Hyperspectral Feature Selection Ensemble for Plant Classification

Ali AlSuwaidi, Charles Veys, Martyn Hussey, Bruce Grieve, Hujun Yin

    Research output: Contribution to conferencePaperpeer-review


    Interest in hyperspectral imaging systems has increased recently substantially for studying and monitoring plant properties and conditions. The numerous financial (i.e. improve breeding process) and environmental (i.e. reduce usage of herbicide) advantages of such systems have been a driving force behind the latest surge. This paper aim to differentiate different plant species using hyperspectral image analysis. Main contribution of the work lies in the use of combined output of multiple feature selection algorithms, as compared to the use of single feature selection algorithm. Two independent hyperspectral datasets, captured by different instrumentations, were used in the evaluation. In total, six different feature selection algorithms (relief-f, chi-square, gini index, information gain, FCBF, and CFS) were used in the experiment. Experimental results show significant improvements in classification accuracy with the ensemble version of multiple feature selection algorithms compared to with the individual feature selection algorithms.
    Original languageEnglish
    Number of pages4
    Publication statusPublished - 2016
    EventHyperspectral Imaging and Applications Conference: SENSORS & SYSTEMS - Ricoh Arena, Coventry, United Kingdom
    Duration: 12 Oct 201613 Oct 2016


    ConferenceHyperspectral Imaging and Applications Conference
    Abbreviated titleHSI2016
    Country/TerritoryUnited Kingdom
    Internet address


    Dive into the research topics of 'Hyperspectral Feature Selection Ensemble for Plant Classification'. Together they form a unique fingerprint.

    Cite this