Robust Object Recognition with Cortex-Like Mechanisms

@article{Serre2007RobustOR,
  title={Robust Object Recognition with Cortex-Like Mechanisms},
  author={Thomas Serre and Lior Wolf and Stanley M. Bileschi and Maximilian Riesenhuber and Tomaso A. Poggio},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2007},
  volume={29},
  pages={411-426}
}
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… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 1,152 CITATIONS

BINK: Biological binary keypoint descriptor

VIEW 12 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

On Rendering Synthetic Images for Training an Object Detector

  • Computer Vision and Image Understanding
  • 2015
VIEW 13 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

A biologically inspired human posture recognition system

VIEW 15 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Predictive feedback to the primary visual cortex during saccades

VIEW 6 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Hierarchical Feature Extraction With Local Neural Response for Image Recognition

  • IEEE Transactions on Cybernetics
  • 2013
VIEW 16 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Biologically Inspired Features for Scene Classification in Video Surveillance

  • IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)
  • 2011
VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Dorsal stream: from algorithm to neuroscience

VIEW 20 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Probabilistic methods for pose-invariant recognition in computer vision

VIEW 10 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2005
2019

CITATION STATISTICS

  • 211 Highly Influenced Citations

  • Averaged 62 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 68 REFERENCES

Object class recognition by unsupervised scale-invariant learning

  • 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.
  • 2003
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL