This paper presents a new similarity measure to be used for general tasks including supervised learning, which is represented by the K-nearest neighbor classifier (KNN). The proposed similarity measure is invariant to large differences in some dimensions in the feature space. The proposed metric is proved mathematically to be a metric. To test its viability for different applications, the KNN u...

In this paper a study of the influence of luminance L* at the CIE L* a* b* color space during color segmentation in highly saturated color images is presented. A comparative study is made between the behavior of segmentation in color images using (1) the Euclidean metric of the RGB channels (2) the Euclidean metric of a* and b* in CIE L*a*b* color space and (3) an adaptive color similarity func...

In this paper we de ne a metric on the collection of all translation invarinat spaces on a locally compact abelian group and we study some properties of the metric space.

Atsuji has internally characterized those metric spaces X for which each real-valued continuous function on X is uniformly continuous as follows: (1) the set X' of limit points of X is compact, and (2) for each £ > 0, the set of points in X whose distance from X' exceeds e is uniformly discrete. We obtain these new characterizations: (a) for each metric space V, the Hausdorff metric on C(X, Y),...

We define wt0-distance which is a special type of wt-distance and obtain some best proximity point theorems involving b-simulation functions. Our results are significant, since we replace simulation function with function, metric space b-metric space, w0-distance wt0-distance. also provide examples to support our results.