
- Scikit Image – Introduction
- Scikit Image - Image Processing
- Scikit Image - Numpy Images
- Scikit Image - Image datatypes
- Scikit Image - Using Plugins
- Scikit Image - Image Handlings
- Scikit Image - Reading Images
- Scikit Image - Writing Images
- Scikit Image - Displaying Images
- Scikit Image - Image Collections
- Scikit Image - Image Stack
- Scikit Image - Multi Image
- Scikit Image - Data Visualization
- Scikit Image - Using Matplotlib
- Scikit Image - Using Ploty
- Scikit Image - Using Mayavi
- Scikit Image - Using Napari
- Scikit Image - Color Manipulation
- Scikit Image - Alpha Channel
- Scikit Image - Conversion b/w Color & Gray Values
- Scikit Image - Conversion b/w RGB & HSV
- Scikit Image - Conversion to CIE-LAB Color Space
- Scikit Image - Conversion from CIE-LAB Color Space
- Scikit Image - Conversion to luv Color Space
- Scikit Image - Conversion from luv Color Space
- Scikit Image - Image Inversion
- Scikit Image - Painting Images with Labels
- Scikit Image - Contrast & Exposure
- Scikit Image - Contrast
- Scikit Image - Contrast enhancement
- Scikit Image - Exposure
- Scikit Image - Histogram Matching
- Scikit Image - Histogram Equalization
- Scikit Image - Local Histogram Equalization
- Scikit Image - Tinting gray-scale images
- Scikit Image - Image Transformation
- Scikit Image - Scaling an image
- Scikit Image - Rotating an Image
- Scikit Image - Warping an Image
- Scikit Image - Affine Transform
- Scikit Image - Piecewise Affine Transform
- Scikit Image - ProjectiveTransform
- Scikit Image - EuclideanTransform
- Scikit Image - Radon Transform
- Scikit Image - Line Hough Transform
- Scikit Image - Probabilistic Hough Transform
- Scikit Image - Circular Hough Transforms
- Scikit Image - Elliptical Hough Transforms
- Scikit Image - Polynomial Transform
- Scikit Image - Image Pyramids
- Scikit Image - Pyramid Gaussian Transform
- Scikit Image - Pyramid Laplacian Transform
- Scikit Image - Swirl Transform
- Scikit Image - Morphological Operations
- Scikit Image - Erosion
- Scikit Image - Dilation
- Scikit Image - Black & White Tophat Morphologies
- Scikit Image - Convex Hull
- Scikit Image - Generating footprints
- Scikit Image - Isotopic Dilation & Erosion
- Scikit Image - Isotopic Closing & Opening of an Image
- Scikit Image - Skelitonizing an Image
- Scikit Image - Morphological Thinning
- Scikit Image - Masking an image
- Scikit Image - Area Closing & Opening of an Image
- Scikit Image - Diameter Closing & Opening of an Image
- Scikit Image - Morphological reconstruction of an Image
- Scikit Image - Finding local Maxima
- Scikit Image - Finding local Minima
- Scikit Image - Removing Small Holes from an Image
- Scikit Image - Removing Small Objects from an Image
- Scikit Image - Filters
- Scikit Image - Image Filters
- Scikit Image - Median Filter
- Scikit Image - Mean Filters
- Scikit Image - Morphological gray-level Filters
- Scikit Image - Gabor Filter
- Scikit Image - Gaussian Filter
- Scikit Image - Butterworth Filter
- Scikit Image - Frangi Filter
- Scikit Image - Hessian Filter
- Scikit Image - Meijering Neuriteness Filter
- Scikit Image - Sato Filter
- Scikit Image - Sobel Filter
- Scikit Image - Farid Filter
- Scikit Image - Scharr Filter
- Scikit Image - Unsharp Mask Filter
- Scikit Image - Roberts Cross Operator
- Scikit Image - Lapalace Operator
- Scikit Image - Window Functions With Images
- Scikit Image - Thresholding
- Scikit Image - Applying Threshold
- Scikit Image - Otsu Thresholding
- Scikit Image - Local thresholding
- Scikit Image - Hysteresis Thresholding
- Scikit Image - Li thresholding
- Scikit Image - Multi-Otsu Thresholding
- Scikit Image - Niblack and Sauvola Thresholding
- Scikit Image - Restoring Images
- Scikit Image - Rolling-ball Algorithm
- Scikit Image - Denoising an Image
- Scikit Image - Wavelet Denoising
- Scikit Image - Non-local means denoising for preserving textures
- Scikit Image - Calibrating Denoisers Using J-Invariance
- Scikit Image - Total Variation Denoising
- Scikit Image - Shift-invariant wavelet denoising
- Scikit Image - Image Deconvolution
- Scikit Image - Richardson-Lucy Deconvolution
- Scikit Image - Recover the original from a wrapped phase image
- Scikit Image - Image Inpainting
- Scikit Image - Registering Images
- Scikit Image - Image Registration
- Scikit Image - Masked Normalized Cross-Correlation
- Scikit Image - Registration using optical flow
- Scikit Image - Assemble images with simple image stitching
- Scikit Image - Registration using Polar and Log-Polar
- Scikit Image - Feature Detection
- Scikit Image - Dense DAISY Feature Description
- Scikit Image - Histogram of Oriented Gradients
- Scikit Image - Template Matching
- Scikit Image - CENSURE Feature Detector
- Scikit Image - BRIEF Binary Descriptor
- Scikit Image - SIFT Feature Detector and Descriptor Extractor
- Scikit Image - GLCM Texture Features
- Scikit Image - Shape Index
- Scikit Image - Sliding Window Histogram
- Scikit Image - Finding Contour
- Scikit Image - Texture Classification Using Local Binary Pattern
- Scikit Image - Texture Classification Using Multi-Block Local Binary Pattern
- Scikit Image - Active Contour Model
- Scikit Image - Canny Edge Detection
- Scikit Image - Marching Cubes
- Scikit Image - Foerstner Corner Detection
- Scikit Image - Harris Corner Detection
- Scikit Image - Extracting FAST Corners
- Scikit Image - Shi-Tomasi Corner Detection
- Scikit Image - Haar Like Feature Detection
- Scikit Image - Haar Feature detection of coordinates
- Scikit Image - Hessian matrix
- Scikit Image - ORB feature Detection
- Scikit Image - Additional Concepts
- Scikit Image - Render text onto an image
- Scikit Image - Face detection using a cascade classifier
- Scikit Image - Face classification using Haar-like feature descriptor
- Scikit Image - Visual image comparison
- Scikit Image - Exploring Region Properties With Pandas
Scikit Image − Morphological gray-level Filters
In grayscale image processing, the maximum and minimum filters are base operators to identify the local maximum and minimum values within an image. These Local maximum and minimum filters are fundamental operators in gray-level morphology.
The Scikit-Image (skimage) provides the maximum and minimum filters as part of the "rank filters" category. They operate on local neighborhoods of pixels, which are defined by 2D structuring elements. And are particularly useful for various image-processing tasks, including noise reduction, feature detection, and morphological operations.
Using the skimage.filters.rank.maximum() function
The filters.rank.maximum() function is used for finding the local maximum values within an image using a specified neighborhood or footprint.
Syntax
Following is the syntax of this function −
skimage.filters.rank.maximum(image, footprint, out=None, mask=None, shift_x=False, shift_y=False, shift_z=False)
Parameters
Here are the details of its parameters −
- Image ([P,] M, N) ndarray (uint8, uint16): This is the input image on which the local maximum operation will be performed.
- Footprint (ndarray): This parameter specifies the neighborhood or footprint used for local maximum computation. The NumPy array contains 1s and 0s.
- Out (optional, ([P,] M, N) array (same dtype as input)): This parameter is used to store the output of the local maximum operation. If specified, it should be a NumPy array of the same shape as the input image. If not specified(set to None), a new array will be allocated for the output.
- Mask (optional, ndarray (integer or float), optional): Mask array that can be used to define the area of the image included in the local neighborhood. Pixels with values greater than 0 in the mask are included in the neighborhood calculation. If not provided (None), the complete image is used by default.
- Shift_x, shift_y, shift_z: These parameters specify an offset added to the center point of the footprint. The shift is bounded to the footprint sizes, meaning the center must remain inside the given footprint.
Return value
The function returns an output image, which is a NumPy array of the same data type as the input image. It is important to note that the function is particularly efficient for larger images and footprints due to its lower algorithm complexity.
