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 presents an HSI classification method that combines random patches network (RPNet) and recursive 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, the 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.
The multifractal spectra of electronic images of fossil coal surfaces obtained from outburst-hazardous zones, outburst-nonhazardous (quiet) zones and outburst zones are studied. It is shown that the structural organization of coal surface elements can be represented by a multifractal with a corresponding f (α) -spectrum of fractal dimensions, which is suitable to determine quantitative difference in microstructures of coal specimens from outburst-hazardous and outburst-nonhazardous beds. Coals from outburst-hazardous and outburst-nonhazardous beds differ in the direction of skewness of multifractal spectra characterizing their surface structure. If the f (α) -spectrum is skewed to the right, then the analyzed coal specimen belongs to an outburst-hazardous bed, and on the contrary, if f (α) is skewed to the left, then it can be concluded that the coal specimen most likely belongs to an outburst-nonhazardous bed.
We present a technique for automated restoration of digital images obtained from faded photographic prints. The proposed defading technique uses our early proposed image contrast enhancement algorithm based on a contrast measure of images in the Chebyshev moment transform domain. Obtained experimental results demonstrate some advantages of the technique as compared to other widely used image enhancement methods.
Работа посвящена вопросу повышения качества аномальных гравитационных полей путем снижения уровня содержащихся в них высокочастотных помех. Приведен краткий обзор существующих подходов и методов подавления высокочастотных помех в полях гравитационных аномалий. Предложен метод фильтрации полей гравитационных аномалий, основанный на преобразовании, выполняемом в области моментов Чебышева. Приведены эмпирически установленные значения коэффициентов предложенного фильтра, использование которых оказывается целесообразным при неизвестном уровне помех. На примере смоделированной карты аномалий гравитационного поля продемонстрировано, что предложенный фильтр подавления помех сопоставим по скорости и превосходит по качеству результата такие фильтры, как билатеральный фильтр, вейвлет-фильтр, фильтры нелокального усреднения, а также хорошо зарекомендовавший себя в практике предварительной обработки гравитационных полей фильтр Винера.