An approach to novelty detection applied to the classification of image regions

@article{Singh2004AnAT,
  title={An approach to novelty detection applied to the classification of image regions},
  author={Sameer Singh and Markos Markou},
  journal={IEEE Transactions on Knowledge and Data Engineering},
  year={2004},
  volume={16},
  pages={396-407}
}
We present a new framework for novelty detection. The framework evaluates neural networks as adaptive classifiers that are capable of novelty detection and retraining on the basis of newly discovered information. We apply our newly developed model to the application area of object recognition in video. We detail the tools and methods needed for novelty detection such that data from unknown classes can be reliably rejected without any a priori knowledge of its characteristics. The rejected data… CONTINUE READING

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-10 OF 69 CITATIONS

Novelty estimation in developmental networks: Acetylcholine and norepinephrine

  • The 2013 International Joint Conference on Neural Networks (IJCNN)
  • 2013
VIEW 7 EXCERPTS
CITES METHODS & RESULTS
HIGHLY INFLUENCED

Visual novelty detection for autonomous inspection robots

VIEW 8 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Time-based multi-layer perceptron for novelty detection in sensor networks

  • 2004 International Conference on Machine Learning and Applications, 2004. Proceedings.
  • 2004
VIEW 5 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Building virtual community in computational intelligence and machine learning [Research Frontier]

  • IEEE Computational Intelligence Magazine
  • 2009
VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Embedding intelligent sensor signal change detection into sensor network protocols

  • 2005 Second Annual IEEE Communications Society Conference on Sensor and Ad Hoc Communications and Networks, 2005. IEEE SECON 2005.
  • 2005
VIEW 3 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Signal change detection in sensor networks with artificial neural network structure

  • CIHSPS 2005. Proceedings of the 2005 IEEE International Conference on Computational Intelligence for Homeland Security and Personal Safety, 2005.
  • 2005
VIEW 3 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Demystifying Numenta anomaly benchmark

  • 2017 International Joint Conference on Neural Networks (IJCNN)
  • 2017

FILTER CITATIONS BY YEAR

2003
2019

CITATION STATISTICS

  • 6 Highly Influenced Citations

References

Publications referenced by this paper.
SHOWING 1-10 OF 53 REFERENCES

An Immunogenetic Approach to Intrusion Detection

D. Dasgupta, F. A. Gonzalez
  • Dept. of Computer Science, Univ. of Memphis, Report No. CS-01-001, May 2001.
  • 2001
VIEW 1 EXCERPT

Minerva scene analysis benchmark

Mona Sharma, Sameer Singh
  • The Seventh Australian and New Zealand Intelligent Information Systems Conference, 2001
  • 2001
VIEW 1 EXCERPT

Novelty Detection in Large Environments

S. Marsland, U. Nehmzow, J. Shapiro
  • Proc. Towards Intelligent Mobile Robots Conf., 2001.
  • 2001
VIEW 1 EXCERPT