albumentations.augmentations.blur.transforms

Applies a Generalized Gaussian blur to the input image with randomized parameters for advanced data augmentation. This transform creates a custom blur kernel based on the Generalized Gaussian distribution, which allows for a wide range of blur effects beyond standard Gaussian blur. It then applies this kernel to the input image through convolution. The transform also incorporates noise into the kernel, resulting in a unique combination of blurring and noise injection. Key features of this augmentation: 1. Generalized Gaussian Kernel: Uses a generalized normal distribution to create kernels that can range from box-like blurs to very peaked blurs, controlled by the beta parameter. 2. Anisotropic Blurring: Allows for different blur strengths in horizontal and vertical directions (controlled by sigma_x and sigma_y), and rotation of the kernel. 3. Kernel Noise: Adds multiplicative noise to the kernel before applying it to the image, creating more diverse and realistic blur effects. Implementation Details: The kernel is generated using a 2D Generalized Gaussian function. The process involves: 1. Creating a 2D grid based on the kernel size 2. Applying rotation to this grid 3. Calculating the kernel values using the Generalized Gaussian formula 4. Adding multiplicative noise to the kernel 5. Normalizing the kernel The resulting kernel is then applied to the image using convolution.

Parameters

Notes

- This transform is particularly useful for simulating complex, real-world blur effects that go beyond simple Gaussian blur. - The combination of blur and noise can help in creating more robust models by simulating a wider range of image degradations. - Extreme values, especially for beta and noise, may result in unrealistic effects and should be used cautiously.

Apply uniform box blur to the input image using a randomly sized square kernel. This transform uses OpenCV's cv2.blur function, which performs a simple box filter blur. The size of the blur kernel is randomly selected for each application, allowing for varying degrees of blur intensity.

Parameters

Example

>>> import numpy as np
>>> import albumentations as A
>>> image = np.random.randint(0, 256, (100, 100, 3), dtype=np.uint8)
>>> transform = A.Blur(blur_limit=(3, 7), p=1.0)
>>> result = transform(image=image)
>>> blurred_image = result["image"]

Notes

- The blur kernel is always square (same width and height). - Only odd kernel sizes are used to ensure the blur has a clear center pixel. - Box blur is faster than Gaussian blur but may produce less natural results. - This blur method averages all pixels under the kernel area, which can reduce noise but also reduce image detail.

Parameters

Apply defocus blur to the input image. This transform simulates the effect of an out-of-focus camera by applying a defocus blur to the image. It uses a combination of disc kernels and Gaussian blur to create a realistic defocus effect.

Parameters

Example

>>> import numpy as np
>>> import albumentations as A
>>> image = np.random.randint(0, 256, (100, 100, 3), dtype=np.uint8)
>>> transform = A.Defocus(radius=(4, 8), alias_blur=(0.2, 0.4))
>>> result = transform(image=image)
>>> defocused_image = result['image']

Notes

- The defocus effect is created using a disc kernel, which simulates the shape of a camera's aperture. - The additional Gaussian blur (alias_blur) helps to soften the edges of the disc kernel, creating a more natural-looking defocus effect. - Larger radius values will create a stronger, more noticeable defocus effect. - The alias_blur parameter can be used to fine-tune the appearance of the defocus, with larger values creating a smoother, potentially more realistic effect.

References

• Defocus aberration: https://en.wikipedia.org/wiki/Defocus_aberration

Apply Gaussian blur to the input image using a randomly sized kernel. This transform blurs the input image using a Gaussian filter with a random kernel size and sigma value. Gaussian blur is a widely used image processing technique that reduces image noise and detail, creating a smoothing effect.

Parameters

Example

>>> import numpy as np
>>> import albumentations as A
>>> image = np.random.randint(0, 256, (100, 100, 3), dtype=np.uint8)
>>> # Default behavior: matches PIL's GaussianBlur
>>> transform = A.GaussianBlur(p=1.0, sigma_limit=(0.5, 3.0))
>>> # Or manual kernel size range
>>> transform = A.GaussianBlur(blur_limit=(3, 7), sigma_limit=(0.5, 3.0), p=1.0)
>>> result = transform(image=image)
>>> blurred_image = result["image"]

Notes

- When blur_limit=0 (default), this implementation exactly matches PIL's

Apply a glass blur effect to the input image. This transform simulates the effect of looking through textured glass by locally shuffling pixels in the image. It creates a distorted, frosted glass-like appearance.

