Weighted Parzen Windows for Pattern Classification

摘要

This thesis presents a novel pattern recognition approach, named Weighted ParzenWindows (WPW). This technique uses a nonparametric supervised learning algorithm to estimate the underlying density function for each set of training data. Classification is accomplished by using the estimated density functions in a minimum risk strategy. The proposed approach reduces the effective size of the training data without introducing significant classification error. Furthermore, it is shown that Bayes-Gaussian, minimum Euclidean-distance, Parzen-window, and nearest-neighbor classifiers can be viewed as special cases of the WPW technique. Experimental results are presented to demonstrate the performance of the WPW algorithm as compared to traditional classifiers. Parzen Windows, Weighted, Pattern, Recognition, Classification, Algorithm.