Open AccessDivergence based SLIC
Author(s) -
Gupta A.K.,
Seal A.,
Khanna P.
Publication year - 2019
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
eISSN - 1350-911X
pISSN - 0013-5194
DOI - 10.1049/el.2019.1092
Subject(s) - divergence (linguistics) , measure (data warehouse) , cluster analysis , metric (unit) , computer science , euclidean distance , artificial intelligence , boundary (topology) , pattern recognition (psychology) , cluster (spacecraft) , distance measures , computation , triangle inequality , plane (geometry) , space (punctuation) , simple (philosophy) , euclidean space , algorithm , mathematics , data mining , combinatorics , geometry , philosophy , linguistics , mathematical analysis , operations management , epistemology , economics , programming language , operating system
The success of cluster analysis for revealing natural grouping in a dataset depends heavily on the chosen dissimilarity measure. Recently, several attempts have been made to replace the popular Euclidean distance measure for dissimilarity with divergences that are known to disobey triangular inequality. In this Letter, a representative partitioning based superpixel algorithm called Simple Linear Iterative Clustering (SLIC) is experimented with a divergence measure. In particular, the Jeffery divergence is employed for dissimilarity computation between colour‐image plane space vectors while performing cluster assignment. Despite being a non‐metric, the Jeffery divergence based SLIC has shown better boundary adherence performance on BSDS500 dataset as compared to the conventional SLIC algorithm.