Open AccessUsing Mean-Shift to Improve Active Shape Model Search
Author(s) -
Wei Dai,
Shitong Wang
Publication year - 2011
Publication title -
journal of algorithms and computational technology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.234
H-Index - 13
eISSN - 1748-3026
pISSN - 1748-3018
DOI - 10.1260/1748-3018.5.1.71
Subject(s) - mean shift , active shape model , landmark , active contour model , computer science , artificial intelligence , active vision , shape change , computer vision , pattern recognition (psychology) , image (mathematics) , image segmentation , segmentation , evolutionary biology , biology
In this paper we introduce a new method for locating shapes. The method is based on active shape model, and combining with mean shift to improve local search in the region around each landmark. Bringing new local descriptor and search strategy to active shape model search, mean shift can improve active shape model in both precision and speed.