Third International conference on advances in communication, network and computing

Research Article

Block Based Image Segmentation

Download
271 downloads
  • @INPROCEEDINGS{10.1007/978-3-642-35615-5_3,
        author={Md. Hasan and Shaila Sharmeen and Md. Rahman and M. Ali and Md. Kabir},
        title={Block Based Image Segmentation},
        proceedings={Third International conference on advances in communication, network and computing},
        proceedings_a={CNC},
        year={2012},
        month={12},
        keywords={Image segmentation pattern based image segmentation fuzzy clustering},
        doi={10.1007/978-3-642-35615-5_3}
    }
    
  • Md. Hasan
    Shaila Sharmeen
    Md. Rahman
    M. Ali
    Md. Kabir
    Year: 2012
    Block Based Image Segmentation
    CNC
    Springer
    DOI: 10.1007/978-3-642-35615-5_3
Md. Hasan1, Shaila Sharmeen1,*, Md. Rahman1, M. Ali1,*, Md. Kabir2,*
  • 1: East West University
  • 2: Bangladesh University of Engineering and Technology
*Contact email: shailacse2k@gmail.com, ameer7302002@yahoo.com, mhkabir@gmail.com

Abstract

Image segmentation is an important research field due increasing Internet and computer based applications and also for video coding but it is very challenging. There exist a huge number of algorithms for image segmentation using split and merge having some limitations for which pattern based object segmentation using split and merge (PSM) was proposed to overcome the problems of basic split and merge (SM) algorithm being unable to segment properly all types of objects in an image due to huge variations among the objects. Addressing this issue, a new algorithm namely block based image segmentation (BIS) algorithm has been presented in this paper considering multi stage merging technique. The experimental analysis proves the superior performance over the existing algorithm.