Open AccessInteractive Natural Image Segmentation and Foreground Extraction
Author(s) -
Y. David Solomon Raju,
D Krishna Reddy
Publication year - 2018
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i3.27.17657
Subject(s) - artificial intelligence , computer science , segmentation , benchmark (surveying) , cluster analysis , image segmentation , segmentation based object categorization , pattern recognition (psychology) , scale space segmentation , computer vision , image (mathematics) , region growing , geography , cartography
Interactive image segmentation is very practical and important problem in computer vision. In this paper a regressive based Green’s function is employed to formulate the problem of segmentation. The method is incorporated with different clustering approaches intended to extract the foreground regions from the natural images. The method performance is improved with proper labeling of foreground and background regions, and with more number of cluster regions. The method is evaluated with two standard benchmark datasets and found that the experimental results were promising.