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

By combining the similarity-weighted joint collaborative representation (SJCR) and extreme learning machine based on mid-level features (MFELM), a decision fusion framework is constructed to classify hyperspectral images with limited training samples. First, the similarity-weighted matrix is obtained by calculating the Gaussian process-based distance between each testing sample and its surroundings, which can expose the spatial unequal contributions between samples. Based on this, the samples with the higher similarities are selected to construct the joint samples. Then, SJCR is exploited to classify the joint samples and calculate the related SJCR coefficients. Secondly, mid-level features with the rich spatial characteristics are formed by utilizing SJCR coefficients, which are introduced to conduct extreme learning machine for classification. Finally, the classification probabilities of SJCR and MFELM are combined in a multiplicative fusion manner to achieve the final classification results. Using different and limited amount of training samples, the proposed method is evaluated by comparing with the popular classifiers. The visual and numerical results indicate the effectiveness of the proposed method for classifying hyperspectral images with the limited training samples.

Decision Fusion Using Similarity-weighted JCR and Mid-level Features based ELM for Hyperspectral Image Classification with Limited Training Samples