Top Highlights

• he main contribution of the jSLIC is a significant speed-up of the original clustering method, transforming the compact- ness parameter such that the value is image independent, and a new post-processing step (after clustering) which now gives more reliable superpixels - the newly established seg- ments are more homogeneous
• In the past, several superpixel algorithms were introduced which were based on, for example the watershed approach, level-set based geometric flow, mode-seeking segmentation scheme or graph-based (a comparison is presented in [2, 9])
• SLIC has a high rate in bound- ary recall and a low rate of under-segmentation error [2].
• Another benefit is the low number of parameters to be set and an opportunity to influence the size and compactness of the resulting superpixels.
• dc (using the CIELAB colour space, which is widely considered as perceptually uniform for small col- our distances) and spatial proximity ds and (b) the search space is reduced by limiting to a region 2S × 2S, propor- tional to the superpixel size S. The search space reduction has a great impact on the speed of whole algorithm, res- ulting on a com...

Domain