LI Hui-fang, YU Bian-zhang. Image segmentation approach based on new multifractal feature vectors[J]. Editorial Office of Optics and Precision Engineering, 2003,(6): 627-631
LI Hui-fang, YU Bian-zhang. Image segmentation approach based on new multifractal feature vectors[J]. Editorial Office of Optics and Precision Engineering, 2003,(6): 627-631DOI:
By computing the spectra associated with different kinds of capacities defined from the grey levels
a new feature vector composed of different kinds of multifractal spectrum of Choquet capacities is proposed
the adaptive FKCN model presented in this paper overcomes the shortcomings of classical algorithms and determines the network structure automatically according to the singularity exponents and spectrum for sum
max
min
iso and capacities of the image. The approach proposed can fully extract the texture information and provide accurate classification results for different textures. Experimental results indicate that
in comparison with the Jacques LEVY
the algorithm proposed has better segmentation quality
improves convergence
and reduces clustering errors as well.
关键词
Keywords
references
JACQUES Lévy Véhel, PASCAL Mignot. Multifractal segmentation of images[J]. In Fractals, 1997,2( 3):371-378.
赵巨波,孙华燕,杜巍. 一种图像边缘特征提取算法[J].光学精密工程, 2000,8(4):325-327.ZHAO J B, SUN H Y, DU W.Edge feature extraction method for image[J].Optics and Precision Engineering,2000,8(4):325-327.(in Chinese)
杨词银,尚海波,贾晨光,等.基于区域分割的自适应反锐化掩模算法[J].光学精密工程,2003,11(2):188-192.YANG C Y, SHANG H B, JIA CH G,et al.Adaptive unsharp masking method based on region segmentation[J].Optics and Precision Engineering,2003,11(2):188-192.(in Chinese)
张明慧,徐卫,张尧禹,等.航空照片的图像增强研究[J]. 光学精密工程2002,10(2):194-200.ZHANG M H, XU W, ZHANG Y Y,et al. Research on image enhancing for aerial photographs[J].Optics and Precision Engineering,2002,10(2):194-200.(in Chinese)
VOJAK R. Multifractal analysis of Choquet capacities: preliminary results[J]. In Advances in Applied Mathematics, 1998,20(1): 1-43.
WANG Y,ZHU Y SH. A short-time multifractal approach for arrhythmia detection based on fuzzy neural network[J]. IEEE Transactions on Biomedical Engineering. 2001, 8(9):989-995.