An Architecture for Texture Segmentation: from Energy Features to Region Detection

This paper presents a texture segmentation model realised with image treatment processing and artificial neural network techniques. Gabor oriented filters are used to extract texture features and Self-Organising Feature Maps to group these features. In order to decrease the number of filters needed to better extract features, we use a multiresolution procedure and a learning rule property to features interpolation. Two main axes of texture recognition are exploited with this model; one by the interpolating capabilities of the feature space, leading to a segmentation based on the number of chosen filters; and the other by the unsupervised segmentation of textured regions, leading to the number of textured objects on the image. Also presented, is a proposition to improve the model by an active learning for features fusion, and where the detection of contours in low resolution levels are used to control the focus on the textured regions of the immediately posterior resolution level.

[1]  William R. Uttal,et al.  A model of visual texture discrimination using multiple weak operators and spatial averaging , 1992, Pattern Recognit..

[2]  Phil Brodatz,et al.  Textures: A Photographic Album for Artists and Designers , 1966 .

[3]  T. Wiesel,et al.  Functional architecture of macaque monkey visual cortex , 1977 .

[4]  Pierre Demartines.  Analyse de donnees par reseaux de neurones auto-organises , 1994 .

[5]  Rafael Fonolla Navarro,et al.  Gaussian wavelet transform: Two alternative fast implementations for images , 1991, Multidimens. Syst. Signal Process..

[6]  D. Pollen,et al.  Phase relationships between adjacent simple cells in the visual cortex. , 1981, Science.

[7]  Olaf Kübler,et al.  Simulation of neural contour mechanisms: from simple to end-stopped cells , 1992, Vision Research.

[8]  Stephen Grossberg,et al.  Competitive Learning: From Interactive Activation to Adaptive Resonance , 1987, Cogn. Sci..

[9]  Stanley C. Ahalt,et al.  Competitive learning algorithms for vector quantization , 1990, Neural Networks.

[10]  Joydeep Ghosh,et al.  Neural Networks for Textured Image Processing , 1991 .

[11]  Jake K. Aggarwal,et al.  Image Interpretation Using Multiple Sensing Modalities , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  A. Chehikian.  1 - Algorithmes optimaux pour la génération de pyramides d'images passe-bas et laplaciennes , 1992 .

[13]  D. Hubel,et al.  Ferrier lecture - Functional architecture of macaque monkey visual cortex , 1977, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[14]  J. Daugman.  Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[15]  S Marcelja,et al.  Mathematical description of the responses of simple cortical cells. , 1980, Journal of the Optical Society of America.

[16]  P Perona,et al.  Preattentive texture discrimination with early vision mechanisms. , 1990, Journal of the Optical Society of America. A, Optics and image science.

[17]  S. Lu,et al.  Texture segmentation by clustering of Gabor feature vectors , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[18]  Linda Tomasini.  Apprentissage d'une représentation statistique et topologique d'un environnement , 1993 .

[19]  A. Oliva,et al.  From Blobs to Boundary Edges: Evidence for Time- and Spatial-Scale-Dependent Scene Recognition , 1994 .

[20]  M. R. Turner,et al.  Texture discrimination by Gabor functions , 1986, Biological Cybernetics.

[21]  R. Young.  GAUSSIAN DERIVATIVE THEORY OF SPATIAL VISION: ANALYSIS OF CORTICAL CELL RECEPTIVE FIELD LINE-WEIGHTING PROFILES. , 1985 .

[22]  Guerin-Dugue,et al.  1 - Implantation de filtres de Gabor par pyramide d'images passe-bas , 1996 .