Title: Estimation of Single-Gaussian and Gaussian mixture models for pattern recognition
Authors: Vaněk, Jan
Machlica, Lukáš
Psutka, Josef
Citation: VANĚK, Jan; MACHLICA, Lukᚡ PSUTKA, Josef. Estimation of Single-Gaussian and Gaussian mixture models for pattern recognition. In: Progress in pattern recognition, image analysis, computer vision, and applications. Berlin: Springer, 2013, p. 49-56. (Lectures notes in computer science; 8258). ISBN 978-3-642-41821-1.
Issue Date: 2013
Publisher: Springer
Document type: článek
URI: http://www.kky.zcu.cz/cs/publications/JanVanek_2013_Estimationof
ISBN: 978-3-642-41821-1
Keywords: odhad mí­ry pravděpodobnosti;směsi Gaussovských modelĹů;Kullback- Leiblerova divergence;odchylka;měří­tko
Keywords in different language: maximum likelihood estimation;Gaussian mixture models;Kullback- Leibler divergence;variance;scaling
Abstract in different language: Single-Gaussian and Gaussian-Mixture Models are utilized in various pattern recognition tasks. The model parameters are estimated usually via Maximum Likelihood Estimation (MLE) with respect to available training data. However, if only small amount of training data is available, the resulting model will not generalize well. Loosely speaking, classification performance given an unseen test set may be poor. In this paper, we propose a novel estimation technique of the model variances. Once the variances were estimated using MLE, they are multiplied by a scaling factor, which reflects the amount of uncertainty present in the limited sample set. The optimal value of the scaling factor is based on the Kullback-Leibler criterion and on the assumption that the training and test sets are sampled from the same source distribution. In addition, in the case of GMM, the proper number of components can be determined.
Rights: © Jan Vaněk - Lukáš Machlica - Josef V. Psutka - Josef Psutka
Appears in Collections:Články / Articles (KIV)
Články / Articles (KKY)

Files in This Item:
File Description SizeFormat 
JanVanek_2013_Estimationof.pdfPlný text208,74 kBAdobe PDFView/Open

Please use this identifier to cite or link to this item: http://hdl.handle.net/11025/17160

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.