## Texture Segmentation by Minimizing Vector-Valued Energy Functionals: The Coupled-Membrane Model (1992)

Venue: | in Proceedings of the Second European Conference on Computer Vision |

Citations: | 33 - 4 self |

### BibTeX

@INPROCEEDINGS{Lee92texturesegmentation,

author = {Tai Sing Lee and David Mumford and Alan Yuille},

title = {Texture Segmentation by Minimizing Vector-Valued Energy Functionals: The Coupled-Membrane Model},

booktitle = {in Proceedings of the Second European Conference on Computer Vision},

year = {1992},

pages = {165--173},

publisher = {Springer-Verlag}

}

### Years of Citing Articles

### OpenURL

### Abstract

Abstract. This paper presents a computational model that segments images based on the textural properties of object surfaces. The proposed Coupled-Membrane model applies the weak membrane approach to an image Wl(O ' derived from the power responses of a family of selfsimilar quadrature Gabor wavelets. While segmentation breaks are allowed in x and y only, coupling is introduced to in all 4 dimensions. The resulting spatial and spectral diffusion prevents minor variations in local textures from producing segmentation boundaries. Experiments showed that the model is adequate in segmenting a class of synthetic and natural texture images. 1

### Citations

3884 | Optimization by simulated annealing - Kirkpatrick, Gelatt, et al. - 1983 |

758 | Visual Reconstruction
- BLAKE, ZISSERMAN
- 1987
(Show Context)
Citation Context ...um analysis and feature detection. The convolution of this family of filters with the image produces a single image WI(u, 0 , x which is the normalized power modulus of the filter ensemble as follows =-=(1)-=-s167 Fig. 1. Rotated and Dilated quadrature Gabor filters where and WI(u (0" I)(xo, Yo 11 y) J J 1(0" ~1(0" 0 *I)(x y)12 (3) o(x Xo, Y )I(x , y)dxdy (4) I)(x , y)12dud6 (5) Since each Gabor filter has... |

670 |
Textures: A Photographic Album for Artists and Designers
- Brodatz
- 1966
(Show Context)
Citation Context ..., x which is the normalized power modulus of the filter ensemble as follows (1)s167 Fig. 1. Rotated and Dilated quadrature Gabor filters where and WI(u (0" I)(xo, Yo 11 y) J J 1(0" ~1(0" 0 *I)(x y)12 =-=(3)-=- o(x Xo, Y )I(x , y)dxdy (4) I)(x , y)12dud6 (5) Since each Gabor filter has a Gaussian spread in its frequency plane, local power spectrum of an image can be sampled in a parsimonious and discrete ma... |

592 |
Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters
- DAUGMAN
- 1975
(Show Context)
Citation Context ...power modulus of the filter ensemble as follows (1)s167 Fig. 1. Rotated and Dilated quadrature Gabor filters where and WI(u (0" I)(xo, Yo 11 y) J J 1(0" ~1(0" 0 *I)(x y)12 (3) o(x Xo, Y )I(x , y)dxdy =-=(4)-=- I)(x , y)12dud6 (5) Since each Gabor filter has a Gaussian spread in its frequency plane, local power spectrum of an image can be sampled in a parsimonious and discrete manner. In our implementation,... |

422 |
Multichannel texture analysis using localized spatial filters
- Bovik, Clark, et al.
- 1990
(Show Context)
Citation Context ...from a single basic wavelet, this whole family of Gabor filters c.an be generated by rotation and dilation from the following single Gabor filter (as shown in figure 1): ifJ(x 5011" ...L(4 ' 100 '" Y =-=(2)-=- Self-similar Gabor filters from this family serve both as band-pass filters and multiscale matched filters, producing a representational scheme that unifies power-spectrum analysis and feature detect... |

247 | Boundary detection by minimizing functionals - Mumford, Shah - 1985 |

207 | Functional architecture of macaque monkey visual cortex - Hubel, Wiesel - 1977 |

133 | Boundary detection by constrained optimization - Geman, Geman, et al. - 1990 |

117 |
Gabor filters as texture discriminator
- Fogel, Sagi
- 1989
(Show Context)
Citation Context ...ed and Dilated quadrature Gabor filters where 1 WI(o, 9, x, y) = —z l(Gcr,8 * I)(x, WI' (3) (Gc,e * I)(x 0 , yo) = i I Ger,e(x — x o, y — yo )/(x, y)dxdy x y (4) and Z = i I l(G cy9 * I)(x, y)12 dadO =-=(5)-=- Since each Gabor filter has a Gaussian spread in its frequency plane, local power spectrum of an image can be sampled in a parsimonious and discrete manner. In our implementation, we use Gabor wavele... |

81 | A common framework for image segmentation - Geiger, AL - 1991 |

50 | Segmentation of textured images and Gestalt organization using spatial/spatial-frequency representations - Reed, Wechsler - 1990 |

31 | Relationship between spatial frequencies and orientation tuning of striate-cortex cells - Webster, Valois - 1985 |

20 | The ecological approach to visual perception. Houghton Miff lin - Gibson - 1979 |

17 | Surface reconstruction preserving disconti- nuities - Marroquin - 1984 |

15 | A computational model of texture segmentation - Malik, Perona - 1989 |

11 | Physiological constraints on models of visual cortical function. In: Models of Brain Function, edited by R.M.J. Cotterill - POLLEN, GASKA, et al. - 1989 |

11 | Spatial-frequency organization i primate striate cortex - Silverman, Grosof, et al. - 1989 |

8 | Computational Model of Cat Striate Physiology - Heeger - 1989 |

2 | Boundary Detection by Constrained Optimization - Graffigne - 1990 |

1 | Computing texture boundaries in images. Nature 333:364c367. A detailed version exists as Voorhees - Voorhees, Poggio - 1988 |