Research and Application of Several Key Techniques in Hyperspectral Image Preprocessing

Abstract

This paper focuses on image segmentation, image correction and spatial-spectral dimensional denoising of images in hyperspectral image preprocessing to improve the classification accuracy of hyperspectral images. Firstly, the images were filtered and segmented by using spectral angle and principal component analysis, and the segmented results are intersected and then used to mask the hyperspectral images. Hyperspectral images with a excellent segmentation result was obtained. Secondly, the standard reflectance plates with reflectance of 2 and 98% were used as a priori spectral information for image correction of samples with known true spectral information. The mean square error between the corrected and calibrated spectra is less than 0.0001. Comparing with the black-and-white correction method, the classification model constructed based on this method has higher classification accuracy. Finally, the convolution kernel of the one-dimensional Savitzky-Golay (SG) filter was extended into a two-dimensional convolution kernel to perform joint spatial-spectral dimensional filtering (TSG) on the hyperspectral images. The SG filter (m = 7,n = 3) and TSG filter (m = 3,n = 4) were applied to the hyperspectral image of Pavia University and the quality of the hyperspectral image was evaluated. It was found that the TSG filter retained most of the original features while the noise information of the filtered hyperspectral image was less. The hyperspectral images of sample 1–1 and sample 1–2 were processed by the image segmentation and image correction methods proposed in this paper. Then the classification models based on SG filtering and TSG filtering hyperspectral images were constructed, respectively. The results showed that the TSG filter-based model had higher classification accuracy and the classification accuracy is more than 98%.

HSIS-Net: Hyperspectral Image Segmentation Using Multi-view Active Learning Based FCSN

“…This section performs the detailed survey on segmentation approaches. There are three different categories of segmentation approaches are used, pixel-level segmentation [15], object-level segmentation [16], and sub-pixel segmentation or unmixing [17]. The choice of approach depends mainly on the application requirement since they offer both advantages and limitations.…”

Identification of peanut storage period based on hyperspectral imaging technology

“…In the original data, there is a lot of signal noise and drift in the spectral signal. All three preprocessing methods can eliminate random noise in the spectral signal and improve the signal-to-noise ratio of the sample signal (Li et al, 2021).…”

On the Effect of Pre-Processing and Model Complexity for Plastic Analysis Using Short-Wave-Infrared Hyper-Spectral Imaging

“…The authors also observed that increasing the patch size, leads to improvements in performance, indicating the benefits of using the spatial information around pixels for deep learning based classifiers compared to linear models. In a recent work [15], the authors introduce HS image segmentation, correction and spectral-spatial denoising as HS image pre-processing to improve the HS image classification accuracy.…”