Faculty of Information Technology

Ton Duc Thang University

August 2023
 Edge Detection
 Extracting The Edges From An Image

 Objective
 What is edge detection and how it can be helpful in image classification.
 Learn how kernels are used to identify the edges in a given image.

https://www.analyticsvidhya.com/blog/2021/03/edge-detection-extracting-the-edges-from-an-image/

@2023 Pham Van Huy and Trinh Hung Cuong 2

 Edge Detection: image classification

Can you differentiate between

the objects?

@2023 Pham Van Huy and Trinh Hung Cuong 3

 Edge Detection: image classification

Can you still easily classify

the images?

@2023 Pham Van Huy and Trinh Hung Cuong 4

 Edge Detection: image classification
 removed the color, the background, and the other minute details from the
pictures
 extract only the edges, we would still be able to classify the image.

@2023 Pham Van Huy and Trinh Hung Cuong 5

 Edges
 Edges are significant local changes of intensity in an image.
 Edges typically occur on the boundary between two different regions in an
image (Trucco, Chapt 4 AND Jain et al., Chapt 5)

@2023 Pham Van Huy and Trinh Hung Cuong 6

 Goal of edge detection
 Produce a line drawing of a scene from an image of that scene
 Important features can be extracted from the edges of an image (e.g.,
corners, lines, curves)
 These features are used by higher-level computer vision algorithms (e.g.,
recognition)

@2023 Pham Van Huy and Trinh Hung Cuong 7

 What causes intensity changes?
 Geometric events
 object boundary (discontinuity in depth and/or surface color and texture)
 surface boundary (discontinuity in surface orientation and/or surface color and texture)

 Non-geometric events
 specularity (direct reflection of light, such as a mirror)
 shadows (from other objects or from the same object)
 inter-reflections

@2023 Pham Van Huy and Trinh Hung Cuong 8

 Edge Detection
 Identify the edges by looking at the numbers or the pixel values

there is a
significant
difference
between the pixel
values around the
edge

@2023 Pham Van Huy and Trinh Hung Cuong 9

 Edge Detection (ct)
 Edge detection is an image processing technique for finding the boundaries
of an object in the given image
 Edges are the part of the image that represents the boundary or the shape of
the object in the image
 the pixel values around the edge show a significant difference or a sudden change in the
pixel values

 Based on this fact we can identify which pixels represent the edge or which
pixel lie on the edge.

@2023 Pham Van Huy and Trinh Hung Cuong 10

 How to Extract the Edges
 compare the pixel values with its surrounding pixels, to find out if a particular
pixel lies on the edge
 use a matrix known as the kernel and perform the element-wise multiplication

@2023 Pham Van Huy and Trinh Hung Cuong 11

 How to Extract the Edges (ct)

@2023 Pham Van Huy and Trinh Hung Cuong 12

 How to Extract the Edges (ct)

@2023 Pham Van Huy and Trinh Hung Cuong 13

 How to Extract the Edges (ct)

@2023 Pham Van Huy and Trinh Hung Cuong 14

 How to Extract the Edges (ct)

@2023 Pham Van Huy and Trinh Hung Cuong 15

 Prewitt & Sobel kernels

Sobel kernels, higher importance is

given to the pixel values right next
to the target pixel

@2023 Pham Van Huy and Trinh Hung Cuong 16

 Prewitt kernels
 Vertical direction -1 0 1
-1 0 1
-1 0 1

@2023 Pham Van Huy and Trinh Hung Cuong 17

 Prewitt kernels (ct)
-1 -1 -1
 Horizontal direction
0 0 0
1 1 1

@2023 Pham Van Huy and Trinh Hung Cuong 18

 Prewitt kernel – both directions

@2023 Pham Van Huy and Trinh Hung Cuong 19

 Ex. 1
 Apply Prewitt/Sobel operators in X direction, Y direction, and both directions
into the following image:

@2023 Pham Van Huy and Trinh Hung Cuong 20

 Edges again
 An edge is a place of rapid change in the image intensity function

Points which lie on an edge can be detected by

• detecting local maxima or minima of the first
edges correspond to
derivative extrema of derivative

@2023 Pham Van Huy and Trinh Hung Cuong 21

 Edges and derivate
 derivatives only exists for continuous functions but the image is a discrete 2D
intensity function
 approximated the image gradients using finite approximation as

https://theailearner.com/tag/prewitt-
operator/

prefer the central difference as

shown above

@2023 Pham Van Huy and Trinh Hung Cuong 22

 Edges and derivate (ct)
 obtain the derivative filter in x and y directions as shown below

• assumed that the x-coordinate is increasing in the “right”-direction, and y-coordinate in

the “down”-direction
• By weighting these x and y derivatives, we can obtain different edge detection filters

@2023 Pham Van Huy and Trinh Hung Cuong 23

 Sobel Operator
 multiplying the x, and y-derivative filters obtained above with some
smoothing filter(1D) in the other direction
 For example, a 3×3 Sobel-x and Sobel-y filter can be obtained as

Gaussian filter is used for

blurring thus, the Sobel
operator computes the
gradient with smoothing

@2023 Pham Van Huy and Trinh Hung Cuong 24

 Sobel operators (ct)
 Convolve these Sobel operators with the image, they estimate the gradients
in the x, and y-directions(say Gx and Gy). For each point, we can calculate
the gradient magnitude and direction as

https://docs.opencv.org/3.4/d2/d2c/tutorial_sobel_derivatives.html

@2023 Pham Van Huy and Trinh Hung Cuong 25

 Prewitt Operator
 x, and y-derivative filters are weighted with the standard averaging filter as
shown below

@2023 Pham Van Huy and Trinh Hung Cuong 26

 Prewitt operator example

 1 0 1 

 1 0  1 
 1 0 1 

Original
1024x710  1 1 1 
 
 0 0 0 
 1 1 1 
Digital Image Processing: Bernd Girod, © 2013 Stanford
University -- Edge Detection 27

@2023 Pham Van Huy and Trinh Hung Cuong 27

 Prewitt operator example (cont.)

Sum of squared threshold = 900 threshold = 4500 threshold = 7200

horizontal and
vertical gradients
(log display)

Digital Image Processing: Bernd Girod, © 2013 Stanford University -- Edge Detection 28

@2023 Pham Van Huy and Trinh Hung Cuong 28

 Sobel operator example

Sum of squared threshold = 1600 threshold = 8000 threshold = 12800

horizontal and
vertical gradients
(log display)

Digital Image Processing: Bernd Girod, © 2013 Stanford University -- Edge Detection 29

@2023 Pham Van Huy and Trinh Hung Cuong 29

 Canny Edge Detection
 Canny Edge Detection is a popular edge detection algorithm. It was
developed by John F. Canny
 It is a multi-stage algorithm:

 Noise Reduction
 Edge detection is susceptible to noise in the image, first step is to remove the noise in
the image with a Gaussian filter

https://docs.opencv.org/4.x/da/d22/tutorial_py_canny.html

@2023 Pham Van Huy and Trinh Hung Cuong 30

 Canny Edge Detection (ct)
 Finding Intensity Gradient of the Image
 Smoothened image is then filtered with a Sobel kernel in both horizontal and vertical
direction
 to get first derivative in horizontal direction (𝐺𝑥 ) and vertical direction (𝐺𝑦 )
 find edge gradient and direction for each pixel (gradient magnitude and angle):

 Gradient direction is always perpendicular to edges. It is rounded to one of four angles

representing vertical, horizontal and two diagonal directions.

@2023 Pham Van Huy and Trinh Hung Cuong 31

 Canny Edge Detection (ct)
 Non-maximum Suppression
 remove any unwanted pixels which may not constitute the edge
 at every pixel, pixel is checked if it is a local maximum in its neighborhood in the
direction of gradient
 Its gradient magnitude is smaller than either of its neighbors?

Point A is on the edge ( in vertical direction).

Point B and C are in gradient directions. So
point A is checked with point B and C to see if it
forms a local maximum. If so, it is considered
for next stage, otherwise, it is suppressed ( put
to zero).

@2023 Pham Van Huy and Trinh Hung Cuong 32

 Canny Edge Detection (ct)
 Hysteresis Thresholding
 This stage decides which are all edges are really edges and which are not
 Use two threshold values, minVal and maxVal
 Any edges with intensity gradient more than maxVal are sure to be edges and those
below minVal are sure to be non-edges
 Those who lie between these two thresholds are classified edges or non-edges based
on their connectivity. If they are connected to "sure-edge«(strong edge) pixels, they
are considered to be part of edges. Otherwise, they are also discarded.

@2023 Pham Van Huy and Trinh Hung Cuong 33

 Canny Edge Detection (ct)
 The edge A is above the maxVal, so considered as "sure-edge". Although edge C is below
maxVal, it is connected to edge A, so that also considered as valid edge and we get that
full curve. But edge B, although it is above minVal and is in same region as that of edge
C, it is not connected to any "sure-edge", so that is discarded.

@2023 Pham Van Huy and Trinh Hung Cuong 34

 Canny Edge Detection (ct)
 Hysteresis Thresholding
 This stage also removes small pixels noises on the assumption that edges are long lines

https://docs.opencv.org/4.x/da/d22/tutorial_py_canny.html

@2023 Pham Van Huy and Trinh Hung Cuong 35

 Ex. 2
 Apply Canny operator into the following image:

@2023 Pham Van Huy and Trinh Hung Cuong 36

 Template Matching
 a technique for finding areas of an image that match (are similar) to a
template image (patch)
 compare the template image against the source image by sliding it

https://docs.opencv.org/3.4/de/da9/tutorial_template_matching.html

@2023 Pham Van Huy and Trinh Hung Cuong 37

 Template Matching (ct)
 moving the patch one pixel at a time (left to right, up to down)
 At each location, a metric is calculated so it represents how "good" or "bad" the match at
that location is (or how similar the patch is to that particular area of the source image)

https://docs.opencv.org/3.4/d4/dc6/tutorial_py_template_matching.html

@2023 Pham Van Huy and Trinh Hung Cuong 38

 OpenCV & Machine Learning
 Machine Learning Library (MLL) is a set of classes and functions for
statistical classification, regression, and clustering of data

https://docs.opencv.org/4.x/dd/ded/group__ml.html

https://docs.opencv.org/4.x/d8/d4b/tutorial_py_knn_opencv.html

@2023 Pham Van Huy and Trinh Hung Cuong 39

 OpenCV & Machine Learning (ct)
 OCR of Hand-written Data using kNN

@2023 Pham Van Huy and Trinh Hung Cuong 40

 References
1. https://docs.opencv.org/4.x/d4/d86/group__imgproc__filter.html
2. https://www.youtube.com/watch?app=desktop&v=kGHz-cEyjiE
3. https://docs.opencv.org/4.x/d4/dc6/tutorial_py_template_matching.html
4. https://www.youtube.com/watch?app=desktop&v=kGHz-cEyjiE
5. https://vincmazet.github.io/bip/filtering/convolution.html

@2023 Pham Van Huy and Trinh Hung Cuong 41