Digital images are generally created as discrete measurements of light, as performed by dedicated sensors. Consequently, each pixel contains a discrete approximation of the light inciding in a sensor element. The nature of this measurement implies certain uncertainty due to discretization matters. In this work we propose to model such uncertainty using intervals, further leading to the generation of so-called interval-valued images. Then, we study the partial differentiation of such images, putting a spotlight on antisymmetric convolution operators for such task. Finally, we illustrate the utility of the interval-valued images by studying the behaviour of an extended version of the well-known Canny edges detection method.
There exists a large number of techniques for content-aware smoothing. Despite its simplicity, the PeronaMalik Anisotropic Diffusion method is among the most employed ones. In this work we study this method in detail and propose a generalization of its diffusion scheme using restricted dissimilarity functions to measure the intensity differences between neighbouring pixels. This generalization permits a better adaptation of the diffusion process to the characteristics of the images.
This work tackles the comparison of radial data, and proposes comparison measures that are further applied to fingerprint analysis. First, we study the similarity of scalar and non-scalar radial data, elaborated on previous works in fuzzy set theory. This study leads to the concepts of Restricted Radial Equivalence Function and Radial Similarity Measure, which model the perceived similarity between scalar and vectorial pieces of radial data, respectively. Second, the utility of these functions is tested in the context of fingerprint analysis, and more specifically, in the singular point detection. With this aim, a novel template-based singular point detection method is proposed, which takes advantage of these functions. Finally, their suitability is tested in different fingerprint databases. Different similarity measures are considered to show the flexibility offered by these measures and the behavior of the new method is compared with well-known singular point detection methods.
In this work we use the Choquet integral as an aggregation function and we apply it in the fuzzy reasoning method of fuzzy rule-based classification systems. We study the behaviour of several fuzzy measures and we propose a genetic learning method of an appropriate fuzzy measure to model the interaction among the set of rules of each class. In the experimental study we show that the new proposal allows the performance of the fuzzy reasoning method of the winning rule to be outperformed when dealing with classification problems in which several fuzzy rules are fired to classify each example.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.