logo Idiap Research Institute        
 [BibTeX] [Marc21]
Semi-blind spatially-variant deconvolution in optical microscopy with local Point Spread Function estimation by use of Convolutional Neural Networks
Type of publication: Idiap-RR
Citation: Shajkofci_Idiap-RR-07-2018
Number: Idiap-RR-07-2018
Year: 2018
Month: 6
Institution: Idiap
Note: Accepted to IEEE ICIP 2018
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.
Projects Idiap
Authors Shajkofci, Adrian
Liebling, Michael
Crossref by Shajkofci_ICIP2018_2018
Added by: [ADM]
Total mark: 0
  • Shajkofci_Idiap-RR-07-2018.pdf (MD5: 481f239d0b44471f10d59ac8450fd3e3)