English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

During the last decade, hyperspectral images have attracted increasinginterest from researchers worldwide. They provide more detailed informationabout an observed area and allow an accurate target detection and precisediscrimination of objects compared to classical RGB and multispectral images.Despite the great potentialities of hyperspectral technology, the analysis andexploitation of the large volume data remain a challenging task. The existenceof irrelevant redundant and noisy images decreases the classification accuracy.As a result, dimensionality reduction is a mandatory step in order to select aminimal and effective images subset. In this paper, a new filter approachnormalized mutual synergy (NMS) is proposed in order to detect relevant bandsthat are complementary in the class prediction better than the originalhyperspectral cube data. The algorithm consists of two steps: images selectionthrough normalized synergy information and pixel classification. The proposedapproach measures the discriminative power of the selected bands based on acombination of their maximal normalized synergic information, minimumredundancy and maximal mutual information with the ground truth. A comparativestudy using the support vector machine (SVM) and k-nearest neighbor (KNN)classifiers is conducted to evaluate the proposed approach compared to thestate of art band selection methods. Experimental results on three benchmarkhyperspectral images proposed by the NASA "Aviris Indiana Pine", "Salinas" and"Pavia University" demonstrated the robustness, effectiveness and thediscriminative power of the proposed approach over the literature approaches.  Keywords: Hyperspectral images; target detection; pixel classification;dimensionality reduction; band selection; information theory; mutualinformation; normalized synergy

A Novel Approach for Dimensionality Reduction and Classification of Hyperspectral Images based on Normalized Synergy