QUESTION $1[$TOTAL MARKS: $25]$

Q $1($a$)[2$ Marks$]$

State $4$ key reasons why machine vision is generally considered useful in industrial

environments.

Q $1($b$)[6$ Marks$]$

Compare and contrast the key differences between human and machine vision

systems. What are the two key types of error you would expect to find in a machine

vision system? State the cost implication of each type of error on the overall system

cost$.$

Q $1($c$)[4$ Marks$]$

Compare and contrast Template Matching and Pattern Recognition using Feature

Extraction approaches to image analysis. Outline an example of how each approach

is commonly used in image analysis.

Q $1($d$)[5$ Marks$]$

Compare and contrast Global, Adaptive and Dynamic based approaches to the image

thresholding task. Outline one approach to image thresholding that is data driven $($i$.$e$.$

not dependent on a user defined fixed threshold value$).$

Q $1($e$)[6$ Marks$]$

Develop a sequence of robust image processing and analysis steps using pseudo

code to find the number of objects $($gears$)$ in the binary image illustrated in Figure

Q$1\mathrm{.}1.$ Your approach must be invariant to image rotation. Comment on the robustness

of your approach in the presence of Gaussian noise.

Figure Q$1\mathrm{.}1$: Binary image.

EE$425$ Image Processing and Analysis

Semester $1$ Examinations $2018/2019$ Page $3$ of $6$

Q $1($f$)[2$ Marks$]$

Compare and contrast Histogram Stretching and Histogram Equalization approaches

to image processing. Give an example of the application of each approach.