Open AccessA Novel Model of Image Segmentation Based on Watershed Algorithm
Author(s) -
Ali Abdullah Yahya,
Jieqing Tan,
Min Hu
Publication year - 2013
Publication title -
advances in multimedia
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.278
H-Index - 17
eISSN - 1687-5699
pISSN - 1687-5680
DOI - 10.1155/2013/120798
Subject(s) - watershed , maxima and minima , image segmentation , image (mathematics) , artificial intelligence , segmentation , transformation (genetics) , mathematical morphology , algorithm , computer science , morphological gradient , enhanced data rates for gsm evolution , pattern recognition (psychology) , thickening , region growing , function (biology) , computer vision , scale space segmentation , mathematics , image processing , engineering , mathematical analysis , biochemistry , chemistry , evolutionary biology , biology , gene , pulp and paper industry
A novel model of image segmentation based on watershed method is proposed in this paper. To prevent the oversegmentation of traditional watershed, our proposed algorithmhas five stages. Firstly, the morphological reconstruction is applied to smooth the flat areaand preserve the edge of the image. Secondly, multiscale morphological gradient isused to avoid the thickening and merging ofthe edges. Thirdly, for contrast enhancement,the top/bottom hat transformation is used. Fourthly, the morphological gradient of an image is modified by imposing regional minimaat the location of both the internal and the external markers. Finally, a weighted function isused to combine the top/bottom hat transformation algorithm and the markers algorithmto get the new algorithm. The experimental results show the superiority of the new algorithmin terms of suppression over-segmentation
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom