In this work, we propose a very simple deep learning network for image classification which comprises only the very basic data processing components: cascaded principal component analysis (PCA), binary hashing, and block-wise histograms.
#15 best model for Image Classification on MNIST
Thereby, we rely on the freely available LUCAS topsoil dataset.
Its architecture is indeed well suited to object analysis by learning and classifying complex (deep) features that represent parts of an object or the object itself.
We propose a novel CNN architecture, wavelet CNNs, which integrates a spectral analysis into CNNs.
In this paper we propose a novel texture descriptor called Fractal Weighted Local Binary Pattern (FWLBP).
Texture is one of the most-studied visual attribute for image characterization since the 1960s.
One important point is that all applications of BSIF in iris recognition have used the original BSIF filters, which were trained on image patches extracted from natural images.