An Image Analysis Methodology Based on Deterministic Tourist Walks

Textures are important visual attribute used in image analysis. This paper presents a novel methodology, based on a deterministic walk, to texture analysis and texture characterization. Most of the methods adopted to classify textures deal with a defined scale of texture. The method proposed explores the set in all scales and is able to characterize efficiently different texture classes. The paper presents the deterministic walk technique and its results for two experiments using Brodatz images.

[1]  Bernard Derrida,et al.  From random walks to spin glasses , 1997 .

[2]  Stefan M. Rüger,et al.  Evaluation of Texture Features for Content-Based Image Retrieval , 2004, CIVR.

[3]  O. Kinouchi,et al.  Deterministic Walks in Random Networks: An Application to Thesaurus Graphs , 2001, cond-mat/0110217.

[4]  Stan Z. Li,et al.  On Discontinuity-Adaptive Smoothness Priors in Computer Vision , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  David Gale,et al.  Mathematical entertainments , 1995 .

[6]  Andrew R. Webb,et al.  Statistical Pattern Recognition , 1999 .

[7]  Joachim Schöll,et al.  Classification by restricted random walks , 2003, Pattern Recognit..

[8]  Denis Boyer,et al.  Looking for the right thing at the right place: Phase transition in an agent model with heterogeneous spatial resources , 2005, Complex..

[9]  D. Boyera,et al.  Modeling the searching behavior of social monkeys , 2004 .

[10]  Osame Kinouchi,et al.  Escaping from cycles through a glass transition. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[11]  David Gale,et al.  Further Travels with My Ant , 1998 .

[12]  Osame Kinouchi,et al.  Exploratory behavior, trap models, and glass transitions. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[13]  Alexandre Souto Martinez,et al.  Analytical results for the statistical distribution related to a memoryless deterministic walk: dimensionality effect and mean-field models. , 2005, Physical review. E, Statistical, nonlinear, and soft matter physics.

[14]  Leonid A. Bunimovich,et al.  Recurrence properties of Lorentz lattice gas cellular automata , 1992 .

[15]  Shigeo Abe DrEng Pattern Classification , 2001, Springer London.

[16]  Peter Grassberger,et al.  The red queen's walk , 1992 .

[17]  O Kinouchi,et al.  Deterministic walks in random media. , 2001, Physical review letters.

[18]  Osame Kinouchi,et al.  Deterministic walks as an algorithm of pattern recognition. , 2006, Physical review. E, Statistical, nonlinear, and soft matter physics.

[19]  Leonid A. Bunimovich,et al.  Deterministic walks in random environments , 2004 .

[20]  David G. Stork,et al.  Pattern Classification , 1973 .

[21]  Wei-Ying Ma,et al.  Image and Video Retrieval , 2003, Lecture Notes in Computer Science.

[22]  Anil K. Jain,et al.  Unsupervised texture segmentation using Gabor filters , 1990, 1990 IEEE International Conference on Systems, Man, and Cybernetics Conference Proceedings.

[23]  Sergey V. Buldyrev,et al.  Statistical physics: The salesman and the tourist , 2001, Nature.