• Home
  • Textbooks
  • Image processing, Analysis, and Machine Vision
  • Image Understanding

Image processing, Analysis, and Machine Vision

Milan Sonka, Václav Hlavác, Roger Boyle

Chapter 10

Image Understanding - all with Video Answers

Educators


Chapter Questions

Problem 1

Explain how human vision differs from computer vision. Why is the problem of image understanding so difficult when every small child "knows how to do it"?

Check back soon!

Problem 2

Explain with examples the differences between lower and upper processing levels.

Check back soon!

Problem 3

Explain the main ideas of the following image understanding control strategies; if possible, provide a block diagram. Specify their primary applicability within the image understanding process.

Check back soon!

Problem 4

What is conflict resolution? When is it needed?

Check back soon!
02:26

Problem 5

What is the difference between short-term and long-term memory?

Anand Jangid
Anand Jangid
Numerade Educator
01:35

Problem 6

Give a real-world example of an image understanding application (other than those in the text) in which each of bottom-up, top-doun and combined control strategies may be used.

Nicole Smina
Nicole Smina
Numerade Educator

Problem 8

Summarize the key location, feature extruction and matching phases of SIFT.

Check back soon!

Problem 9

Take a linear 2D data set: add noise to selected data points until a least-squares fit fails to come close to 'correct' (many easily available packages will do this). What can you say about the perturbations you have made to achieve this?

Check back soon!

Problem 10

What kind of information can be represented by point distribution models?

Check back soon!
01:23

Problem 10

Explain the process of determining the modes of variation represented by point distribution models.

Raushan Kumar
Raushan Kumar
Numerade Educator

Problem 11

Considering information provided in Table 10.1, how many principal components must be used in the point distribution model to leave less than $5 \%$ variation unexplained?

Check back soon!

Problem 12

What is the main difference between the PDM and AAM?

Check back soon!

Problem 13

List and explain all steps needed for
(a) AAM training and
(b) AAM-based segmentation

Check back soon!

Problem 14

Give the most obvious example of how statistical pattern recognition can be used in classification/labeling of multi-spectral satellite image data.

Check back soon!

Problem 15

Give the essential rationale why a boosted cascade of classifiers is an efficient approach to object detection.

Check back soon!

Problem 16

Considering AdaBoost, when and why do you stop boosting rounds?

Check back soon!

Problem 17

Explain principles of the joint classification-regression process when using random forests for object detection and localization.

Check back soon!

Problem 18

Explain the main strategy of discrete labeling Give a real-world example of image interpretation to which discrete labeling can be applied, providing details.

Check back soon!
View

Problem 19

Explain why discrete relaxation is a special case of probabilistic relaxation.

Victor Salazar
Victor Salazar
Numerade Educator

Problem 20

Explain the principle of genetic image segmentation and interpretation. Why are primary and specific adjacency graphs used?

Check back soon!

Problem 21

Name some shortcomings of conventional image segmentation based on region growing. and on semantic region growing. Does genetic image segmentation and interpretation solve these shortcomings? Which ones and how?

Check back soon!

Problem 22

Define an order-k Markov model.

Check back soon!

Problem 23

Define an order-k Hidden Markov model.

Check back soon!

Problem 24

Define in the context of HMMs:
$\bullet$ Evaluation
$\bullet$ Decoding
$\bullet$ Learning

Check back soon!
04:15

Problem 25

Cite with illustration some problems in which equation (10.85) well describes a vision related problem.

Ryan Hood
Ryan Hood
Numerade Educator
01:35

Problem 26

Generate and plot some mixtures of 2,3 and 4 1D Gaussians. Demonstrate to yourself that recapturing the original parameters from observations of the mixture would be difficult.

Manik Pulyani
Manik Pulyani
Numerade Educator