Performance Analysis of Discrete Wavelets in Hyper Spectral Image Classification: A Deep Learning Approach

Abstract

The use of convolutional neural networks (CNNs) to classify hyperspectral images (HSIs) is being done in contemporary research works. HSI data poses a challenge to the current technique for data analysis because of its extensive spectrum information. It has been noted that conventional CNN primarily grabs the spatial characteristics of HSI while ignoring the spectral data. In that way, it exhibits poor performance. As a result, spectral feature extraction now plays a big role in HSI data processing. Out of the several existing strategies for HSI spectral feature extraction, the discrete wavelet transform (DWT) approach is selected for analysis as a solution to the issue. Because it preserves the contrast between spectral signatures, spectral feature extraction using Wavelet Decomposition might be helpful. This work analyses two basic DWTs, namely Haar and Daubechies wavelets for this topic and gives a thorough examination of deep learning-based HSI categorization. In this regard, this paper examines the concept of wavelet CNN which highlights spectral characteristics by layering DWTs. The 2D CNN is next connected to the retrieved spectral features. It highlights spatial characteristics and generates a spatial spectral feature vector for classification. In particular, factor analysis is utilised to minimise the HSI dimension first. The discrete wavelet decomposition algorithm is then used to get four-level decomposition features. They are concatenated with 4-layer convolution features for merging spatial and spectral information, respectively. The entire approach aims to improve the final performance of the HSI classification with appropriate choice of mother wavelet. Experiments with wavelet feature fusion CNN on benchmark data sets like Indian Pines were conducted to assess the performance. To determine the overall classification accuracy, the classification results were analysed. In the context of extracting spectral features, it is discovered that Daubechies wavelets perform better in terms of classification than Haar wavelets.