Wavelet based edge feature enhancement for convolutional neural networks

TL;DR

This paper introduces two wavelet-based preprocessing methods to enhance edge features in input images for CNNs, leading to improved accuracy in image classification tasks.

Contribution

The paper proposes novel wavelet-based preprocessing layers for CNNs that enhance edge features, demonstrating significant accuracy improvements over existing methods.

Findings

Enhanced edge features improve CNN accuracy

Wavelet-based preprocessing outperforms baseline methods

Methods show significant accuracy gains in experiments

Abstract

Convolutional neural networks are able to perform a hierarchical learning process starting with local features. However, a limited attention is paid to enhancing such elementary level features like edges. We propose and evaluate two wavelet-based edge feature enhancement methods to preprocess the input images to convolutional neural networks. The first method develops feature enhanced representations by decomposing the input images using wavelet transform and limited reconstructing subsequently. The second method develops such feature enhanced inputs to the network using local modulus maxima of wavelet coefficients. For each method, we have developed a new preprocessing layer by implementing each purposed method and have appended to the network architecture. Our empirical evaluations demonstrate that the proposed methods are outperforming the baselines and previously published work with significant accuracy gains.