Abstract:
The proposed image segmentation algorithm identifies
information-rich versus low information regions based on
surface entropy. Thereafter on the information-rich regions, the
mean shift algorithm is applied to generate possible centroid
initialization points. This enables the Simple Non-Iterative Clustering
(SNIC) algorithm when initialized through the proposed
mechanism to provide more concentrated segmentation in those
information-rich regions and sparse segmentation in the low
information regions.
Citation:
J. Bandara Senanayaka, D. Thilanka Morawaliyadda, S. Tharuka Senarath, R. Indika Godaliyadda and M. Parakrama Ekanayake, "Adaptive Centroid Placement Based SNIC for Superpixel Segmentation," 2020 Moratuwa Engineering Research Conference (MERCon), 2020, pp. 242-247, doi: 10.1109/MERCon50084.2020.9185361.