Conjuntos Difusos em Processamento Digital de Imagens
Article Sidebar
Main Article Content
Abstract
The utilization of the remote sensing technique for classifying images is one of the most used for the building of land use / coverage maps. These maps represent geographic data and each area is related to an established land use / coverage category (uncovered soil, vegetation, etc.). Therefore, most of classifiers aim at relating a pixel to a single class. However, the data are not accurate. Commonly, more than a class are present at a given piece of land. The relation of a pixel to a single class can result in loss of part of the available data.
This paper approaches the theory of fuzzy sets as a way of processing digital images.
Traditional methods of image classification have often shown to be troublesome, especially with respect to the class limits and spectral responses inside a class. Such methods related each pixel to a single class, i.e., to a land coverage class. While there are no difficulties with pixels which represent a single class, pixels which present more than a spectral class may show distortions, either on the measurements of class characteristic parameters or on the classification process itself.
The introduction of fuzzy data allows to identify pure characteristic pixels as well as those which represent more than a single class.
Downloads
Article Details
Issue
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish in this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors can enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) before and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (see "The Effect of Open Access").
How to Cite
