Python implements random enhanced transformation of images

import os
import random
import cv2
import numpy as np
from PIL import Image, ImageEnhance, ImageOps

# Define various data enhancement methodsdef random_rotate(image, angle_range=(-30, 30)):
    angle = (angle_range[0], angle_range[1])
    (h, w) = [:2]
    center = (w // 2, h // 2)
    M = cv2.getRotationMatrix2D(center, angle, 1.0)
    rotated = (image, M, (w, h), borderMode=cv2.BORDER_REFLECT)
    return rotated

def random_translate(image, translate_range=(-50, 50)):
    tx = (translate_range[0], translate_range[1])
    ty = (translate_range[0], translate_range[1])
    (h, w) = [:2]
    M = np.float32([[1, 0, tx], [0, 1, ty]])
    translated = (image, M, (w, h), borderMode=cv2.BORDER_REFLECT)
    return translated

def random_flip(image):
    flip_code = ([-1, 0, 1])
    flipped = (image, flip_code)
    return flipped

def random_scale(image, scale_range=(0.8, 1.2)):
    scale = (scale_range[0], scale_range[1])
    (h, w) = [:2]
    new_dim = (int(w * scale), int(h * scale))
    scaled = (image, new_dim, interpolation=cv2.INTER_LINEAR)
    return scaled

def random_crop(image, crop_size=(224, 224)):
    (h, w) = [:2]
    if crop_size[0] > h or crop_size[1] > w:
        # When the crop size is larger than the image size, throw an exception or adjust the crop size        raise ValueError("Crop size is larger than image size.")
    top = (0, h - crop_size[0])
    left = (0, w - crop_size[1])
    cropped = image[top:top+crop_size[0], left:left+crop_size[1]]
    return cropped

def random_color_jitter(image):
    pil_image = ((image, cv2.COLOR_BGR2RGB))
    color_jitter = (pil_image).enhance((0.6, 1.4))
    contrast_jitter = (color_jitter).enhance((0.5, 1.5))
    brightness_jitter = (contrast_jitter).enhance((0.6, 1.4))
    sharpness_jitter = (brightness_jitter).enhance((0.6, 1.4))
    jittered = ((sharpness_jitter), cv2.COLOR_RGB2BGR)
    return jittered

def random_add_noise(image):
    row, col, ch = 
    mean = 0
    var = 0.1
    sigma = var ** 0.5
    gauss = (mean, sigma, (row, col, ch))
    gauss = (row, col, ch)
    noisy = image + gauss
    return (noisy, 0, 255).astype(np.uint8)

# Data Enhanced Main Functiondef augment_random_images(src_folder, dst_folder, num_images_to_select, num_augmentations_per_image):
    if not (dst_folder):
        (dst_folder)

    # Get all image file names    all_filenames = [f for f in (src_folder) if ().endswith(('.png', '.jpg', '.jpeg'))]

    # If the number of selected images is greater than the total number of images, only all images are processed    num_images_to_process = min(num_images_to_select, len(all_filenames))

    # Randomly select images    selected_filenames = (all_filenames, num_images_to_process)

    # Create a list of enhanced methods    augmentation_methods = [
        random_rotate,
        #random_translate,
        random_flip,
        random_scale,
        #random_crop,
        random_color_jitter,
        random_add_noise
    ]

    for filename in selected_filenames:
        img_path = (src_folder, filename)
        image = (img_path)

        for i in range(num_augmentations_per_image):
            # Randomly select an enhancement method            augmentation_method = (augmentation_methods)
            
            # Apply the selected enhancement method            augmented_img = augmentation_method(image)

            # Save enhanced image            base_name, ext = (filename)
            save_path = (dst_folder, f"{base_name}_aug_{i}{ext}")
            (save_path, augmented_img)

if __name__ == "__main__":
    src_folder = 'path/to/source/folder'  # Replace with your source folder path    dst_folder = 'path/to/destination/folder'  # Replace with the folder path where you want to save the enhanced image    num_images_to_select = 10  # Number of images randomly selected from the source folder    num_augmentations_per_image = 5  # Number of enhanced images generated per image
    augment_random_images(src_folder, dst_folder, num_images_to_select, num_augmentations_per_image)
    print(f"Image enhancement completed，The enhanced image has been saved to {dst_folder}")