Developed global biotic cross pollination algorithm for CIS
K. Sasi Kala Rani, D. Rasi, Subramaniam Nachimuthu Deepa · International Journal of Business Intelligence and Data Mining · 2017
This paper focuses on the visual-based colour image segmentation with a global biotic cross pollination algorithm (GBCPA). The global biotic cross pollination algorithm segments the structurally challenging objects based on the colour, edge, entropy and edge information in the CIE L*a*b* colour space. The L*a*b* colour space is a colour-opponent space considered to approximate human vision. L* denotes the luminosity or brightness layer, chromaticity layer a* indicates colour falls along red-green axis and chromaticity layer b* indicates the blue-yellow axis. The FPO algorithm considering the global biotic cross pollination is proposed to improve the quality of the solution and computational speed. GBCPA is first introduced to find the locality of the solution. The performance of GBCPA is tested on a standard Berkeley segmentation dataset with 300 images. The dataset is illustrated under different evaluating strategies.