Document Type
Thesis
Date of Award
5-31-1990
Degree Name
Master of Science in Electrical Engineering - (M.S.)
Department
Electrical and Computer Engineering
First Advisor
Nirwan Ansari
Second Advisor
Ali N. Akansu
Third Advisor
Irving Y. Wang
Abstract
Dominant point detection is one of the most important preprocessing steps for landmark-based shape recognition and point-based motion estimation. Two new methods for detecting dominant points are presented. Both methods do not require any input parameter and the dominant points obtained by these methods remain relatively the same even when the object curve is scaled or rotated.
In the first method, for each boundary point, a support region is assigned to the point based on its local properties. Each point is then smoothed by a Gaussian filter with a width proportional to its determined support region. A significance measure for each point is then computed. Dominant points are finally obtained through nonmaximum suppression.
The second method is rather simple. It traces the contour of an object curve, and, for each boundary point, it assigns a "chain code" which indicates the direction of the trace. Dominant points are then determined by detecting the change of direction of each point.
These two methods lead to an important observation that the performance of a dominant points detection algorithm depends not only on the significance measure and the support region Mit also on the presence of noise.
Unlike other dominant point detection algorithms which are sensitive to scaling and rotation of the object curve, these two new methods will overcome this difficulty. Furthermore, they are robust in the presence of noise.
The proposed two methods are compared to those of several other dominant point detection algorithms in terms of the CPU processing time, the approximation errors and the number of the detected dominant points of a given curve.
Recommended Citation
Huang, Kuo-wei, "Non-parametric dominant point detection algorithms" (1990). Theses. 2743.
https://digitalcommons.njit.edu/theses/2743
