Partitioned Relief-F Method for Dimensionality Reduction of Hyperspectral Images

Abstract

The classification of hyperspectral remote sensing images is difficult due to the curse of dimensionality. Therefore, it is necessary to find an effective way to reduce the dimensions of such images. The Relief-F method has been introduced for supervising dimensionality reduction, but the band subset obtained by this method has a large number of continuous bands, resulting in a reduction in the classification accuracy. In this paper, an improved method—called Partitioned Relief-F—is presented to mitigate the influence of continuous bands on classification accuracy while retaining important information. Firstly, the importance scores of each band are obtained using the original Relief-F method. Secondly, the whole band interval is divided in an orderly manner, using a partitioning strategy according to the correlation between the bands. Finally, the band with the highest importance score is selected in each sub-interval. To verify the effectiveness of the proposed Partitioned Relief-F method, a classification experiment is performed on three publicly available data sets. The dimensionality reduction methods Principal Component Analysis (PCA) and original Relief-F are selected for comparison. Furthermore, K-Means and Balanced Iterative Reducing and Clustering Using Hierarchies (BIRCH) are selected for comparison in terms of partitioning strategy. This paper mainly measures the effectiveness of each method indirectly, using the overall accuracy of the final classification. The experimental results indicate that the addition of the proposed partitioning strategy increases the overall accuracy of the three data sets by 1.55%, 3.14%, and 0.83%, respectively. In general, the proposed Partitioned Relief-F method can achieve significantly superior dimensionality reduction effects.

Crop Type Classification by DESIS Hyperspectral Imagery and Machine Learning Algorithms

“…Here, 29 DESIS HBNs were finally selected out of 235 within the 500-100 nm range. The selected HBNs have already been used in many other agricultural studies [53], [54], [55], including the prediction of biophysical and biochemical parameters, such as leaf area index (LAI), nitrogen, crop growth stage classification, biomass, yield prediction, weed, disease detection, LULC classification, stress, pigment, etc. For instance, the bands at about 504, 522, and 540 nm are good for disease, LAI, and stress applications, while those at around 556 and 625 nm can be used to map the crop growth stages.…”

Spectroscopy Imaging Techniques as In Vivo Analytical Tools to Detect Plant Traits

“…Feature extraction utilizes the original data, while feature selection requires class marking to choose the representative wavelength. However, wavelength extraction can remove intrinsic features [70].…”

Quantifying physiological trait variation with automated hyperspectral imaging in rice

“…(2018) ; Yu et al. (2020) , while the RRefliefF algorithm is a supervised, ranking-based method that calculates an importance score of each wavelength by considering the similarity and dissimilarity between wavelengths Ren et al. (2020) .…”