Texture Classification is a fundamental issue in computer vision and image processing, playing a significant role in many applications such as medical image analysis, remote sensing, object recognition, document analysis, environment modeling, content-based image retrieval and many more.
Source: Improving Texture Categorization with Biologically Inspired Filtering
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.
Ranked #16 on
Image Classification
on MNIST
FACE RECOGNITION FACE VERIFICATION IMAGE CLASSIFICATION OBJECT RECOGNITION TEXTURE CLASSIFICATION
Thereby, we rely on the freely available LUCAS topsoil dataset.
We propose a novel CNN architecture, wavelet CNNs, which integrates a spectral analysis into CNNs.
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.
For that reason, transforming these diagrams in a way that is compatible with machine learning is an important topic currently researched in TDA.
Given that spatial and spectral approaches are known to have different characteristics, it will be interesting to incorporate a spectral approach into CNNs.
IMAGE CLASSIFICATION OBJECT RECOGNITION TEXTURE CLASSIFICATION
We present a histogram layer for artificial neural networks (ANNs).
As image generation techniques mature, there is a growing interest in explainable representations that are easy to understand and intuitive to manipulate.
Locally Rotation Invariant (LRI) image analysis was shown to be fundamental in many applications and in particular in medical imaging where local structures of tissues occur at arbitrary rotations.
Texture is one of the most-studied visual attribute for image characterization since the 1960s.