Texture analysis using graphs generated by deterministic partially self-avoiding walks

Texture is one of the most important visual attributes for image analysis. It has been widely used in image analysis and pattern recognition. A partially self-avoiding deterministic walk has recently been proposed as an approach for texture analysis with promising results. This approach uses walkers (called tourists) to exploit the gray scale image contexts in several levels. Here, we present an approach to generate graphs out of the trajectories produced by the tourist walks. The generated graphs embody important characteristics related to tourist transitivity in the image. Computed from these graphs, the statistical position (degree mean) and dispersion (entropy of two vertices with the same degree) measures are used as texture descriptors. A comparison with traditional texture analysis methods is performed to illustrate the high performance of this novel approach.

Figure optionsDownload high-quality image (127 K)Download as PowerPoint slideResearch highlights
► Create a graph containing only vertices and no edges.
► For each pixel of the image, perform the deterministic partially self-avoiding walk.
► For each transition of the walk, create an edge connecting their respective nodes in the graph.
► Texture classification is performed using graph properties.