Linguistic description of relative positions in images

Abstract

Fuzzy set methods have been used to model and manage uncertainty in various aspects of image processing, pattern recognition, and computer vision. High-level computer vision applications hold a great potential for fuzzy set theory because of its links to natural language. Linguistic scene description, a language-based interpretation of regions and their relationships, is one such application that is starting to bear the fruits of fuzzy set theoretic involvement. In this paper, we are expanding on two earlier endeavors. We introduce new families of fuzzy directional relations that rely on the computation of histograms of forces. These families preserve important relative position properties. They provide inputs to a fuzzy rule base that produces logical linguistic descriptions along with assessments as to the validity of the descriptions. Each linguistic output uses hedges from a dictionary of about 30 adverbs and other terms that can be tailored to individual users. Excellent results from several synthetic and real image examples show the applicability of this approach.

Language Descriptions of Spatial Relation based on F-histogram

“…The past fifteen to twenty years have seen significant advancements in the development of mathematical and computational modeling of distance relation, directional relation, and topological relation between image objects [1][2][3][4][5]. Over the same period, several methods [6][7] have been proposed for generating automated linguistic descriptions of these relations.…”

Representing Topological Relationships between Complex Regions by F-Histograms

“…In (Matsakis et al 2001), we used force histograms to generate a linguistic description of the relative position between two objects in terms of the four primitive directional relationships ("to the right of," "above," "to the left of," "below"). In future work, we plan to generate a linguistic expression that describes the topological relationships between two objects in terms of the thirteen Allen relations.…”

“…Moreover, we have recently shown (Matsakis and Nikitenko, to appear) that the F-histogram constitutes a valuable tool for extracting topological relationship information from 2D concave objects. The present paper builds both on (Matsakis et al 2001) and (Matsakis and Nikitenko, to appear). It lays the foundation for generating a linguistic description that captures the essence of the topological relationships between two complex regions in terms of the thirteen Allen relations.…”

“…As demonstrated in (Matsakis 2002), these histograms can be of great use in understanding the spatial organization of regions in images. For instance, they can provide inputs to systems for linguistic scene description (Matsakis et al 2001). Moreover, we have recently shown (Matsakis and Nikitenko, to appear) that the F-histogram constitutes a valuable tool for extracting topological relationship information from 2D concave objects.…”

An inexact inferencing strategy for spatial objects with determined and indeterminate boundaries

“…Many contributions have been made. The authors in [9] define new families of fuzzy directional relations in terms of the computation of force histograms, which is based on .the raster data. In'this paper, we will take into account these two major spatial relations based on the vector data.…”