Extraction of Surface-Related Features in a Recurrent Model of V1-V2 Interactions
Ulrich Weidenbacher, Heiko Neumann · 2009
Read Extraction of Surface-Related Features in a Recurrent Model of V1-V2 Interactions by Ulrich Weidenbacher, Heiko Neumann (2009) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0005909.txt.
Description
Ulrich Weidenbacher and Heiko Neumann modeled in 2009 how the visual brain pulls surfaces out of flat images. We segment objects effortlessly, yet a two-dimensional retinal image loses depth whenever one surface hides another. Somehow the brain rebuilds the hidden wholes.
Their recurrent model links the first two visual areas, V1 and V2, in loops that extract surface-related features. Feedback between the areas helps resolve occlusions, borders, and partly hidden edges in the scene. Such models guide both neuroscience experiments and computer vision design. The work turns a perceptual gift into explicit, testable circuitry.
Catalog record
| CREATOR | Ulrich Weidenbacher, Heiko Neumann |
|---|---|
| YEAR | 2009 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 82 KB |
| LICENSE | Creative Commons Attribution License |
| RIGHTS | CC BY |
| SOURCE | PLOS ONE |
Source: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0005909