take pdfs and distort them with imgaug

distortimages.py

import imageio, glob
import PyPDF2       
from wand.image import Image
from wand.color import Color
import numpy        
import imgaug as ia 
from imgaug import augmenters as iaa
import numpy as np  
import cv2          
                    
def get_pdfs():     
    for path in glob.glob("*.pdf"): 
        all_pages = Image(filename=path, resolution=150)
        pages = []  
        for i, page in enumerate(all_pages.sequence):
            with Image(page) as img:
                img.format = 'png'  
                img_buffer=np.asarray(bytearray(img.make_blob()), dtype=np.uint8)
                retval = cv2.imdecode(img_buffer, cv2.IMREAD_UNCHANGED)
                retval = cv2.resize(retval,(img.width,img.height))
                    
            pages.append(retval)
            augmented = augment_images(pages)
        write_image(path.strip(".pdf"),augmented)
                    
def augment_images(images): 
    ia.seed(numpy.random.randint(100000, size=1)[0])
    for image in images:    
        #image might not have 3 dimensions
        if np.ndim(image) < 3:
            image = image[np.newaxis,:, :]
    # Example batch of images.      
    # The array has shape (32, 64, 64, 3) and dtype uint8.

    seq = iaa.Sequential([
            #iaa.Fliplr(0.5), # horizontal flips
        iaa.Crop(percent=(0, 0.1)), # random crops
        # Small gaussian blur with random sigma between 0 and 0.5.
        # But we only blur about 50% of all images.
        iaa.Sometimes(0.5,
            iaa.GaussianBlur(sigma=(0, 0.5))
            ),
        # Strengthen or weaken the contrast in each image.
        iaa.ContrastNormalization((0.75, 1.5)),
        # Add gaussian noise.
        # For 50% of all images, we sample the noise once per pixel.
        # For the other 50% of all images, we sample the noise per pixel AND
        # channel. This can change the color (not only brightness) of the
        # pixels.
        iaa.AdditiveGaussianNoise(loc=0, scale=(0.0, 0.05*255), per_channel=0.5),
        # Make some images brighter and some darker.
        # In 20% of all cases, we sample the multiplier once per channel,
        # which can end up changing the color of the images.
        iaa.Multiply((0.8, 1.2), per_channel=0.2),
        # Apply affine transformations to each image.
        # Scale/zoom them, translate/move them, rotate them and shear them.
        iaa.Affine(
            scale={"x": (0.8, 1.2), "y": (0.8, 1.2)},
            translate_percent={"x": (-0.2, 0.2), "y": (-0.2, 0.2)},
            rotate=(-25, 25),
            shear=(-8, 8)
            )
        ], random_order=True) # apply augmenters in random order

    images_aug = seq.augment_images(images)
    return images_aug

def write_image(path,image):
    imageio.mimwrite(path+".tiff",image, format="TIFF")

get_pdfs()