On Spectral-Spatial Classification of Hyperspectral Images Using Image Denoising and Enhancement Techniques, Wavelet Transforms and Controlled Data Set Partitioning

Obtaining relevant classification results for hyperspectral images depends on the quality of the data and the proposed selection of the samples and descriptors for the training and testing phases. We propose a hyperspectral image classification machine learning framework based on image processing techniques for denoising and enhancement and a parallel approach for the feature extraction step. This parallel approach is designed to extract the features by employing the wavelet transform in the spectral domain, and by using Local Binary Patterns to capture the texture-like information linked to the geometry of the scene in the spatial domain. The spectral and spatial features are concatenated for a Support Vector Machine-based supervised classifier. For the experimental validation, we propose a controlled sampling approach that ensures the independence of the selected samples for the training data set, respectively the testing data set, offering unbiased performance results. We argue that a random selection applied on the hyperspectral dataset to separate the samples for the learning and testing phases can cause overlapping between the two datasets, leading to biased classification results. The proposed approach, with the controlled sampling strategy, tested on three public datasets, Indian Pines, Salinas and Pavia University, provides good performance results.

Automated summary

Obtaining accurate classification results for hyperspectral images requires high-quality data and carefully selected samples and descriptors for training and testing. This study proposes a machine learning framework for hyperspectral image classification, which includes denoising and enhancement techniques, as well as a parallel approach for feature extraction. The proposed approach combines spectral and spatial features using a Support Vector Machine classifier. Experimental results on three public datasets demonstrate the effectiveness of the proposed approach, especially in terms of avoiding biased classification results caused by overlapping between training and testing datasets.