Skip to content

bioinspired_Retina

bioinspiredclassOpenCV 5.0.0
import { bioinspired_Retina } from '@banou/opencv-wasm'

Use after await initOpenCV(). See the initialization and named imports guide.

Native object: release it with using or delete(). Factories can return null; check before calling methods. Inherits Algorithm.

class which allows the Gipsa/Listic Labs model to be used with OpenCV.

This retina model allows spatio-temporal image processing (applied on still images, video sequences). As a summary, these are the retina model properties:

  • It applies a spectral whithening (mid-frequency details enhancement)
  • high frequency spatio-temporal noise reduction
  • low frequency luminance to be reduced (luminance range compression)
  • local logarithmic luminance compression allows details to be enhanced in low light conditions

USE : this model can be used basically for spatio-temporal video effects but also for : _using the getParvo method output matrix : texture analysiswith enhanced signal to noise ratio and enhanced details robust against input images luminance ranges _using the getMagno method output matrix : motion analysis also with the previously cited properties

for more information, reer to the following papers : 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 Vision: Images, Signals and Neural Networks: Models of Neural Processing in Visual Perception (Progress in Neural Processing),By: Jeanny Herault, ISBN: 9814273686. WAPI (Tower ID): 113266891.

The retina filter includes the research contributions of phd/research collegues from which code has been redrawn by the author : take a look at the retinacolor.hpp module to discover Brice Chaix de Lavarene color mosaicing/demosaicing and the reference paper: B. Chaix de Lavarene, D. Alleysson, B. Durette, J. Herault (2007). "Efficient demosaicing through recursive filtering", IEEE International Conference on Image Processing ICIP 2007 take a look at imagelogpolprojection.hpp to discover retina spatial log sampling which originates from Barthelemy Durette phd with Jeanny Herault. A Retina / V1 cortex projection is also proposed and originates from Jeanny's discussions. more informations in the above cited Jeanny Heraults's book.

Constructors and members

static create

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

create(inputSize: Size): bioinspired_Retina | null;
inputSize

the input frame size

Returns

The bioinspired_Retina | null result.

static create1

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

create1(inputSize: Size, colorMode: boolean, colorSamplingMethod: number, useRetinaLogSampling: boolean, reductionFactor: number, samplingStrength: number): bioinspired_Retina | null;
5 available overloads
create1(inputSize: Size, colorMode: boolean): bioinspired_Retina | null;
create1(inputSize: Size, colorMode: boolean, colorSamplingMethod: number): bioinspired_Retina | null;
create1(inputSize: Size, colorMode: boolean, colorSamplingMethod: number, useRetinaLogSampling: boolean): bioinspired_Retina | null;
create1(inputSize: Size, colorMode: boolean, colorSamplingMethod: number, useRetinaLogSampling: boolean, reductionFactor: number): bioinspired_Retina | null;
create1(inputSize: Size, colorMode: boolean, colorSamplingMethod: number, useRetinaLogSampling: boolean, reductionFactor: number, samplingStrength: number): bioinspired_Retina | null;
inputSize

the input frame size

colorMode

the chosen processing mode : with or without color processing

colorSamplingMethod

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

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

reductionFactor

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

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

Returns

The bioinspired_Retina | null result.

clone

Create another handle to the same native object. This retains the object without copying its pixels or algorithm state; dispose both handles separately.

clone(): this;
Returns

The this result.

getInputSize

Retreive retina input buffer size

getInputSize(): Size;
Returns

the retina input buffer size

getOutputSize

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

getOutputSize(): Size;
Returns

the retina output buffer size

setup

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

- if the xml file does not exist, then default setup is applied
- warning, Exceptions are thrown if read XML file is not valid
setup(retinaParameterFile: EmbindString, applyDefaultSetupOnFailure: boolean): void;
3 available overloads
setup(): void;
setup(retinaParameterFile: EmbindString): void;
setup(retinaParameterFile: EmbindString, applyDefaultSetupOnFailure: boolean): void;
retinaParameterFile

