Scribd
Upload
11 views9 pages

18cse390t U1 s4 Slo2 Content

The document discusses various image processing operations, particularly focusing on point operators, which are basic transformations where output pixel values depend solely on corresponding input pixel values. It covers examples such as brightness and contrast adjustments, histogram equalization, and color transformations. Additionally, it introduces compositing and matting techniques used in photo editing to combine foreground objects with different backgrounds.

Uploaded by

Deepa S
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
11 views9 pages

18cse390t U1 s4 Slo2 Content

The document discusses various image processing operations, particularly focusing on point operators, which are basic transformations where output pixel values depend solely on corresponding input pixel values. It covers examples such as brightness and contrast adjustments, histogram equalization, and color transformations. Additionally, it introduces compositing and matting techniques used in photo editing to combine foreground objects with different backgrounds.

Uploaded by

Deepa S
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 9

18CSE390T

Computer Vision
U1 - S4 - SLO-2 - Image Processing: Point Operators
Image Processing

Some common image processing operations:


(a) partial histogram equalization;
(b) orientation map computed from the second-order
steerable filter (Freeman1992) ©1992 IEEE;
(c) bilateral filter (Durand and Dorsey2002) © 2002
ACM;
(d) image pyramid;
(e) Laplacian pyramid blending (Burt and
Adelson1983b) © 1983 ACM;
(f) line-based image warping (Beier and Neely1992) ©
1992 ACM
Point Operators
• The simplest kinds of image processing transforms are point
operators
• Each output pixel’s value depends on only the corresponding input
pixel value
• Examples of such operators include brightness and contrast
adjustments as well as color correction and transformations
• In the image processing literature, such operations are also known as
point processes
Point Operators

(a) original image along with its three


color (per-channel) histograms;

(b) brightness increased (additive


offset, b = 16)

(c) contrast increased (multiplicative gain,


a = 1:1);

(d) gamma (partially) linearized ( = 1:2)


Point Operators

(e) full histogram equalization;

(f) partial histogram equalization


Pixel Transforms
• In the continuous domain, this can be denoted as

• where x is in the D-dimensional (usually D = 2 for images) domain of


the input and output functions f and g, which operate over some
range, which can either be scalar or vector valued.
• For discrete (sampled) images, the domain consists of a finite number
of pixel locations, x = (i; j), and we can write
Color Transforms
• While color images can be treated as arbitrary vector-valued
functions or collections of independent bands, it usually makes sense
to think about them as highly correlated signals with strong
connections to the image formation process, sensor design, and
human perception
• You can brightening a picture by adding a constant value to all three
(R,G and B) channels
• adding the same value to each color channel not only increases the
apparent intensity of each pixel, it can also affect the pixel’s hue and
saturation
Compositing and matting
• In many photo editing and visual effects applications, it is often
desirable to cut a foreground object out of one scene and put it on
top of a different background

(a) source image (b) extracted foreground object F


(c) alpha matte shown in grayscale (d) new composite C
Compositing and matting
• Compositing equation C = (1-)B + F . The images are taken from a
close-up of the region of the hair in the upper right part of the lion
• This operator attenuates the influence of the background image B by
a factor (1-) and then adds in the color (and opacity) values
corresponding to the foreground layer F
• It is convenient to represent the foreground colors in pre-multiplied
form, i.e. F
• But, when matting using local color consistency, the pure un-
multiplied foreground colors F are used, since these remain constant
(or vary slowly) in the vicinity of the object edge

You might also like