Skip to content
ml-recall

#sobel

3 questions from Computer Vision Basics

Timed test

3 questions · 3 min · score and explanations at the end

Take a test
Q 1 / 3Score 0 / 0

Question 1: Short answer

mediumAI-checkedComputer Vision Basics

The Sobel kernels Kx=[−101−202−101]K_x = \begin{bmatrix}-1&0&1\\-2&0&2\\-1&0&1\end{bmatrix} and Ky=[−1−2−1000121]K_y = \begin{bmatrix}-1&-2&-1\\0&0&0\\1&2&1\end{bmatrix} are applied by cross-correlation (no kernel flip, as in a CNN layer) to the patch [0102001020202040]\begin{bmatrix}0&10&20\\0&10&20\\20&20&40\end{bmatrix}, giving the gradient estimates GxG_x and GyG_y at its centre. What is the gradient magnitude Gx2+Gy2\sqrt{G_x^2 + G_y^2}?

a number