Scattering Transform using Randomized Averages
TL;DR: The purpose of this work aims at implementation of scattering transform using random projection based averages which could result in better high frequency reconstruction and computation speed.
read more
Abstract: The purpose of this work aims at implementation of scattering transform using random projection based averages which could result in better high frequency reconstruction and computation speed. First Scattering transform is applied on the image and first order coefficients are extracted. For computing the second order coefficients random projection averaged values of the first order values are used to compute next level transform. The results show that the edge quality of the image is enhanced and run-time of the method got reduced.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
References
•Book
A wavelet tour of signal processing
Stéphane Mallat
- 01 Jan 1998
TL;DR: An introduction to a Transient World and an Approximation Tour of Wavelet Packet and Local Cosine Bases.
20.3K
Ten Lectures on Wavelets
TL;DR: In this article, the regularity of compactly supported wavelets and symmetry of wavelet bases are discussed. But the authors focus on the orthonormal bases of wavelets, rather than the continuous wavelet transform.
14.2K
An iterative technique for the rectification of observed distributions
TL;DR: In this article, the authors consider the problem of determining the distribution of proper motions in a line-of-sight line of sight (LoSOS) image from a given number count.
4.2K
Signal estimation from modified short-time Fourier transform
D. Griffin,Jae Lim +1 more
TL;DR: An algorithm to estimate a signal from its modified short-time Fourier transform (STFT) by minimizing the mean squared error between the STFT of the estimated signal and the modified STFT magnitude is presented.
Invariant Scattering Convolution Networks
Joan Bruna,Stéphane Mallat +1 more
TL;DR: The mathematical analysis of wavelet scattering networks explains important properties of deep convolution networks for classification.