Skip to content

inpainting_ctinpainting_ctInpaintingCtInpaintingCtinpainting_ctinpainting_ct🔗

Short description🔗

inpainting_ctinpainting_ctInpaintingCtInpaintingCtinpainting_ctinpainting_ct — Perform an inpainting by coherence transport.

Signature🔗

inpainting_ct( image Image, region Region, out image InpaintedImage, number Epsilon, number Kappa, number Sigma, number Rho, number ChannelCoefficients )inpainting_ct( Image, Region : InpaintedImage : Epsilon, Kappa, Sigma, Rho, ChannelCoefficients : )void InpaintingCt( const HObject& Image, const HObject& Region, HObject* InpaintedImage, const HTuple& Epsilon, const HTuple& Kappa, const HTuple& Sigma, const HTuple& Rho, const HTuple& ChannelCoefficients )static void HOperatorSet.InpaintingCt( HObject image, HObject region, out HObject inpaintedImage, HTuple epsilon, HTuple kappa, HTuple sigma, HTuple rho, HTuple channelCoefficients )def inpainting_ct( image: HObject, region: HObject, epsilon: float, kappa: float, sigma: float, rho: float, channel_coefficients: MaybeSequence[float] ) -> HObject

Herror inpainting_ct( const Hobject Image, const Hobject Region, Hobject* InpaintedImage, double Epsilon, double Kappa, double Sigma, double Rho, double ChannelCoefficients )

Herror T_inpainting_ct( const Hobject Image, const Hobject Region, Hobject* InpaintedImage, const Htuple Epsilon, const Htuple Kappa, const Htuple Sigma, const Htuple Rho, const Htuple ChannelCoefficients )

HImage HImage::InpaintingCt( const HRegion& Region, double Epsilon, double Kappa, double Sigma, double Rho, const HTuple& ChannelCoefficients ) const

HImage HImage::InpaintingCt( const HRegion& Region, double Epsilon, double Kappa, double Sigma, double Rho, double ChannelCoefficients ) const

HImage HImage.InpaintingCt( HRegion region, double epsilon, double kappa, double sigma, double rho, HTuple channelCoefficients )

HImage HImage.InpaintingCt( HRegion region, double epsilon, double kappa, double sigma, double rho, double channelCoefficients )

Description🔗

The operator inpainting_ctInpaintingCt inpaints a missing region Regionregionregion of an image Imageimageimage by transporting image information from the region’s boundary along the coherence direction into this region.

Since this operator’s basic concept is inpainting by continuing broken contour lines, the image content and inpainting region must be such that this idea makes sense. That is, if a contour line hits the region to inpaint at a pixel \(p\), there should be some opposite point \(q\) where this contour line continues so that the continuation of contour lines from two opposite sides can succeed. In cases where there is less geometry in the image, a diffusion-based inpainter, e.g., harmonic_interpolationHarmonicInterpolation may yield better results. Alternatively, Kappakappakappa can be set to 00. An extreme situation with little global geometries are pure textures. Then the idea behind this operator will fail to produce good results (think of a checkerboard with a big region to inpaint relative to the checker fields). For these kinds of images, a texture-based inpainting, e.g., inpainting_textureInpaintingTexture, can be used instead.

The operator uses a so-called upwind scheme to assign gray values to the missing pixels, i.e.,:

  • The order of the pixels to process is given by their Euclidean distance to the boundary of the region to inpaint.

  • A new value \(u_{i}\) is computed as a weighted average of already known values \(u_{j}\) within a disc of radius Epsilonepsilonepsilon around the current pixel. The disc is restricted to already known pixels.

  • The size of this scheme’s mask depends on Epsilonepsilonepsilon.

The initially used image data comes from a stripe of thickness Epsilonepsilonepsilon around the region to inpaint. Thus, Epsilonepsilonepsilon must be at least 1 for the scheme to work, but should be greater. The maximum value for Epsilonepsilonepsilon depends on the gray values that should be transported into the region. Choosing Epsilonepsilonepsilon \(=\) 55 can be used in many cases.

Since the goal is to close broken contour lines, the direction of the level lines must be estimated and used in the weight. This estimated direction is called the coherence direction, and is computed by means of the structure tensor S.

\[\begin{eqnarray*} S = G_{\rho} \ast Dv Dv^{T} \end{eqnarray*}\]

and

\[\begin{eqnarray*} v = G_{\sigma} * u \end{eqnarray*}\]

where * denotes the convolution, \(u\) denotes the gray value image, \(D\) the derivative and \(G\) Gaussian kernels with standard deviation \(\sigma\) and \(\rho\). These standard deviations are defined by the operator’s parameters Sigmasigmasigma and Rhorhorho. Sigmasigmasigma should have the size of the noise or unimportant little objects, which are then not considered in the estimation step by the pre-smoothing. Rhorhorho gives the size of the window around a pixel that will be used for direction estimation. The coherence direction \(c\) then is given by the eigendirection of \(S\) with respect to the minimal eigenvalue \(\lambda\), i.e.

\[\begin{eqnarray*} S c = \lambda c , |c|=1 \end{eqnarray*}\]

For multichannel or color images, the scheme above is applied to each channel separately, but the weights must be the same for all channels to propagate information in the same direction. Since the weight depends on the coherence direction, the common direction is given by the eigendirection of a composite structure tensor. If \(u_{1},...,u_{n}\) denote the \(n\) channels of the image, the channel structure tensors \(S_{1},...,S_{n}\) are computed and then combined to the composite structure tensor \(S\).

\[\begin{eqnarray*} S = \sum_{i=1}^{n} a_{i} S_{i} \end{eqnarray*}\]

The coefficients \(a_{i}\) are passed in ChannelCoefficientschannelCoefficientschannel_coefficients, which is a tuple of length \(n\) or length 1. If the tuple length is 1, the arithmetic mean is used, i.e., \(a_{i} = 1/n\). If the length of ChannelCoefficientschannelCoefficientschannel_coefficients matches the number of channels, the \(a_{i}\) are set to

\[\begin{eqnarray*} a_{i} = \frac{\textrm{ChannelCoefficients}_{i}}{\sum_{i=1}^{n} \textrm{ChannelCoefficients}_{i}} \end{eqnarray*}\]

in order to get a well-defined convex combination. Hence, the ChannelCoefficientschannelCoefficientschannel_coefficients must be greater than or equal to zero and their sum must be greater than zero. If the tuple length is neither 1 nor the number of channels or the requirement above is not satisfied, the operator returns an error message.

