• Home
  • Textbooks
  • Image processing, Analysis, and Machine Vision
  • Image Pre-Processing

Image processing, Analysis, and Machine Vision

Milan Sonka, Václav Hlavác, Roger Boyle

Chapter 5

Image Pre-Processing - all with Video Answers

Educators


Chapter Questions

Problem 1

What is the main aim of image pre-processing?

Check back soon!

Problem 2

Give examples of situations in which brightness transformations, geometric transformations, smoothing, edge detection, and/or image restorations are typically applied.

Check back soon!

Problem 3

What is the main difference between brightness correction and gray-scale transformation?

Check back soon!

Problem 4

Explain the rationale of histogram equalization.

Check back soon!

Problem 5

Explain why the histogram of a discrete image is not flat after histogram equalization.

Check back soon!

Problem 6

Consider the image given in Figure 5.3a. After histogram equalization (Figure 5.3b), much more detail is visible. Does histogram equalization increase the amount of information contained in image data? Explain.

Check back soon!
View

Problem 7

What are the two main steps of geometric transforms?

Victor Salazar
Victor Salazar
Numerade Educator

Problem 8

What is the minimum number of corresponding pixel pairs that must be determined if the following transforms are used to perform a geometric correction?
(a) Bilinear transform
(b) Affine transform

Check back soon!
View

Problem 9

Give a geometric transformation equation for
(a) Rotation
(b) Change of scale
(c) Skewing by an angle

Victor Salazar
Victor Salazar
Numerade Educator

Problem 10

Consider brightness interpolation-explain why it is better to perform brightness interpolation using brightness values of neighboring points in the input image than interpolating in the output image.

Check back soon!

Problem 11

Explain the principles of nearest-neighbor interpolation, linear interpolation, and bicubic interpolation.

Check back soon!

Problem 12

Explain why smoothing and edge detection have conflicting aims.

Check back soon!

Problem 13

Explain why Gaussian filtering is often the preferred averaging method.

Check back soon!

Problem 14

Explain why smoothing typically blurs image edges.

Check back soon!

Problem 15

Name several smoothing methods that try to avoid image blurring. Explain their main principles.

Check back soon!

Problem 16

Explain why median filtering performs well in images corrupted by impulse noise.

Check back soon!

Problem 17

Give convolution masks for the following edge detectors:
(a) Roberts
(b) Laplace
(c) Prewitt
(d) Sobel
(e) Kirsch
Which ones can serve as compass operators? List several applications in which determining edge direction is important.

Check back soon!

Problem 18

Explain why subtraction of a second derivative of the image function from the original image results in the visual effect of image sharpening.

Check back soon!
00:52

Problem 19

What are LoG and DoG? How do you compute them? How are they used?

Liuxi Sun
Liuxi Sun
Numerade Educator

Problem 20

Propose a robust way of detecting significant image edges using zero-crossings.

Check back soon!
00:50

Problem 21

Explain why LoG is a better edge detector than Laplace edge detector.

David Collins
David Collins
Numerade Educator
14:33

Problem 22

Explain the notion of scale in image processing.

Geena Pullo
Geena Pullo
Numerade Educator

Problem 23

Explain the importance of hysteresis thresholding and non-maximal suppression in the Canny edge detection process. How do these two concepts influence the resulting edge image?

Check back soon!

Problem 24

Explain the principles of noise suppression, histogram modification, and contrast enhancement performed in adaptive neighborhoods.

Check back soon!
01:11

Problem 25

What is the aperture problem? How does it affect finding correspondence for line features and corner features? Add a simple sketch to your answer demonstrating the concept of aperture and the consequences for correspondence of lines and corners.

Ajay Singhal
Ajay Singhal
Numerade Educator

Problem 26

Explain the principles of image restoration based on
(a) Inverse convolution
(b) Inverse filtration
(c) Whener filtration
List the main differences among the above methods.

Check back soon!
00:56

Problem 27

Give image distortion functions for
(a) Relative camera motion
(b) Out-of-focus lens
(c) Atmospheric turbulence

Mark Scythian
Mark Scythian
Numerade Educator