LECTURE 29

CORNER DETECTION
DAY ORDER – 2, HOUR – 3

Dr. R. SENTHILNATHAN M.E. PhD

Associate Professor
Department of Mechatronics Engineering
SRM Institute of Science and Technology

1 15MH323E – MACHINE VISION AND IMAGE 11-10-2018

PROCESSING (JUNE 2018 TO NOV 2018)
Key Point Features
 In computer vision, usually we need to find matching
points between different frames of an environment.

 If we know how two images relate to each other, we

can use both images to extract information of them.

 When we say matching points we are referring, in a

general sense, to characteristics in the scene that we can
recognize easily. We call these characteristics features.

 It must be uniquely recognizable

2 15MH323E – MACHINE VISION AND IMAGE PROCESSING (JUNE 2018 TO NOV 2018) 11-10-2018
Types of Image Features
 Edges

 Corners (also known as interest points)

 Blobs (also known as regions of interest )

3 15MH323E – MACHINE VISION AND IMAGE PROCESSING (JUNE 2018 TO NOV 2018) 11-10-2018
Corners
 Corner is the intersection of two edges, it
represents a point in which the directions of these
two edges change.

 Hence, the gradient of the image (in both

directions) have a high variation, which can be
used to detect it.

4 15MH323E – MACHINE VISION AND IMAGE PROCESSING (JUNE 2018 TO NOV 2018) 11-10-2018
Applications
 motion detection

 image registration

 video tracking

 panorama stitching

 3D modelling and
object recognition

5 15MH323E – MACHINE VISION AND IMAGE PROCESSING (JUNE 2018 TO NOV 2018) 11-10-2018
Harris Corner Detection
 Consider a grayscale image I . We are going to
sweep a window w(x,y) (with displacements u in
the x direction and v in the right direction) and
will calculate the variation of intensity.

6 15MH323E – MACHINE VISION AND IMAGE PROCESSING (JUNE 2018 TO NOV 2018) 11-10-2018
Harris Corner Detection
 Since we are looking for windows with corners,
we are looking for windows with a large variation
in intensity. Hence, we have to maximize the
equation above, specifically the term

7 15MH323E – MACHINE VISION AND IMAGE PROCESSING (JUNE 2018 TO NOV 2018) 11-10-2018
Harris Corner Detection

8 15MH323E – MACHINE VISION AND IMAGE PROCESSING (JUNE 2018 TO NOV 2018) 11-10-2018
Harris Corner Detection
 A score is calculated for each window, to
determine if it can possibly contain a corner:

9 15MH323E – MACHINE VISION AND IMAGE PROCESSING (JUNE 2018 TO NOV 2018) 11-10-2018