Spatial‐spectral analysis method using texture features combined with PCA for information extraction in hyperspectral images

Abstract

This work proposes a new method to treat spatial and spectral information interactively. The method extracts spatial features, ie, variogram, gray-level co-occurrence matrix (GLCM), histograms of oriented gradients (HOG), and local binary pattern (LBP) features, from each wavelength image of hypercube and principal component analysis (PCA) is applied on this spatial feature matrix to identify wavelength-dependent variation in spatial patterns. Resultant image is obtained by projecting the score values to the original data. Three datasets, including a synthetic hyperspectral image (Dataset 1), a set of real hyperspectral images of salmon fillets (Dataset 2), and remote-sensing images (Dataset 3), were utilized to evaluate the performance of the proposed method.Results from Dataset 1 showed that the spatial-spectral methods had the potential of reducing baseline offset noise. Dataset 2 revealed that spatial-spectral methods can alleviate noisy pixels with strong signal and reduce shadow effects. In addition, substantial improvements were obtained in case of classification between white stripe and red muscle pixels by using the HOG-based approach with correct classification rate (CCR) of 0.97 compared with the models directly built from raw and standard normal variate (SNV) preprocessed spectra (CCR = 0.94). Samson image of Dataset 3 suggested the flexibility and effectiveness of the proposed method by improving CCR of 0.96 using conventional PCA on SNV pretreated spectra to 0.98 using GLCMbased approach on SNV preprocessed spectra. Overall, experimental results demonstrated that the spatial-spectral methods can improve the results found by using the spectral information alone because of the spatial information provided.

Deep Spectral-Spatial Features of Near Infrared Hyperspectral Images for Pixel-Wise Classification of Food Products

“…PLSDA and SVM focus exclusively on the spectral domain despite the inherent spatial-spectral duality of the hyperspectral dataset. In other words, the hyperspectral data are considered not as an image but as an unordered listing of spectral vectors where the spatial coordinates can be shuffled arbitrarily without affecting classification modeling results [ 37 ]. As we can observe from classification and misclassification maps of sweet samples, PLSDA and SVM classifiers exhibit random noise in pixel-based classification (significantly less in the CNN-based methods), because they ignore spatial-contextual information when providing a pixel prediction.…”

A Review of Sorting and Separating Technologies Suitable for Compostable and Biodegradable Plastic Packaging

“…PCA decomposes spectral data into several principal components (PCs), linear combinations of the original data, embedding the spectral variations of each collected spectral data set (Wold et al, 1987). The first few PCs, resulting from PCA, are used to analyse the common features among samples: samples characterized by similar spectral signatures tend to aggregate in the score plot as a cluster (Xu and Gowen, 2020). Finally, the recognition of different products and/or materials is obtained utilizing classification methods, such as Partial Least-Squares Discriminant Analysis (PLS-DA).…”

Exploring local spatial features in hyperspectral images

“…MIA has also been coupled to wavelet transform (WT) multiresolution analysis, 10 and this combination has been proven effective in resolving spatial features in multispectral 11 and Raman hyperspectral images 12 . In addition, other strategies, like coclustering 13 and gray‐level co‐occurrence matrices (GLCMs), 14 have recently been applied to examine texture in HSI datasets. Textural features in HSI have also been explored by using three‐dimensional discrete WT (DWT) 15 or by fusion of the two‐dimensional DWT decomposition images obtained from each spectral channel 16 .…”