applied to each channel of the demultiplexed image.

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()
Keyword Arguments
  • saturateColors: bool.

    boolean that activates color saturation (if true) or desactivate (if false)

  • colorSaturationValue: float.

    the saturation factor : a simple factor applied on the chrominance buffers

Python prototype (for reference only):

setColorSaturation([, saturateColors[, colorSaturationValue]]) -> None
@spec setup(t()) :: t() | {:error, String.t()}

Try to open an XML retina parameters file to adjust current retina instance setup

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()
Keyword Arguments
  • retinaParameterFile: String.

    the parameters filename

  • applyDefaultSetupOnFailure: bool.

    set to true if an error must be thrown on error

  • if the xml file does not exist, then default setup is applied

  • warning, Exceptions are thrown if read XML file is not valid

You can retrieve the current parameters structure using the method Retina::getParameters and update it before running method Retina::setup.

Python prototype (for reference only):

setup([, retinaParameterFile[, applyDefaultSetupOnFailure]]) -> None
@spec setup(t(), [{atom(), term()}, ...] | nil) :: t() | {:error, String.t()}

Try to open an XML retina parameters file to adjust current retina instance setup

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()
Keyword Arguments
  • retinaParameterFile: String.

    the parameters filename

  • applyDefaultSetupOnFailure: bool.

    set to true if an error must be thrown on error

  • if the xml file does not exist, then default setup is applied

  • warning, Exceptions are thrown if read XML file is not valid

You can retrieve the current parameters structure using the method Retina::getParameters and update it before running method Retina::setup.

Python prototype (for reference only):

setup([, retinaParameterFile[, applyDefaultSetupOnFailure]]) -> None
Link to this function

setupIPLMagnoChannel(self)

View Source
@spec setupIPLMagnoChannel(t()) :: t() | {:error, String.t()}

Set parameters values for the Inner Plexiform Layer (IPL) magnocellular channel

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()
Keyword Arguments
  • normaliseOutput: bool.

    specifies if (true) output is rescaled between 0 and 255 of not (false)

  • parasolCells_beta: float.

    the low pass filter gain used for local contrast adaptation at the IPL level of the retina (for ganglion cells local adaptation), typical value is 0

  • parasolCells_tau: float.

    the low pass filter time constant used for local contrast adaptation at the IPL level of the retina (for ganglion cells local adaptation), unit is frame, typical value is 0 (immediate response)

  • parasolCells_k: float.

    the low pass filter spatial constant used for local contrast adaptation at the IPL level of the retina (for ganglion cells local adaptation), unit is pixels, typical value is 5

  • amacrinCellsTemporalCutFrequency: float.

    the time constant of the first order high pass fiter of the magnocellular way (motion information channel), unit is frames, typical value is 1.2

  • v0CompressionParameter: float.

    the compression strengh of the ganglion cells local adaptation output, set a value between 0.6 and 1 for best results, a high value increases more the low value sensitivity... and the output saturates faster, recommended value: 0.95

  • localAdaptintegration_tau: float.

    specifies the temporal constant of the low pas filter involved in the computation of the local "motion mean" for the local adaptation computation

  • localAdaptintegration_k: float.

    specifies the spatial constant of the low pas filter involved in the computation of the local "motion mean" for the local adaptation computation

this channel processes signals output from OPL processing stage in peripheral vision, it allows motion information enhancement. It is decorrelated from the details channel. See reference papers for more details.

Python prototype (for reference only):

setupIPLMagnoChannel([, normaliseOutput[, parasolCells_beta[, parasolCells_tau[, parasolCells_k[, amacrinCellsTemporalCutFrequency[, V0CompressionParameter[, localAdaptintegration_tau[, localAdaptintegration_k]]]]]]]]) -> None
Link to this function

setupIPLMagnoChannel(self, opts)

View Source
@spec setupIPLMagnoChannel(t(), [{atom(), term()}, ...] | nil) ::
  t() | {:error, String.t()}

Set parameters values for the Inner Plexiform Layer (IPL) magnocellular channel

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()
Keyword Arguments
  • normaliseOutput: bool.

    specifies if (true) output is rescaled between 0 and 255 of not (false)

  • parasolCells_beta: float.

    the low pass filter gain used for local contrast adaptation at the IPL level of the retina (for ganglion cells local adaptation), typical value is 0

  • parasolCells_tau: float.

    the low pass filter time constant used for local contrast adaptation at the IPL level of the retina (for ganglion cells local adaptation), unit is frame, typical value is 0 (immediate response)

  • parasolCells_k: float.

    the low pass filter spatial constant used for local contrast adaptation at the IPL level of the retina (for ganglion cells local adaptation), unit is pixels, typical value is 5

  • amacrinCellsTemporalCutFrequency: float.

    the time constant of the first order high pass fiter of the magnocellular way (motion information channel), unit is frames, typical value is 1.2

  • v0CompressionParameter: float.

    the compression strengh of the ganglion cells local adaptation output, set a value between 0.6 and 1 for best results, a high value increases more the low value sensitivity... and the output saturates faster, recommended value: 0.95

  • localAdaptintegration_tau: float.

    specifies the temporal constant of the low pas filter involved in the computation of the local "motion mean" for the local adaptation computation

  • localAdaptintegration_k: float.

    specifies the spatial constant of the low pas filter involved in the computation of the local "motion mean" for the local adaptation computation

this channel processes signals output from OPL processing stage in peripheral vision, it allows motion information enhancement. It is decorrelated from the details channel. See reference papers for more details.

Python prototype (for reference only):

setupIPLMagnoChannel([, normaliseOutput[, parasolCells_beta[, parasolCells_tau[, parasolCells_k[, amacrinCellsTemporalCutFrequency[, V0CompressionParameter[, localAdaptintegration_tau[, localAdaptintegration_k]]]]]]]]) -> None
Link to this function

setupOPLandIPLParvoChannel(self)

View Source
@spec setupOPLandIPLParvoChannel(t()) :: t() | {:error, String.t()}

Setup the OPL and IPL parvo channels (see biologocal model)

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()
Keyword Arguments
  • colorMode: bool.

    specifies if (true) color is processed of not (false) to then processing gray level image

  • normaliseOutput: bool.

    specifies if (true) output is rescaled between 0 and 255 of not (false)

  • photoreceptorsLocalAdaptationSensitivity: float.

    the photoreceptors sensitivity renage is 0-1 (more log compression effect when value increases)

  • photoreceptorsTemporalConstant: float.

    the time constant of the first order low pass filter of the photoreceptors, use it to cut high temporal frequencies (noise or fast motion), unit is frames, typical value is 1 frame

  • photoreceptorsSpatialConstant: float.

    the spatial constant of the first order low pass filter of the photoreceptors, use it to cut high spatial frequencies (noise or thick contours), unit is pixels, typical value is 1 pixel

  • horizontalCellsGain: float.

    gain of the horizontal cells network, if 0, then the mean value of the output is zero, if the parameter is near 1, then, the luminance is not filtered and is still reachable at the output, typicall value is 0

  • hcellsTemporalConstant: float.

    the time constant of the first order low pass filter of the horizontal cells, use it to cut low temporal frequencies (local luminance variations), unit is frames, typical value is 1 frame, as the photoreceptors

  • hcellsSpatialConstant: float.

    the spatial constant of the first order low pass filter of the horizontal cells, use it to cut low spatial frequencies (local luminance), unit is pixels, typical value is 5 pixel, this value is also used for local contrast computing when computing the local contrast adaptation at the ganglion cells level (Inner Plexiform Layer parvocellular channel model)

  • ganglionCellsSensitivity: float.

    the compression strengh of the ganglion cells local adaptation output, set a value between 0.6 and 1 for best results, a high value increases more the low value sensitivity... and the output saturates faster, recommended value: 0.7

OPL is referred as Outer Plexiform Layer of the retina, it allows the spatio-temporal filtering which withens the spectrum and reduces spatio-temporal noise while attenuating global luminance (low frequency energy) IPL parvo is the OPL next processing stage, it refers to a part of the Inner Plexiform layer of the retina, it allows high contours sensitivity in foveal vision. See reference papers for more informations. for more informations, please have a look at the paper Benoit A., Caplier A., Durette B., Herault, J., "USING HUMAN VISUAL SYSTEM MODELING FOR BIO-INSPIRED LOW LEVEL IMAGE PROCESSING", Elsevier, Computer Vision and Image Understanding 114 (2010), pp. 758-773, DOI: http://dx.doi.org/10.1016/j.cviu.2010.01.011

