NoiseTexturize

class augraphy.augmentations.noisetexturize.NoiseTexturize(sigma_range=(3, 10), turbulence_range=(2, 5), texture_width_range=(100, 500), texture_height_range=(100, 500), p=1)

Bases: Augmentation

Creates a random noise pattern to emulate paper textures. Consequently applies noise patterns to the original image from big to small.

Parameters:

• sigma_range (tuple, optional) – Defines bounds of noise fluctuations.

• turbulence_range (tuple, optional) – Defines how quickly big patterns will be replaced with the small ones. The lower value - the more iterations will be performed during texture generation.

• texture_width_range (tuple, optional) – Tuple of ints determining the width of the texture image. If the value is higher, the texture will be more refined.

• texture_height_range (tuple, optional) – Tuple of ints determining the height of the texture. If the value is higher, the texture will be more refined.

• p (float, optional) – The probability this Augmentation will be applied.

noise(width, height, channel, ratio, sigma)

The function generates an image, filled with gaussian nose. If ratio parameter is specified, noise will be generated for a lesser image and then it will be upscaled to the original size. In that case noise will generate larger square patterns. To avoid multiple lines, the upscale uses interpolation.

Parameters:

• width (int) – Width of generated image.

• height (int) – Height of generated image.

• channel (int) – Channel number of generated image.

• ratio (int) – The size of generated noise “pixels”.

• sigma (int) – Defines bounds of noise fluctuations.

Overview

The Noise Texturize augmentation creates a random noise pattern to emulate paper textures.

Initially, a clean image with single line of text is created.

Code example:

# import libraries
import cv2
import numpy as np
from augraphy import *


# create a clean image with single line of text
image = np.full((500, 1500,3), 250, dtype="uint8")
cv2.putText(
    image,
    "Lorem ipsum dolor sit amet, consectetur adipiscing elit",
    (80, 250),
    cv2.FONT_HERSHEY_SIMPLEX,
    1.5,
    0,
    3,
)

cv2.imshow("Input image", image)

Clean image:

Example 1

In this example, a NoiseTexturize augmentation instance is initialized and the sigma value that define noise fluctuatiosn is set to random value in between 2 and 3 (2, 3). The noise turbulence range is set to random value in between 2 and 5 (2,5). The texture width and height are set to random value in netween 50 to 500 pixels (50, 500).

Code example:

noise_texturize = NoiseTexturize(sigma_range=(2, 3),
                                 turbulence_range=(2, 5),
                                 texture_width_range=(50, 500),
                                 texture_height_range=(50, 500),
                                 )

img_noise_texturize = noise_texturize(image)
cv2.imshow("noise_texturize", img_noise_texturize

Augmented image: