filters module#

Filter library for the application

class filters.add_margin(img)#

Bases: img_filter

Add margin to the image.

apply(params)#
init(img)#
class filters.bilateral(img)#

Bases: img_filter

Bilateral filter from opencv.

apply(params)#
class filters.bilateral_scikit(img)#

Bases: img_filter

Skimage denoise_bilateral filter. Averages pixels based on their distance and color similarity. Preserves edges while removing unwanted noise. Much slower than opencv implementation.

apply(params)#
class filters.binarize(img)#

Bases: img_filter

Binarization filter from opencv.

apply(params)#
init(img)#
class filters.binarize_otsu(img)#

Bases: img_filter

Otsu binarization filter from opencv.

apply(_)#
init(img)#
class filters.block_match(img)#

Bases: img_filter

Block matching filter from bm3d.

This filter is very slow and should be used only on small images

apply(params)#
class filters.dilate(img)#

Bases: img_filter

Dilation morphological operation from OpenCV module.

apply(params)#
class filters.erode(img)#

Bases: img_filter

Erosion morphological operation from OpenCV module.

apply(params)#
class filters.farid(img)#

Bases: img_filter

Farid filter from filters. Finds edges of the image.

apply(_)#
class filters.gaussian(img)#

Bases: img_filter

Gaussian blur filter from scikit-image. Easier to use than opencv version.

apply(params)#
class filters.hessian(img)#

Bases: img_filter

Hessian filter from scikit-image filters.

apply(params)#
class filters.img_filter(img)#

Bases: object

Parent class for all the filters.

class filters.invert(img)#

Bases: img_filter

Invert the image using bitwise_not from opencv.

apply(_)#
class filters.median(img)#

Bases: img_filter

Median blur filter from scikit-image. Using this over opencv version as that one is limited to 5x5 kernel.

apply(params)#
class filters.meijering(img)#

Bases: img_filter

Meijering filter from scikit-image filters. Finds continuous ridges.

apply(_)#
class filters.nlmeans(img)#

Bases: img_filter

Non-local means filter from scikit-image.

apply(params)#
class filters.sato(img)#

Bases: img_filter

Meijering filter from scikit-image filters. Exctracts continuous ridges.

apply(_)#
class filters.scale_values(img)#

Bases: img_filter

Scale values of the image to use the entire range of data type. This should remove the line height issues.

apply(_)#
class filters.total_variation(img)#

Bases: img_filter

Scikit image denoise_tv_chambolle filter from scikit-image.

Performs total variation denoising technique based on original Chambolle paper. This filter removes fine detail, but preserves details such as edges.

apply(params)#
class filters.unsharp_mask_pil(img)#

Bases: img_filter

Unsharp mask filter from PIL.

apply(params)#
class filters.unsharp_mask_scikit(img)#

Bases: img_filter

Unsharp mask filter from scikit.

Apply blurring using gaussian filter, then subtract the blurred image from the original image. Radius parameter is the sigma parameter of the gaussian filter. Amount parameter regulates the strength of the unsharp mask. Better results than using this from opencv.

apply(params)#