As discussed in the Chapter 1, Getting Started with Image Processing, the point-wise intensity transformation operation applies a transfer function, T, to each pixel, f(x,y), of the input image to generate a corresponding pixel in the output image. The transformation can be expressed as g(x,y) = T(f(x,y)) or, equivalently, s = T(r), where r is the gray-level of a pixel in the input image and s is the transformed gray-level of the same pixel in the output image. It's a memory-less operation, and the output intensity at the location,(x, y), depends only on the input intensity at the same point. Pixels of the same intensity get the same transformation. This does not bring in new information and may cause loss of information, but can improve the visual appearance or make features easier to detect—that is why these transformations are often applied at the pre-processing step in the image processing pipeline. The following screenshot shows the point processing, as well as the mask/kernel processing (for spatial filters that consider neighborhood pixels also for transformation, as we have already seen):
Some popular intensity transformations are the following:
- Image negatives
- Color space transformation
- Log transform
- Power-law transformation
- Contrast stretching
- Scalar quantization
- Thresholding
We already discussed a few of them in the Chapter 1, Getting Started with Image Processing. Here, we will start with log transformation on a colored RGB image using PIL, and then discuss a few transformations that we have not yet covered.
As usual, we will start by importing all the required modules from the relevant Python libraries:
import numpy as np
from skimage import data, img_as_float, img_as_ubyte, exposure, io, color
from skimage.io import imread
from skimage.exposure import cumulative_distribution
from skimage.restoration import denoise_bilateral, denoise_nl_means, estimate_sigma
from skimage.measure import compare_psnr
from skimage.util import random_noise
from skimage.color import rgb2gray
from PIL import Image, ImageEnhance, ImageFilter
from scipy import ndimage, misc
import matplotlib.pylab as pylab