Skip to course content
Free computer vision course

Computer Vision and Multimodal AI

Module 04 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. An edge detector responds to…

2. Two objects that touch produce…

3. Otsu's method solves…

4. Classical segmentation assumes…

5. IoU alone is insufficient because it…

---

Answer Key and Explanations

Check these only after attempting every question.

1. B - any intensity change, including shadows and printed lines

It measures gradient. The interpretation as an object boundary is yours.

2. B - one contour

They are one connected region, and the information needed to split them is not in the binary mask.

3. B - the choice of a global threshold without tuning

It picks one number optimally, which does not help when no single number is correct.

4. B - the target has a consistent, describable appearance

Where that assumption fails, parameter tuning is time spent on something that is wrong rather than mistuned.

5. B - does not say which direction the prediction is wrong

'Too big' has perfect recall and poor precision; the direction determines the fix.

Practical Check

Apply this module to your own work: complete the module activity for *Edges, Contours, Thresholding and Segmentation Intuition*, 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.