Title :
Wavelet maxima based lacunarity texture analysis
Author :
Bogdan, Alexandru
Author_Institution :
Electro Opt. Sci. Inc., Irvington, NJ, USA
Abstract :
We present a new method that extracts lacunarity descriptors from textured regions using wavelet maxima. The distributions of the local wavelet maxima density in a sliding window over the region of interest are compared using different method in order to generate lacunarity parameters. The algorithms have been tested on data from the MelaFind skin cancer diagnostic image database.
Keywords :
cancer; image texture; medical image processing; skin; wavelet transforms; lacunarity descriptors; lacunarity texture analysis; local wavelet maxima density distribution; skin cancer; textured regions; wavelet transform; Continuous wavelet transforms; Data mining; Fractals; Lesions; Malignant tumors; Parameter estimation; Signal analysis; Skin cancer; Wavelet analysis; Wavelet transforms; fractal lacunarity; texture analysis; wavelet maxima;
Conference_Titel :
Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on
Conference_Location :
Dallas, TX
Print_ISBN :
978-1-4244-4295-9
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2010.5495349
