The relationship between local feature distributions and object recognition | Zendy

H. Galperin | Zendy; Peter J. Bex | Zendy; József Fiser | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

The relationship between local feature distributions and object recognition

Author(s) -

H. Galperin,

Peter J. Bex,

József Fiser

Publication year - 2010

Publication title -

journal of vision

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 1.126

H-Index - 113

ISSN - 1534-7362

DOI - 10.1167/8.6.519

Subject(s) - artificial intelligence , contrast (vision) , pattern recognition (psychology) , grayscale , feature (linguistics) , orientation (vector space) , computer vision , wavelet , computer science , coherence (philosophical gambling strategy) , noise (video) , luminance , mathematics , image (mathematics) , statistics , philosophy , linguistics , geometry

• Edge filters can produce successful computational models (Bell & Sejnowskii, 1997) • Aligned orientations are important for contour detection (Field, Hayes & Hess, 1993) • Junctions may not be detected by local sensors (McDermott, 2004) •Regions of curvature may define important features (Biederman, 1987) •Junctions involved in judging shape, transparency, and reflectance (Malik, 1987) (Anderson, 1997) (Adelson, 1993) • Computational models of mid-level vision based upon junctions (Sajda &Finkel, 1995)

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research