Object recognition by spectral feature derived from canonical shape representation
Document Type
Article
Publication Date
5-1-2013
Abstract
In this paper, we introduce a new spectral shape feature that can be used in content-based object recognition. We explain a new canonical string representation for a polygonal shape approximation from which the proposed spectral feature is derived. This spectral feature is a composition of Fourier coefficients of the shape function that is derived from the canonical representation. We applied the proposed feature in classification of lung nodules by means of our hierarchical learning scheme proposed in another study. The results show that the spectral feature is promising for lung nodule recognition. © 2012 Springer-Verlag Berlin Heidelberg.
Publication Source (Journal or Book title)
Machine Vision and Applications
First Page
855
Last Page
868
Recommended Citation
Soysal, Ö., & Chen, J. (2013). Object recognition by spectral feature derived from canonical shape representation. Machine Vision and Applications, 24 (4), 855-868. https://doi.org/10.1007/s00138-012-0468-7