Example
The following example finds the local maximum values for each pixel in the input image, based on the given footprint −
import matplotlib.pyplot as plt from skimage import io, util from skimage.morphology import disk from skimage.filters.rank import maximum # Load the example image as a grayscale image image = io.imread('Images/black rose.jpg', as_gray=True) image = util.img_as_ubyte(image) # Finding the local maximum of the image using a disk-shaped neighborhood result = maximum(image, disk(5)) # Plot the original image and the result fig, axes = plt.subplots(1, 2, figsize=(15, 5)) ax = axes.ravel() # Display the Original Image ax[0].imshow(image, cmap='gray') ax[0].set_title('Original Image') ax[0].axis('off') # Display the Result ax[1].imshow(result, cmap='gray') ax[1].set_title('Resultant image after calculating the local maximum') ax[1].axis('off') plt.tight_layout() plt.show()
Output
Using the skimage.filters.rank.minimum() function
The filters.rank.minimum() function is similar to skimage.filters.rank.maximum, but it computes the local minimum instead of the local maximum within an image using a specified neighborhood or footprint.
Syntax
Following is the syntax of this function −
skimage.filters.rank.minimum(image, footprint, out=None, mask=None, shift_x=False, shift_y=False, shift_z=False)
Parameters
Here are the details of its parameters −
- Image ([P,] M, N) ndarray (uint8, uint16): This is the input image on which the local minimum operation will be performed.
- Footprint (ndarray): This parameter specifies the neighborhood or footprint used for local maximum computation. The NumPy array contains 1s and 0s.
- Out (optional, ([P,] M, N) array (same dtype as input)): This parameter is used to store the output of the local maximum operation. If specified, it should be a NumPy array of the same shape as the input image. If not specified(set to None), a new array will be allocated for the output.
- Mask (optional, ndarray (integer or float), optional): Mask array that can be used to define the area of the image included in the local neighborhood. Pixels with values greater than 0 in the mask are included in the neighborhood calculation. If not provided (None), the complete image is used by default.
- Shift_x, shift_y, shift_z: These parameters specify an offset added to the center point of the footprint. The shift is bounded to the footprint sizes, meaning the center must remain inside the given footprint.
Return value
The function returns an output image, which is a NumPy array of the same data type as the input image.
It is important to note that the function is particularly efficient for larger images and footprints due to its lower algorithm complexity.
Example 1
The following example finds the local minimum values for each pixel in the input image, based on the given footprint −
import matplotlib.pyplot as plt from skimage import io, util from skimage.morphology import disk from skimage.filters.rank import minimum # Load the example image as a grayscale image image = io.imread('Images/black rose.jpg', as_gray=True) image = util.img_as_ubyte(image) # Finding the local minimum of the image using a disk-shaped neighborhood result = minimum(image, disk(5)) # Plot the original image and the result fig, axes = plt.subplots(1, 2, figsize=(15, 5)) ax = axes.ravel() # Display the Original Image ax[0].imshow(image, cmap='gray') ax[0].set_title('Original Image') ax[0].axis('off') # Display the Result ax[1].imshow(result, cmap='gray') ax[1].set_title('Resultant image after calculating the local minimum') ax[1].axis('off') plt.tight_layout() plt.show()
Output
Example 2
The following example demonstrates the use of morphological gray-level filters, specifically opening, and closing, using the skimage.filters.rank.maximum() and skimage.filters.rank.minimum() functions −
from skimage.filters.rank import maximum, minimum from skimage import io, util import matplotlib.pyplot as plt # Load an example image and convert it to a grayscale image noisy_image = util.img_as_ubyte(io.imread('Images/image5.jpg', as_gray=True)) # Perform gray-level closing and opening morphological operations using disk-shaped neighborhoods opening = maximum(minimum(noisy_image, disk(5)), disk(5)) closing = minimum(maximum(noisy_image, disk(5)), disk(5)) # Display the original image, gray-level closing, and opening result fig, axes = plt.subplots(nrows=1, ncols=3, figsize=(10, 10)) ax = axes.ravel() ax[0].imshow(noisy_image, cmap=plt.cm.gray) ax[0].set_title('Original') ax[1].imshow(closing, cmap=plt.cm.gray) ax[1].set_title('Gray-level closing') ax[2].imshow(opening, cmap=plt.cm.gray) ax[2].set_title('Gray-level opening') for a in ax: a.axis('off') plt.tight_layout() plt.show()