Pattern based object segmentation using split and merge

Author

Karim, Z. ; Paiker, N.R. ; Ali, M.A. ; Sorwar, G. ; Islam, Md Minarul

Author_Institution

Dept. of Comput. Sci. & Eng., Mil. Inst. of Sci. & Technol., Dhaka, Bangladesh

fYear

2009

Firstpage

2166

Lastpage

2169

Abstract

Split and Merge (SM) algorithm is a well recognized algorithm for segmenting homogeneous regions in an image. Though SM algorithm is simple and easy, this algorithm is unable to segment all type objects in an image successfully due to huge variations among the objects in size, shape, color and intensity. Moreover, the SM algorithm is also highly dependent on threshold values used for split and merge stages. Addressing these issues, a new algorithm namely pattern based object segmentation using split and merge (PSM) considering the basic SM algorithm, the region stability, and the patterns for object extraction. The experimental results prove the superior segmentation performance of the PSM algorithm in comparison with the basic SM algorithm, suppressed fuzzy c-means (SFCM), and object based image segmentation using fuzzy clustering (FISG).

Keywords

feature extraction; image classification; image colour analysis; image matching; image segmentation; video coding; SM algorithm; bit rate video coding application; image color; image recognition algorithm; image segmentation algorithm; image threshold value; misclassification error; object extraction; pattern matching; pattern-based object segmentation; split-and-merge algorithm; suppressed fuzzy c-mean clustering; Clustering algorithms; Computer science; Image segmentation; Object segmentation; Pattern matching; Pixel; Samarium; Shape; Stability; Video coding; Image segmentation; micro-blocks; pattern matching; region stability; split-and-merge; video coding;

fLanguage

English

Publisher

ieee

Conference_Titel

Fuzzy Systems, 2009. FUZZ-IEEE 2009. IEEE International Conference on

Conference_Location

Jeju Island

ISSN

1098-7584

Print_ISBN

978-1-4244-3596-8

Type

conf

DOI

10.1109/FUZZY.2009.5277064

Filename

5277064