Gabor function-based medical image compression

Andersen, Murray N.; Loew, M.; Brown, D. W.

doi:10.1016/0262-8856(95)91144-3

Cited by 1 publication

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The mirror image of filters reflected across the u and v frequency axes are also disqualified, since these filters have identical responses for real-valued I(x, y). In the following section, the diagonal form for C i also simplifies the calculation of the determinant and inverse as later needed in (25). Finally, our experimental results support the use of the diagonal form in (24), since both the design of the filters in the system and the design of the classifier are based on (24).…”

Section: Statistical Modelsupporting

confidence: 62%

“…We indicate the error's dependence on the filter parameters by including the argument Θ k in (26). Equations (25) and (26) provide the relationship between the image-segmentation error and the multivariate Gaussian statistics of the vector output of the k channels. The predicted error is taken to be the bound given in (26).…”

Section: Segmentation Error Measurementioning

confidence: 99%

“…Gabor filters have been employed in such diverse applications as texture segmentation, [1][2][3][4][5][6][7][8][9][10][11][12] image retrieval, 13 document analysis, 14,15 image coding, 16,17 retina identification, 18 character recognition, 19 target detection, 20,21 fractal dimension measurement, 22 edge detection, 23 line characterization, 24 medical image compression, 25 and image representation. 26 Despite such wide ranging applications, a variety of issues still remain when considering the problem of designing multiple Gabor filters for segmenting multi-textured images.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Designing multiple Gabor filters for multitexture image segmentation

Higgins

1999

Opt. Eng

View full text Add to dashboard Cite

We consider the problem of segmenting multitextured images using multiple Gabor filters. In particular, we present a mathematical framework for a multichannel texture-segmentation system consisting of a parallel bank of filter channels, a vector classifier stage, and a postprocessing stage. The framework establishes mathematical relationships between the predicted texture-segmentation error, the frequency spectra of constituent textures, and the parameters of the filter channels. The framework also permits the systematic formulation of filter-design procedures and provides predicted vector output statistics that are useful for classifier design. This paper focuses on the mathematical framework and provides experimental results that confirm the utility of the framework in the design of a complete image-segmentation system. The results demonstrate effective segmentation using a straightforward classifier and fewer than half the number of filters needed in previously proposed approaches.

show abstract

Section: Statistical Modelsupporting

confidence: 62%