Linear reconstruction of perceived images from human brain activity

Sanne Schoenmakers (Corresponding author), Markus Barth, Tom Heskes, Marcel van Gerven

Research output: Contribution to journalArticleAcademicpeer-review

94 Citations (Scopus)


With the advent of sophisticated acquisition and analysis techniques, decoding the contents of someone's experience has become a reality. We propose a straightforward linear Gaussian approach, where decoding relies on the inversion of properly regularized encoding models, which can still be solved analytically. In order to test our approach we acquired functional magnetic resonance imaging data under a rapid event-related design in which subjects were presented with handwritten characters. Our approach is shown to yield state-of-the-art reconstructions of perceived characters as estimated from BOLD responses. This even holds for previously unseen characters. We propose that this framework serves as a baseline with which to compare more sophisticated models for which analytical inversion is infeasible.
Original languageEnglish
Pages (from-to)951-961
Number of pages10
Publication statusPublished - Dec 2013
Externally publishedYes

Bibliographical note

In the media:


  • fMRI analysis
  • image reconstruction
  • linear regression
  • regularisation
  • Bayes Theorem


Dive into the research topics of 'Linear reconstruction of perceived images from human brain activity'. Together they form a unique fingerprint.

Cite this