Comments on "Modified K-means algorithm for vector quantizer design"

View/ Open
Author(s)
Paliwal, KK
Ramasubramanian, V
Griffith University Author(s)
Year published
2000
Metadata
Show full item recordAbstract
Recently a modified -means algorithm for vector quantization design has been proposed where the codevector updating step is as follows: new codevector = current codevector + scale factor (new centroid current codevector). This algorithm uses a fixed value for the scale factor. In this paper, we propose the use of a variable scale factor which is a function of the iteration number. For the vector quantization of image data, we show that it offers faster convergence than the modified -means algorithm with a fixed scale factor, without affecting the optimality of the codebook.Recently a modified -means algorithm for vector quantization design has been proposed where the codevector updating step is as follows: new codevector = current codevector + scale factor (new centroid current codevector). This algorithm uses a fixed value for the scale factor. In this paper, we propose the use of a variable scale factor which is a function of the iteration number. For the vector quantization of image data, we show that it offers faster convergence than the modified -means algorithm with a fixed scale factor, without affecting the optimality of the codebook.
View less >
View less >
Journal Title
IEEE Transactions on Image Processing
Volume
9
Issue
11
Publisher URI
Copyright Statement
© 2000 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Subject
Cognitive and computational psychology
History, heritage and archaeology