Abstract | ||
---|---|---|
New computational models have made it possible to reconstruct perceived images from BOLD responses in visual cortex. We expand a linear Gaussian framework for percept decoding with Gaussian mixture models to better represent the prior distribution of images. In our setup, different mixture components correspond to different letter categories. Our framework not only leads to more accurate reconstructions, but also automatically infers semantic categories from low-level visual areas of the human brain. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/PRNI.2014.6858542 | PRNI |
Keywords | Field | DocType |
computational models,fmri-based image reconstruction,image distribution,image coding,low-level visual areas,semantic categories,bold responses,mixture models,visual cortex,image reconstruction,biomedical mri,gaussian processes,mixture components,brain,gaussian mixture models,perceived image reconstruction,visual perception,linear gaussian framework,decoding,medical image processing,human brain,measurement,visualization,semantics,gaussian mixture model | Iterative reconstruction,Computer vision,Visual cortex,Pattern recognition,Computer science,Computational model,Gaussian,Artificial intelligence,Decoding methods,Prior probability,Mixture model,Percept | Conference |
ISSN | Citations | PageRank |
2330-9989 | 3 | 0.40 |
References | Authors | |
5 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sanne Schoenmakers | 1 | 36 | 2.70 |
Marcel Van Gerven | 2 | 321 | 39.35 |
Tom Heskes | 3 | 1519 | 198.44 |