Output details
11 - Computer Science and Informatics
University of Westminster
Improved batch fuzzy learning vector quantization for image compression
<23>Originality: The paper presents the development and evaluation of a novel batch fuzzy learning vector quantisation (FLVQ) algorithm. It addresses and solves the following problems: (a) selection of the initial value for the learning rate coinciding with the fuzziness parameter, (b) methodology for reducing high computational cost, (c) the transfer of training vectors to crisp mode.
Significance: The problem solved in this paper plays an important role in various image compression approaches.
Rigour: All major findings of this research are supported by mathematical analyses. Results published in a leading peer-reviewed journal.