Scribd
Upload
40 views

ME4707 Robótica: Herramientas de Visión Computacional II

This document discusses edge detection in images using computer vision techniques. It begins by defining edges as curves that represent discontinuities in surface normals, depth, color, or illumination. It then discusses how the image gradient can be used to detect edges, where the gradient direction indicates the edge orientation and the gradient magnitude indicates the edge strength. It presents discrete gradient operators like the Sobel operator to approximate derivatives in digital images. It also discusses using the Laplacian of Gaussian (LoG) filter at multiple scales to detect edges while eliminating noise. Finally, it notes that subtracting a smoothed image from the original can also help identify edges.

Uploaded by

Carolina Garcia Guerrero
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
40 views

ME4707 Robótica: Herramientas de Visión Computacional II

This document discusses edge detection in images using computer vision techniques. It begins by defining edges as curves that represent discontinuities in surface normals, depth, color, or illumination. It then discusses how the image gradient can be used to detect edges, where the gradient direction indicates the edge orientation and the gradient magnitude indicates the edge strength. It presents discrete gradient operators like the Sobel operator to approximate derivatives in digital images. It also discusses using the Laplacian of Gaussian (LoG) filter at multiple scales to detect edges while eliminating noise. Finally, it notes that subtracting a smoothed image from the original can also help identify edges.

Uploaded by

Carolina Garcia Guerrero
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 48

ME4707

Robótica

Herramientas de Visión
Computacional II
Edge detection

Convert a 2D image into a set of curves


• Extracts salient features of the scene
• More compact than pixels
Origin of Edges

surface normal discontinuity

depth discontinuity

surface color discontinuity

illumination discontinuity

Edges are caused by a variety of factors


Edge detection

How can you tell that a pixel is on an edge?


Profiles of image intensity edges
Image gradient
The gradient of an image:

The gradient points in the direction of most rapid change in intensity

The gradient direction is given by:

• how does this relate to the direction of the edge?


The edge strength is given by the gradient magnitude
The discrete gradient
How can we differentiate a digital image f[x,y]?
• Option 1: reconstruct a continuous image, then take gradient
• Option 2: take discrete derivative (finite difference)

?
Gradient operators

Common simplification:
The Sobel operator
Better approximations of the derivatives exist
• The Sobel operators below are very commonly used

-1 0 1 1 2 1
-2 0 2 0 0 0
-1 0 1 -1 -2 -1

• The standard defn. of the Sobel operator omits the 1/8 term
– doesn’t make a difference for edge detection
– the 1/8 term is needed to get the right gradient value, however
Example:
Image enhancement using Laplacian
Effects of noise
Consider a single row or column of the image
• Plotting intensity as a function of position gives a signal

Where is the edge?


Solution: smooth first

Where is the edge? Look for peaks in


Derivative theorem of convolution

This saves us one operation:


Laplacian of Gaussian
Consider

Laplacian of Gaussian
operator

Where is the edge? Zero-crossings of bottom graph


2D edge detection filters

Laplacian of Gaussian (LoG)

Gaussian derivative of Gaussian

is the Laplacian operator:


Scale
Smoothing
Eliminates noise edges.
Makes edges smoother.
Removes fine detail.
(Forsyth & Ponce)
fine scale
high
threshold
coarse
scale,
high
threshold
coarse
scale
low
threshold
Scale space (Lindeberg, Witkin)
first derivative peaks

larger

Gaussian filtered signal

Properties of scale space (w/ Gaussian smoothing)


• edge position may shift with increasing scale ()
• two edges may merge with increasing scale
• an edge may not split into two with increasing scale
Edge detection by subtraction

original
Edge detection by subtraction

smoothed (5x5 Gaussian)


Edge detection by subtraction

Why does
this work?

smoothed – original
(scaled by 4, offset +128) filter demo
Lecturas del capítulo:
Gonzales, R.C. Woods, R.E. “Digital Image Processing”

• Chapter 3: Image Enhancement in the Spatial Domain.


• Chapter 9: Morphological Image Processing.
• Chapter 10: Image Segmentation.

You might also like