High Pass Filter for image processing in python by using scipy/numpy

Question

I am currently studying image processing. In Scipy, I know there is one median filter in Scipy.signal. Can anyone tell me if there is one filter similar to high pass filter?

Thank you

Answer 1

"High pass filter" is a very generic term. There are an infinite number of different "highpass filters" that do very different things (e.g. an edge dectection filter, as mentioned earlier, is technically a highpass (most are actually a bandpass) filter, but has a very different effect from what you probably had in mind.)

At any rate, based on most of the questions you've been asking, you should probably look into scipy.ndimage instead of scipy.filter, especially if you're going to be working with large images (ndimage can preform operations in-place, conserving memory).

As a basic example, showing a few different ways of doing things:

import matplotlib.pyplot as plt
import numpy as np
from scipy import ndimage
import Image

def plot(data, title):
    plot.i += 1
    plt.subplot(2,2,plot.i)
    plt.imshow(data)
    plt.gray()
    plt.title(title)
plot.i = 0

# Load the data...
im = Image.open('lena.png')
data = np.array(im, dtype=float)
plot(data, 'Original')

# A very simple and very narrow highpass filter
kernel = np.array([[-1, -1, -1],
                   [-1,  8, -1],
                   [-1, -1, -1]])
highpass_3x3 = ndimage.convolve(data, kernel)
plot(highpass_3x3, 'Simple 3x3 Highpass')

# A slightly "wider", but sill very simple highpass filter 
kernel = np.array([[-1, -1, -1, -1, -1],
                   [-1,  1,  2,  1, -1],
                   [-1,  2,  4,  2, -1],
                   [-1,  1,  2,  1, -1],
                   [-1, -1, -1, -1, -1]])
highpass_5x5 = ndimage.convolve(data, kernel)
plot(highpass_5x5, 'Simple 5x5 Highpass')

# Another way of making a highpass filter is to simply subtract a lowpass
# filtered image from the original. Here, we'll use a simple gaussian filter
# to "blur" (i.e. a lowpass filter) the original.
lowpass = ndimage.gaussian_filter(data, 3)
gauss_highpass = data - lowpass
plot(gauss_highpass, r'Gaussian Highpass, $\sigma = 3 pixels$')

plt.show()