Robust object recognition with cortex-like mechanisms

DMCA

Robust object recognition with cortex-like mechanisms (2007)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Thomas Serre , Lior Wolf , Stanley Bileschi , Maximilian Riesenhuber , Tomaso Poggio

Venue:	IEEE Trans. Pattern Analysis and Machine Intelligence
Citations:	381 - 42 self

BibTeX

@ARTICLE{Serre07robustobject,
    author = {Thomas Serre and Lior Wolf and Stanley Bileschi and Maximilian Riesenhuber and Tomaso Poggio},
    title = {Robust object recognition with cortex-like mechanisms},
    journal = {IEEE Trans. Pattern Analysis and Machine Intelligence},
    year = {2007},
    pages = {411--426}
}

OpenURL

Abstract

Abstract—We introduce a new general framework for the recognition of complex visual scenes, which is motivated by biology: We describe a hierarchical system that closely follows the organization of visual cortex and builds an increasingly complex and invariant feature representation by alternating between a template matching and a maximum pooling operation. We demonstrate the strength of the approach on a range of recognition tasks: From invariant single object recognition in clutter to multiclass categorization problems and complex scene understanding tasks that rely on the recognition of both shape-based as well as texture-based objects. Given the biological constraints that the system had to satisfy, the approach performs surprisingly well: It has the capability of learning from only a few training examples and competes with state-of-the-art systems. We also discuss the existence of a universal, redundant dictionary of features that could handle the recognition of most object categories. In addition to its relevance for computer vision, the success of this approach suggests a plausibility proof for a class of feedforward models of object recognition in cortex.

Keyphrases

robust object recognition cortex-like mechanism object category maximum pooling operation complex scene plausibility proof invariant single object recognition hierarchical system texture-based object visual cortex state-of-the-art system computer vision new general framework categorization problem template matching recognition task feedforward model complex visual scene invariant feature representation redundant dictionary training example object recognition biological constraint

DMCA