Jack Tompkins
Department of Computer Science
[email protected]
What is Contrast Enhancement
Original Image with low contrast
Enhanced Image
Luminance
 While contrast enhancement can be accomplished
across r, g, and b bands, often the image is first
converted to gray scale.
 https://www.itu.int/dms_pubrec/itu-r/rec/bt/R-RECBT.601-7-201103-I!!PDF-E.pdf
 When translating a color image to black and white (mode
“L”), use the ITU-R 601-2 luma transform:
 L = R * 299/1000 + G * 587/1000 + B * 114/1000
Contrast
 Low contrast images with neighbors clustered on the
low end of the intensity scale, closer to 0, are called
low-key.
 Low contrast images that reside on the high end of the
intensity scale, closer to 255, are called high-key.
 Normal contrast images are equalized.
 High contrast images will exhibit a full range of tones
from black to white, with dark shadows and bright
highlights.
How to Enhance Contrast
 Neighboring pixels with similar intensity are hard to
distinguish. Low Contrast -> image values
concentrated in a narrow range.
 Contrast enhancement -> distribute the pixel intensities
across a broader range while maintaining relative
brightness
Visualizing Pixel Counts
Histograms
 A histogram is a display of statistical information
representing the frequency of data items in successive
numerical intervals of equal size.
 Histogram of a monochrome image with 256 possible
gray levels or intensities ranging from 0 through 255.
 Each bin in the histogram represents a probability.
P(i) = ni / n, where ni is the number of pixels with
intensity i, n is the total number of pixels.
Pixel Counts - Histograms
Visualizing Pixel Counts
Histograms
 histograms.xslx
 Bw1.jpg
 Luther Bell
 Lena
 Oira.jpg
By What Technique?
 Use a function, g, to generate a new image B from
image A:
B(x, y) = g(A(x, y)), x = 0,…, n-1, y = 0,…, m-1
 The function, g, maps pixel intensities for each pixel in
image A to a new intensity for that pixel in image B.
 Monotonically non-decreasing, (relative intensity
relations remain)
 A short chapter excerpt with examples: TT92
Linear Transform
 Uniform linear transformation
 Say intensities are concentrated from 0 to 64, and we
wish to map these to 0 to 255
 g(f) = m f + b, where m = (t1 – t0)/(s1 - s0), b = t1 – m s1
g(f ) = 255/64 * f + 255 – 255/64 * 64 = 255/64 f
see histograms.xslx
 Easily adapted to piecewise transformations using
multiple slope segments over sequential groups
 Can be fully automated
Histogram Equalization
 Digital Image Processing – Gonzalez & Woods, p 93
 The probability of occurrence of gray level rk in an image is
approximated by
 p(rk) = nk / n k = 0, 1, 2, …, L-1, where nk is the number of pixels with gray level
rk, n is the number of pixels, and L is the total number of possible gray levels in the
image (typically 256)
A plot of pr(rk) is called a histogram, efficiently stored in an array
with indices 0..255
 A processed output image is obtained by mapping each pixel with level
rk in the input image into a corresponding pixel with level sk in the
output image

𝑘
𝑗=0
𝑝 (rj) = (L-1)
𝑘 𝑛𝑗
𝑗=0 𝑛
sk = (L-1)

Efficiently stored in an array with indices 0..255 as a look up table
 Histogram Equalization
= ((L-1)/n)
𝑘
𝑗=0 𝑛𝑗

Additional Techniques
 Image Contrast Enhancement Methods
 Log transform: g(f) = c log(1 + f)
 Power transform: g(f) = c f r, 0 < r < 1
Saving multiple image histograms
to a single CSV file
Data gathering
Scanning in the Image Files