Dual-Tree Wavelet Scattering Network with Parametric Log Transformation for Object Classification
This work addresses image classification problems for computer vision applications, but it appears incremental as it builds upon existing ScatterNet methods.
The paper tackled improving translation invariant representations for object classification by introducing a ScatterNet with parametric log transformation and Dual-Tree complex wavelets, resulting in outperforming Mallat's ScatterNet in classification accuracy and computational efficiency on two image datasets.
We introduce a ScatterNet that uses a parametric log transformation with Dual-Tree complex wavelets to extract translation invariant representations from a multi-resolution image. The parametric transformation aids the OLS pruning algorithm by converting the skewed distributions into relatively mean-symmetric distributions while the Dual-Tree wavelets improve the computational efficiency of the network. The proposed network is shown to outperform Mallat's ScatterNet on two image datasets, both for classification accuracy and computational efficiency. The advantages of the proposed network over other supervised and some unsupervised methods are also presented using experiments performed on different training dataset sizes.