This preview shows page 1. Sign up to view the full content.
Unformatted text preview: e are K clusters C1, C2, …., CK, with means m1, m2,,……, mK. A
least square error measure, D, can be defined to measure how close the data are to their assigned
clusters. A least square clustering procedure could consider all possible partitions into K clusters
and select the one that minimizes D.
Isodata clustering: Edge based image representation:
Edge Detection. Faculty of Engineering Robotics Technology MECH 4041 11
B.Eng (Hons.) Mechatronics S. Venkannah Mechanical and Production Engineering Department Edge detection considers the intensity change that occurs in the pixels at the boundary or edges
of a part. Given that a region of similar attributes has been found but the boundary shape is
unknown, the boundary can be determined by a simple edge following procedure. For the binary
image, the procedure is to scan the image until a pixel within the region is encountered. For a
pixel within the region, turn left and step, otherwise turn right and step. The procedure is
stopped when the boundary is traversed and the path has returned to the starting pixel. The
contour following procedure can be extended to gray level images.
There are other approaches to edge detection e.g.
First difference/one dimensional methods
Each operator requires consideration of at least two pixels, the local sub image shown below will
DEF Faculty of Engineering Robotics Technology MECH 4041 12
B.Eng (Hons.) Mechatronics S. Venkannah Mechanical and Production Engineering Department GHI
A through I are intensity values. “E” represents the (x,y) location of the image point under
consideration and A through D and F through I are E’s Neighbors.
The first difference/one dimensional operators are of the following generic type:
Edge 1 = |I-E| + | E-A|
Edge 2 = | F-E| + | E-D|
Edge 3 = |H-E| + | E-B|
Edge 4 = |G-E| + | E-C|
Edge 1 computes a first difference function in the “northwest:southeast’ direction. This
particular edge function is most sensitive to edges perpendicular to the direction or orientation of
computation and essentially returns a magnitude of edge in only one spatial direction. The
functions Edge 2...
View Full Document
- Spring '14