Monogenic Wavelet Scattering Network for Texture Image Classification

TL;DR

This paper introduces a Monogenic Wavelet Scattering Network (MWSN) that enhances texture image classification by extracting hierarchical, directional features with interpretability, outperforming standard scattering networks on the CUReT database.

Contribution

The paper proposes a novel MWSN that replaces 2D Morlet wavelet filtering with monogenic wavelet filtering, improving feature extraction for texture classification.

Findings

MWSN outperforms standard STN on CUReT database.

Hierarchical and directional features are effectively extracted.

Features can be compressed with PCA for classification.

Abstract

The scattering transform network (STN), which has a similar structure as that of a popular convolutional neural network except its use of predefined convolution filters and a small number of layers, can generates a robust representation of an input signal relative to small deformations. We propose a novel Monogenic Wavelet Scattering Network (MWSN) for 2D texture image classification through a cascade of monogenic wavelet filtering with nonlinear modulus and averaging operators by replacing the 2D Morlet wavelet filtering in the standard STN. Our MWSN can extract useful hierarchical and directional features with interpretable coefficients, which can be further compressed by PCA and fed into a classifier. Using the CUReT texture image database, we demonstrate the superior performance of our MWSN over the standard STN. This performance improvement can be explained by the natural extension of 1D analyticity to 2D monogenicity.