Wavelet based edge feature enhancement for convolutional neural networks
This work addresses the enhancement of edge features in CNNs for image processing tasks, representing an incremental improvement in preprocessing techniques.
The paper tackled the problem of limited attention to elementary edge features in convolutional neural networks by proposing two wavelet-based preprocessing methods, which resulted in significant accuracy gains over baselines and prior work.
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.