the parameters filename

applyDefaultSetupOnFailure

set to true if an error must be thrown on error

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

printSetup

Outputs a string showing the used parameters setup

printSetup(): string;
Returns

a string which contains formated parameters information

write

Write xml/yml formated parameters information

write(fs: EmbindString): void;
fs

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

setupOPLandIPLParvoChannel

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

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
setupOPLandIPLParvoChannel(colorMode: boolean, normaliseOutput: boolean, photoreceptorsLocalAdaptationSensitivity: number, photoreceptorsTemporalConstant: number, photoreceptorsSpatialConstant: number, horizontalCellsGain: number, HcellsTemporalConstant: number, HcellsSpatialConstant: number, ganglionCellsSensitivity: number): void;
10 available overloads
setupOPLandIPLParvoChannel(): void;
setupOPLandIPLParvoChannel(colorMode: boolean): void;
setupOPLandIPLParvoChannel(colorMode: boolean, normaliseOutput: boolean): void;
setupOPLandIPLParvoChannel(colorMode: boolean, normaliseOutput: boolean, photoreceptorsLocalAdaptationSensitivity: number): void;
setupOPLandIPLParvoChannel(colorMode: boolean, normaliseOutput: boolean, photoreceptorsLocalAdaptationSensitivity: number, photoreceptorsTemporalConstant: number): void;
setupOPLandIPLParvoChannel(colorMode: boolean, normaliseOutput: boolean, photoreceptorsLocalAdaptationSensitivity: number, photoreceptorsTemporalConstant: number, photoreceptorsSpatialConstant: number): void;
setupOPLandIPLParvoChannel(colorMode: boolean, normaliseOutput: boolean, photoreceptorsLocalAdaptationSensitivity: number, photoreceptorsTemporalConstant: number, photoreceptorsSpatialConstant: number, horizontalCellsGain: number): void;
setupOPLandIPLParvoChannel(colorMode: boolean, normaliseOutput: boolean, photoreceptorsLocalAdaptationSensitivity: number, photoreceptorsTemporalConstant: number, photoreceptorsSpatialConstant: number, horizontalCellsGain: number, HcellsTemporalConstant: number): void;
setupOPLandIPLParvoChannel(colorMode: boolean, normaliseOutput: boolean, photoreceptorsLocalAdaptationSensitivity: number, photoreceptorsTemporalConstant: number, photoreceptorsSpatialConstant: number, horizontalCellsGain: number, HcellsTemporalConstant: number, HcellsSpatialConstant: number): void;
setupOPLandIPLParvoChannel(colorMode: boolean, normaliseOutput: boolean, photoreceptorsLocalAdaptationSensitivity: number, photoreceptorsTemporalConstant: number, photoreceptorsSpatialConstant: number, horizontalCellsGain: number, HcellsTemporalConstant: number, HcellsSpatialConstant: number, ganglionCellsSensitivity: number): void;
colorMode

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

normaliseOutput

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

photoreceptorsLocalAdaptationSensitivity

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

photoreceptorsTemporalConstant

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

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

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

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

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

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

setupIPLMagnoChannel

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

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.
setupIPLMagnoChannel(normaliseOutput: boolean, parasolCells_beta: number, parasolCells_tau: number, parasolCells_k: number, amacrinCellsTemporalCutFrequency: number, V0CompressionParameter: number, localAdaptintegration_tau: number, localAdaptintegration_k: number): void;
9 available overloads
setupIPLMagnoChannel(): void;
setupIPLMagnoChannel(normaliseOutput: boolean): void;
setupIPLMagnoChannel(normaliseOutput: boolean, parasolCells_beta: number): void;
setupIPLMagnoChannel(normaliseOutput: boolean, parasolCells_beta: number, parasolCells_tau: number): void;
setupIPLMagnoChannel(normaliseOutput: boolean, parasolCells_beta: number, parasolCells_tau: number, parasolCells_k: number): void;
setupIPLMagnoChannel(normaliseOutput: boolean, parasolCells_beta: number, parasolCells_tau: number, parasolCells_k: number, amacrinCellsTemporalCutFrequency: number): void;
setupIPLMagnoChannel(normaliseOutput: boolean, parasolCells_beta: number, parasolCells_tau: number, parasolCells_k: number, amacrinCellsTemporalCutFrequency: number, V0CompressionParameter: number): void;
setupIPLMagnoChannel(normaliseOutput: boolean, parasolCells_beta: number, parasolCells_tau: number, parasolCells_k: number, amacrinCellsTemporalCutFrequency: number, V0CompressionParameter: number, localAdaptintegration_tau: number): void;
setupIPLMagnoChannel(normaliseOutput: boolean, parasolCells_beta: number, parasolCells_tau: number, parasolCells_k: number, amacrinCellsTemporalCutFrequency: number, V0CompressionParameter: number, localAdaptintegration_tau: number, localAdaptintegration_k: number): void;
normaliseOutput

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

parasolCells_beta

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

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

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

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

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

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

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

run

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

after run, encapsulated retina module is ready to deliver its outputs using dedicated
acccessors, see getParvo and getMagno methods
run(inputImage: Mat): void;
inputImage

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

applyFastToneMapping

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

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.
applyFastToneMapping(inputImage: Mat, outputToneMappedImage: Mat): void;
inputImage

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).

outputToneMappedImage

Output destination, filled by the native operation. the output 8bit/channel tone mapped image (CV_8U or CV_8UC3 format).

getParvo

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

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
getParvo(retinaOutput_parvo: Mat): void;
retinaOutput_parvo

Output destination, filled by the native operation. 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.

getParvoRAW

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

getParvoRAW(retinaOutput_parvo: Mat): void;
retinaOutput_parvo

Output destination, filled by the native operation. retina output parvo argument (Mat).

getParvoRAW1

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

getParvoRAW1(): Mat;
Returns

The Mat result. Release returned native handles with using or delete(), including handles nested in results.

getMagno

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

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
getMagno(retinaOutput_magno: Mat): void;
retinaOutput_magno

Output destination, filled by the native operation. 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.

getMagnoRAW

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

getMagnoRAW(retinaOutput_magno: Mat): void;
retinaOutput_magno

Output destination, filled by the native operation. retina output magno argument (Mat).

getMagnoRAW1

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

getMagnoRAW1(): Mat;
Returns

The Mat result. Release returned native handles with using or delete(), including handles nested in results.

setColorSaturation

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.

setColorSaturation(saturateColors: boolean, colorSaturationValue: number): void;
3 available overloads
setColorSaturation(): void;
setColorSaturation(saturateColors: boolean): void;
setColorSaturation(saturateColors: boolean, colorSaturationValue: number): void;
saturateColors

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

colorSaturationValue

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

clearBuffers

Clears all retina buffers

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

activateMovingContoursProcessing

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

activateMovingContoursProcessing(activate: boolean): void;
activate

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

activateContoursProcessing

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

activateContoursProcessing(activate: boolean): void;
activate

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

These signatures describe this package. Upstream documentation can mention optional backends that are absent from this build. Check runtime compatibility before choosing a backend or file format.