Image gradients, Sobel, and Canny
WHAT IT TESTS: edge-detection foundations. OUTLINE: the gradient measures local intensity change in x and y; Sobel approximates it via convolution kernels; Canny uses gradient magnitude and direction plus non-max suppression and hysteresis.
WHAT IT TESTS: whether you connect derivatives to edges. ANSWER OUTLINE: an image gradient is the vector of partial derivatives of intensity in x and y; its magnitude marks how sharply brightness changes and its direction points across the edge. Sobel approximates these derivatives with small convolution kernels that also smooth. Canny builds on the gradient: smooth, compute gradient magnitude and direction, apply non-maximum suppression to thin edges, then double-threshold with hysteresis to link them.
Read the original → interview
- #image-gradient
- #sobel
- #canny
- #edge-detection
- #convolution
Get five bites like this every day.
Tezvyn delivers a daily feed of 60-second tech bites with quizzes to lock in what you learn.