Python prototype (for reference only):

setupOPLandIPLParvoChannel([, colorMode[, normaliseOutput[, photoreceptorsLocalAdaptationSensitivity[, photoreceptorsTemporalConstant[, photoreceptorsSpatialConstant[, horizontalCellsGain[, HcellsTemporalConstant[, HcellsSpatialConstant[, ganglionCellsSensitivity]]]]]]]]]) -> None
Link to this function

setupOPLandIPLParvoChannel(self, opts)

View Source
@spec setupOPLandIPLParvoChannel(t(), [{atom(), term()}, ...] | nil) ::
  t() | {:error, String.t()}

Setup the OPL and IPL parvo channels (see biologocal model)

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()
Keyword Arguments
  • colorMode: bool.

    specifies if (true) color is processed of not (false) to then processing gray level image

  • normaliseOutput: bool.

    specifies if (true) output is rescaled between 0 and 255 of not (false)

  • photoreceptorsLocalAdaptationSensitivity: float.

    the photoreceptors sensitivity renage is 0-1 (more log compression effect when value increases)

  • photoreceptorsTemporalConstant: float.

    the time constant of the first order low pass filter of the photoreceptors, use it to cut high temporal frequencies (noise or fast motion), unit is frames, typical value is 1 frame

  • photoreceptorsSpatialConstant: float.

    the spatial constant of the first order low pass filter of the photoreceptors, use it to cut high spatial frequencies (noise or thick contours), unit is pixels, typical value is 1 pixel

  • horizontalCellsGain: float.

    gain of the horizontal cells network, if 0, then the mean value of the output is zero, if the parameter is near 1, then, the luminance is not filtered and is still reachable at the output, typicall value is 0

  • hcellsTemporalConstant: float.

    the time constant of the first order low pass filter of the horizontal cells, use it to cut low temporal frequencies (local luminance variations), unit is frames, typical value is 1 frame, as the photoreceptors

  • hcellsSpatialConstant: float.

    the spatial constant of the first order low pass filter of the horizontal cells, use it to cut low spatial frequencies (local luminance), unit is pixels, typical value is 5 pixel, this value is also used for local contrast computing when computing the local contrast adaptation at the ganglion cells level (Inner Plexiform Layer parvocellular channel model)

  • ganglionCellsSensitivity: float.

    the compression strengh of the ganglion cells local adaptation output, set a value between 0.6 and 1 for best results, a high value increases more the low value sensitivity... and the output saturates faster, recommended value: 0.7

OPL is referred as Outer Plexiform Layer of the retina, it allows the spatio-temporal filtering which withens the spectrum and reduces spatio-temporal noise while attenuating global luminance (low frequency energy) IPL parvo is the OPL next processing stage, it refers to a part of the Inner Plexiform layer of the retina, it allows high contours sensitivity in foveal vision. See reference papers for more informations. for more informations, please have a look at the paper Benoit A., Caplier A., Durette B., Herault, J., "USING HUMAN VISUAL SYSTEM MODELING FOR BIO-INSPIRED LOW LEVEL IMAGE PROCESSING", Elsevier, Computer Vision and Image Understanding 114 (2010), pp. 758-773, DOI: http://dx.doi.org/10.1016/j.cviu.2010.01.011

Python prototype (for reference only):

setupOPLandIPLParvoChannel([, colorMode[, normaliseOutput[, photoreceptorsLocalAdaptationSensitivity[, photoreceptorsTemporalConstant[, photoreceptorsSpatialConstant[, horizontalCellsGain[, HcellsTemporalConstant[, HcellsSpatialConstant[, ganglionCellsSensitivity]]]]]]]]]) -> None
@spec write(t(), binary()) :: t() | {:error, String.t()}

Write xml/yml formated parameters information

Positional Arguments
  • self: Evision.Bioinspired.Retina.t()

  • fs: String.

    the filename of the xml file that will be open and writen with formatted parameters information

Python prototype (for reference only):

write(fs) -> None