A visual object recognition system invariant to scale and rotation

Yasuomi D. Sato, Jenia Jitsev, Christoph von der Malsburg

Abstract

We here address the problem of scale and orientation invariant object recognition, making use of a correspondence-based mechanism, in which the identity of an object represented by sensory signals is determined by matching it to a representation stored in memory. The sensory representation is in general affected by various transformations, notably scale and rotation, thus giving rise to the fundamental problem of invariant object recognition. We focus here on a neurally plausible mechanism that deals simultaneously with identification of the object and detection of the transformation, both types of information being important for visual processing. Our mechanism is based on macrocolumnar units. These evaluate identity- and transformation-specific feature similarities, performing competitive computation on the alternatives of their own subtask, and cooperate to make a coherent global decision for the identity, scale and rotation of the object.
BibTeX
@inproceedings{sato2008visual,
  author = {Yasuomi D. Sato and Jenia Jitsev and Christoph von der Malsburg},
  title = {{A visual object recognition system invariant to scale and rotation}},
  booktitle = {ICANN},
  year = {2008},
  url = {https://openreview.net/forum?id=hzlO4xtc01},
}

Loading related content...

Figure