Shape description by image foresting transform

R.S. Torres1, A.X. Falcao1, L.F. Costa2
1Institute of Computing, State University of Campinas-UNICAMP, Sao Paulo, Brazil
2Institute of Physics, University of Sao Paulo, Sao Paulo, Brazil

Tóm tắt

The image foresting transform (IFT) is a unified and effective graph-based approach to the design of image-processing operations, often with considerable efficiency gains over published algorithms. This paper extends the applications of the Euclidean IFT to two recently proposed shape descriptors: saliences and multiscale fractal dimension. It explains how to obtain the salience information and the multiscale fractal dimension of contours and skeletons and presents their comparison in terms of robustness and separability.

Từ khóa

#Shape #Fractals #Pixel #Skeleton #Robustness #Cost function #Physics computing #Process design #Algorithm design and analysis #Filtering

Tài liệu tham khảo

costa, 2001, An integrated approach to shape analysis: Results and perspectives, International Conference on Quality Control by Artificial Vision, 23 10.1016/S0031-3203(01)00148-0 peitgen, 1992, Fractals for the Classroom Part 1 Introduction to Fractals and Chaos costa, 2001, Shape Analysis and Classification Theory and Practice 10.1037/h0054663 monlague, 1991, Morphogenesis and territorial coverage by isolated mammalian retinal ganglion cells, Journal of Neuroscience, 11, 1440, 10.1523/JNEUROSCI.11-05-01440.1991 falcão, 2001, Design of connected operators using the image foresting transform, Proceedings of SPIE on Medical lmaging, 4322, 468, 10.1117/12.431120 10.1007/0-306-47025-X_37