Parameters

Example

>>> import numpy as np
>>> import albumentations as A
>>> image = np.random.randint(0, 256, (100, 100, 3), dtype=np.uint8)
>>> transform = A.GlassBlur(sigma=0.7, max_delta=4, iterations=3, mode="fast", p=1)
>>> result = transform(image=image)
>>> glass_blurred_image = result["image"]

Notes

- This transform is particularly effective for creating a 'looking through glass' effect or simulating the view through a frosted window. - The 'fast' mode is recommended for most use cases as it provides a good balance between effect quality and computation speed. - Increasing 'iterations' will strengthen the effect but also increase the processing time linearly.

References

• This implementation is based on the technique described in: "ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness" https://arxiv.org/abs/1903.12261
• Original implementation: https://github.com/hendrycks/robustness/blob/master/ImageNet-C/create_c/make_imagenet_c.py

Apply median blur to the input image. This transform uses a median filter to blur the input image. Median filtering is particularly effective at removing salt-and-pepper noise while preserving edges, making it a popular choice for noise reduction in image processing.

Parameters

Example

>>> import numpy as np
>>> import albumentations as A
>>> image = np.random.randint(0, 256, (100, 100, 3), dtype=np.uint8)
>>> transform = A.MedianBlur(blur_limit=(3, 7), p=0.5)
>>> result = transform(image=image)
>>> blurred_image = result["image"]

Notes

- The kernel size (aperture linear size) must always be odd and greater than 1. - Unlike mean blur or Gaussian blur, median blur uses the median of all pixels under the kernel area, making it more robust to outliers. - This transform is particularly useful for: * Removing salt-and-pepper noise * Preserving edges while smoothing images * Pre-processing images for edge detection algorithms - For color images, the median is calculated independently for each channel. - Larger kernel sizes result in stronger blurring effects but may also remove fine details from the image.

References

• Median filter: https://en.wikipedia.org/wiki/Median_filter
• OpenCV medianBlur: https://docs.opencv.org/master/d4/d86/group__imgproc__filter.html#ga564869aa33e58769b4469101aac458f9

Apply motion blur to the input image using a directional kernel. This transform simulates motion blur effects that occur during image capture, such as camera shake or object movement. It creates a directional blur using a line-shaped kernel with controllable angle, direction, and position.

Parameters

Example

>>> import albumentations as A
>>> # Horizontal camera shake (symmetric)
>>> transform = A.MotionBlur(
...     angle_range=(-5, 5),      # Near-horizontal motion
...     direction_range=(0, 0),    # Symmetric blur
...     p=1.0
... )
>>>
>>> # Object moving right
>>> transform = A.MotionBlur(
...     angle_range=(0, 0),        # Horizontal motion
...     direction_range=(0.8, 1.0), # Strong forward bias
...     p=1.0
... )

Notes

- angle controls the orientation of the motion line - direction controls the distribution of the blur along that line - Together they can simulate various motion effects: * Camera shake: Small angle range + direction near 0 * Object motion: Specific angle + direction=1.0 * Complex motion: Random angle + random direction

References

• Motion blur fundamentals: https://en.wikipedia.org/wiki/Motion_blur
• Directional blur kernels: https://www.sciencedirect.com/topics/computer-science/directional-blur
• OpenCV filter2D (used for convolution): https://docs.opencv.org/master/d4/d86/group__imgproc__filter.html#ga27c049795ce870216ddfb366086b5a04
• Research on motion blur simulation: "Understanding and Evaluating Blind Deconvolution Algorithms" (CVPR 2009) https://doi.org/10.1109/CVPR.2009.5206815
• Motion blur in photography: "The Manual of Photography", Chapter 7: Motion in Photography ISBN: 978-0240520377
• Kornia's implementation (similar approach): https://kornia.readthedocs.io/en/latest/augmentation.html#kornia.augmentation.RandomMotionBlur

Apply zoom blur transform.

Parameters