Module 03 Knowledge Check
5 questions. Pass mark 4 out of 5. Answer every question before checking the answer key below, then retry after reading the feedback.
1. Increasing a Gaussian blur kernel…
- A. removes noise while preserving edges
- B. removes noise and edge detail together
- C. sharpens edges
- D. has no effect on edges
2. Sharpening an image amplifies…
- A. only real edges
- B. edges and noise equally
- C. only noise
- D. neither
3. An image with a strong lighting gradient needs…
- A. a higher global threshold
- B. adaptive thresholding
- C. Otsu's method
- D. histogram equalisation only
4. The correct morphology order for removing specks and filling holes is…
- A. close then open
- B. open then close
- C. either order
- D. close twice
5. A pipeline tuned on bright images and deployed on dim ones…
- A. raises an error
- B. fails silently - the object is simply not detected
- C. adapts automatically
- D. produces a warning
---
Answer Key and Explanations
Check these only after attempting every question.
1. B - removes noise and edge detail together
Both noise and edge detail are small fast changes, and a low-pass filter cannot distinguish them.
2. B - edges and noise equally
To the filter both are the same phenomenon: a pixel differing from its neighbours.
3. B - adaptive thresholding
No single global value works when the background at one end is brighter than the object at the other.
4. B - open then close
Closing first grows the specks into blobs that opening can no longer remove.
5. B - fails silently - the object is simply not detected
Every hard-coded constant is a hidden assumption about lighting that only different images expose.
Practical Check
Apply this module to your own work: complete the module activity for *Basic Image Processing with OpenCV*, then write one sentence naming what your result shows and one naming what it does not.
Strong Answer Pattern
A strong answer names the task, the evidence used, the check performed, and the remaining limitation. It avoids "proved", "guaranteed", or "always" unless the evidence genuinely supports it.