Video Lecturers on Digital Image Processing Gholamreza Anbarjafari

Video Lecturers on Digital Image Processing Gholamreza Anbarjafari, Ph. D Digital Image Processing Contrast Enhancement: Part I

Video Lecturers on Digital Image Processing Contrast Enhancement Gholamreza Anbarjafari, Ph. D

Video Lecturers on Digital Image Processing Gholamreza Anbarjafari, Ph. D Converts to black & white Linear Part contributes to the contrast stretching © 2002 R. C. Gonzalez & R. E. Woods

Video Lecturers on Digital Image Processing Gholamreza Anbarjafari, Ph. D Some basic grey-level transformation functions used for contrast enhancement L=2 k k: number of bits used to represent each pixel © 2002 R. C. Gonzalez & R. E. Woods

Video Lecturers on Digital Image Processing Gholamreza Anbarjafari, Ph. D Image Negatives s= (L-1)-r s is the pixel value of the output image and r is the pixel value of the input image. (left) Original digital mammogram. (right) Negative image obtained using the negative transformation © 2002 R. C. Gonzalez & R. E. Woods

Video Lecturers on Digital Image Processing Gholamreza Anbarjafari, Ph. D Logarithmic Transformations s= c log(1+r) s is the pixel value of the output image and r is the pixel value of the input image. (left) Fourier spectrum of Barbara’s image. (right) Result of applying the log transformation

Video Lecturers on Digital Image Processing Gholamreza Anbarjafari, Ph. D Logarithmic Transformations s= c rγ s is the pixel value of the output image and r is the pixel value of the input image. (γ ≥ 0 and 0 ≤ r ≤ 1) Plots for various values of γ (c=1) © 2002 R. C. Gonzalez & R. E. Woods

Video Lecturers on Digital Image Processing Gholamreza Anbarjafari, Ph. D Logarithmic Transformations a b c d (a) original image. (b) γ = 0. 5. (c) γ = 0. 3. (d) γ = 0. 7.

Video Lecturers on Digital Image Processing Gholamreza Anbarjafari, Ph. D Piecewise-Linear Transformations An example of piecewise linear transformation function © 2002 R. C. Gonzalez & R. E. Woods

Video Lecturers on Digital Image Processing Gholamreza Anbarjafari, Ph. D Piecewise-Linear Transformations grey-level slicing Pixel values between [A, B] are highlighted Other pixel values are preserved Other pixel values are darkened © 2002 R. C. Gonzalez & R. E. Woods

Video Lecturers on Digital Image Processing Gholamreza Anbarjafari, Ph. D Piecewise-Linear Transformations Bit Plane slicing An 8 -bit fractal image © 2002 R. C. Gonzalez & R. E. Woods

Video Lecturers on Digital Image Processing Gholamreza Anbarjafari, Ph. D Piecewise-Linear Transformations MSB Bit Plane slicing LSB © 2002 R. C. Gonzalez & R. E. Woods

Video Lecturers on Digital Image Processing Gholamreza Anbarjafari, Ph. D Histogram Processing Normalized histogram : is p(rk)=nk/n, for k=0, 1, …, L-1 and p(rk) can be considered to give an estimate of the probability of occurrence of ray level rk.

Video Lecturers on Digital Image Processing Gholamreza Anbarjafari, Ph. D Histogram of 4 basic grey-level characteristics Dark image Bright image © 2002 R. C. Gonzalez & R. E. Woods

Video Lecturers on Digital Image Processing Gholamreza Anbarjafari, Ph. D Histogram of 4 basic grey-level characteristics Low contrast image High contrast image © 2002 R. C. Gonzalez & R. E. Woods

Video Lecturers on Digital Image Processing Gholamreza Anbarjafari, Ph. D Summary § We have looked at: § What is contrast stretching? § What are different transformations? § What is histogram and histogram processing? § Next time we will talk about more on contrast stretching by using other techniques