Tolerance near sets and image correspondence

The principal problem considered in this paper is how to solve the image correspondence problem using a bio-inspired approach. One solution to this problem is to consider tolerance near sets that model human perception in a physical continuum. Near sets are generalisations of rough sets introduced by Zdzislaw Pawlak during the early 1980s. Tolerance near sets have been inspired by C.E. Zeeman's work on visual perception and Henri Poincare's work on the contrast between mathematical continua and the physical continua in a pragmatic philosophy of science that laid the foundations for tolerance spaces. In this paper, the basics of perceptual systems and tolerance near sets are presented as bases for the solution of the image correspondence problem. The contribution of this paper is a humanistic perception-based approach to discovering similarities between images, classifying images and an approach to quantifying the nearness of images using the Henry-Peters nearness measure.