Spectral-spatial classification of hyperspectral images based on multifractal features

Uchaev, Dmitry V.; Uchaev, Denis V.; Malinnikov, V. A.

doi:10.1117/12.2573715

Cited by 2 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The key steps of HSI classification are feature extraction and representation [7,8]. Before the widespread application of deep learning methods, HSI classification is based on the use of hand-crafted (shallow) features, such as local binary patterns [9,10], morphological features [11,12], fractal-based features [13,14]. However, shallow feature extraction techniques often require careful engineering and domain knowledge of experts, which limits their applications.…”

Section: Introductionmentioning

confidence: 99%

Small Sample Hyperspectral Image Classiﬁcation Based on the Random Patches Network and Recursive Filtering

Uchaev¹,

Uchaev²

2022

Preprint

View full text Add to dashboard Cite

In recent years, different deep learning frameworks were introduced for hyperspectral image (HSI) classification. However, the proposed network models have a higher model complexity and do not provide high classification accuracy if few-shot learning is used. This paper pre-sents an HSI classification method that combines random patches network (RPNet) and re-cursive filtering (RF) to obtain informative deep features. The proposed method first convolves image bands with random patches to extract multi-level deep RPNet features. Thereafter, the RPNet feature set is subjected to dimension reduction through principal component analysis (PCA) and the extracted components are filtered using the RF procedure. Finally, HSI spectral features and the obtained RPNet-RF features are combined to classify the HSI using a support vector machine (SVM) classifier. In order to test the performance of the proposed RPNet-RF method, some experiments were performed on three widely known datasets using a few training samples for each class and classification results were compared with those obtained by other advanced HSI classification methods adopted for small training samples. The comparison showed that the RPNet-RF classification is characterized by higher values of such evaluation metrics as overall accuracy and Kappa coefficient (https://github.com/UchaevD/RPNet-RF).

show abstract