Skip to course content
Free computer vision course

Computer Vision and Multimodal AI

Module 02 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. Image format should be determined from…

2. Resizing an image down and back up…

3. HSV is most useful when you need to…

4. A model trained on quality-95 JPEGs and served quality-40 ones…

5. A loader that silently skips undecodable files…

---

Answer Key and Explanations

Check these only after attempting every question.

1. B - the file's header bytes

An extension is a claim. Trusting it produces a decoder error deep in a training loop on one unnamed file.

2. B - permanently destroys fine detail

Anything a few pixels across in the original is gone before the model sees it, whatever the architecture.

3. B - pick a colour independent of brightness

'Find the yellow object' is a hue range in HSV and an awkward condition in BGR that breaks when lighting changes.

4. B - sees a systematically different distribution

JPEG error is structured, following the 8x8 block grid, not random noise.

5. B - hides both dataset shrinkage and upstream changes

Return the reason and count rejections by kind - a rise in one kind is a signal about a source.

Practical Check

Apply this module to your own work: complete the module activity for *Loading, Resizing, Colour Spaces and File Formats*, 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.