The purpose of using other ChannelCoefficientschannelCoefficientschannel_coefficients than the arithmetic mean is to adapt to different color codes. The coherence direction is a geometrical information of the composite image, which is given by high contrasts such as edges. Thus the more contrast a channel has, the more geometrical information it contains, and consequently the greater its coefficient should be chosen (relative to the others). For RGB images, [0.299, 0.587, 0.114][0.299, 0.587, 0.114] is a good choice.

The weight in the scheme is the product of a directional component and a distance component. If \(p\) is the 2D coordinate vector of the current pixel to be inpainted and \(q\) the 2D coordinate of a pixel in the neighborhood (the disc restricted to already known pixels), the directional component measures the deviation of the vector \(p-q\) from the coherence direction. If the deviation exponentially scaled by \(\beta\) is large, a low directional component is assigned, whereas if it is small, a large directional component is assigned. \(\beta\) is controlled by Kappakappakappa (in percent):

\[\begin{eqnarray*} \beta = 20 * \textrm{Epsilon} * \textrm{Kappa} / 100 \end{eqnarray*}\]

Kappakappakappa defines how important it is to propagate information along the coherence direction, so a large Kappakappakappa yields sharp edges, while a low Kappakappakappa allows for more diffusion.

A special case is when Kappakappakappa is zero: In this case the directional component of the weight is constant (one). The direction estimation step is then skipped to save computational costs and the parameters Sigmasigmasigma, Rhorhorho, ChannelCoefficientschannelCoefficientschannel_coefficients become meaningless, i.e, the propagation of information is not based on the structures visible in the image.

The distance component is \(1/|p-q|\). Consequently, if \(q\) is far away from \(p\), a low distance component is assigned, whereas if it is near to \(p\), a high distance component is assigned.

Attention🔗

Note that filter operators may return unexpected results if an image with a reduced domain is used as input. Please refer to the chapter Filters.

Execution information🔗

Execution information
  • Multithreading type: reentrant (runs in parallel with non-exclusive operators).

  • Multithreading scope: global (may be called from any thread).

Parameters🔗

Imageimageimage (input_object) (multichannel-)image(-array) → object (byte / uint2 / real)object (byte / uint2 / real)HObject (byte / uint2 / real)HImage (byte / uint2 / real)HObject (byte / uint2 / real)Hobject (byte / uint2 / real)

Input image.

Regionregionregion (input_object) region → objectobjectHObjectHRegionHObjectHobject

Inpainting region.

InpaintedImageinpaintedImageinpainted_image (output_object) (multichannel-)image(-array) → object (byte / uint2 / real)object (byte / uint2 / real)HObject (byte / uint2 / real)HImage (byte / uint2 / real)HObject (byte / uint2 / real)Hobject * (byte / uint2 / real)

Output image.

Epsilonepsilonepsilon (input_control) number → (real)(real)HTuple (double)HTuple (double)floatHtuple (double)

Radius of the pixel neighborhood.

Default: 5.05.0
Value range: 1.0 ≤ Epsilon ≤ 20.0
Minimum increment: 1.0
Recommended increment: 1.0

Kappakappakappa (input_control) number → (real)(real)HTuple (double)HTuple (double)floatHtuple (double)

Sharpness parameter in percent.

Default: 25.025.0
Value range: 0.0 ≤ Kappa ≤ 100.0
Minimum increment: 1.0
Recommended increment: 1.0

Sigmasigmasigma (input_control) number → (real)(real)HTuple (double)HTuple (double)floatHtuple (double)

Pre-smoothing parameter.

Default: 1.411.41
Value range: 0.0 ≤ Sigma ≤ 20.0
Minimum increment: 0.001
Recommended increment: 0.01

Rhorhorho (input_control) number → (real)(real)HTuple (double)HTuple (double)floatHtuple (double)

Smoothing parameter for the direction estimation.

Default: 4.04.0
Value range: 0.001 ≤ Rho ≤ 20.0
Minimum increment: 0.001
Recommended increment: 0.01

ChannelCoefficientschannelCoefficientschannel_coefficients (input_control) number(-array) → (real)(real)HTuple (double)HTuple (double)MaybeSequence[float]Htuple (double)

Channel weights.

Default: 11

Example🔗

(HDevelop)


read_image (Image, 'claudia')
gen_circle (Circle, 333, 164, 35)
inpainting_ct (Image, Circle, InpaintedImage, 15, 25, 1.5, 3,1.0)

Combinations with other operators🔗

Combinations

Alternatives

harmonic_interpolationHarmonicInterpolation, inpainting_anisoInpaintingAniso, inpainting_mcfInpaintingMcf, inpainting_cedInpaintingCed, inpainting_textureInpaintingTexture

References🔗

Folkmar Bornemann, Tom März: ``Fast Image Inpainting Based On Coherence Transport’‘; Journal of Mathematical Imaging and Vision; vol. 28, no. 3; pp. 259-278; 2007.

Module🔗

Foundation