English

Semi-Blind Spatially-Variant Deconvolution in Optical Microscopy with Local Point Spread Function Estimation By Use Of Convolutional Neural Networks

Computer Vision and Pattern Recognition 2019-05-21 v4 Machine Learning

Abstract

We present a semi-blind, spatially-variant deconvolution technique aimed at optical microscopy that combines a local estimation step of the point spread function (PSF) and deconvolution using a spatially variant, regularized Richardson-Lucy algorithm. To find the local PSF map in a computationally tractable way, we train a convolutional neural network to perform regression of an optical parametric model on synthetically blurred image patches. We deconvolved both synthetic and experimentally-acquired data, and achieved an improvement of image SNR of 1.00 dB on average, compared to other deconvolution algorithms.

Keywords

Cite

@article{arxiv.1803.07452,
  title  = {Semi-Blind Spatially-Variant Deconvolution in Optical Microscopy with Local Point Spread Function Estimation By Use Of Convolutional Neural Networks},
  author = {Adrian Shajkofci and Michael Liebling},
  journal= {arXiv preprint arXiv:1803.07452},
  year   = {2019}
}

Comments

2018/02/11: submitted to IEEE ICIP 2018 - 2018/05/04: accepted to IEEE ICIP 2018

R2 v1 2026-06-23T00:58:57.417Z