Order statistics learning vector quantizer

@article{Pitas1996OrderSL,
  title={Order statistics learning vector quantizer},
  author={Ioannis Pitas and Constantine Kotropoulos and Nikos Nikolaidis and Ruan Yang and M. Gabbouj},
  journal={IEEE transactions on image processing : a publication of the IEEE Signal Processing Society},
  year={1996},
  volume={5 6},
  pages={
          1048-53
        }
}
We propose a novel class of learning vector quantizers (LVQs) based on multivariate data ordering principles. A special case of the novel LVQ class is the median LVQ, which uses either the marginal median or the vector median as a multivariate estimator of location. The performance of the proposed marginal median LVQ in color image quantization is demonstrated by experiments. 
View on PubMed
cs.tut.fi
27 Citations
Background Citations
4
Methods Citations
7

27 Citations

Citation Type

Citation Type

An axiomatic approach to soft learning vector quantization and clustering
TLDR
An axiomatic approach to soft learning vector quantization (LVQ) and clustering based on reformulation indicates that minimization of admissible reformulation functions using gradient descent leads to a broad variety of soft learning vectors quantization and clustered algorithms.
From Aggregation Operators to Soft Learning Vector Quantization and Clustering Algorithms
On the Variants of the Self-Organizing Map That Are Based on Order Statistics
TLDR
The marginal median SOM and the vector median SOM are used to re-distribute emotional speech patterns from the Danish Emotional Speech database that were originally classified as being neutral to four emotional states such as hot anger, happiness, sadness, and surprise.
Reformulating Learning Vector Quantization and Radial Basis Neural Networks
TLDR
It is shown that gradient descent learning makes reformulated RBF neural networks an attractive alternative to conventional feed-forward neural networks.
Soft learning vector quantization and clustering algorithms based on ordered weighted aggregation operators
  • N. Karayiannis
  • Computer Science
    IEEE Trans. Neural Networks Learn. Syst.
  • 2000
TLDR
The proposed LVQ and clustering algorithms are used to perform segmentation of magnetic resonance (MR) images of the brain and provide the basis for evaluating a variety of ordered weighted LVQ And Clustering algorithms.
Robust and adaptive techniques in self-organizing neural networks
TLDR
Applications that prove the superiority of the proposed variants of LVQ and RBF neural networks in noisy color image segmentation, color-based image recognition, segmentation of ultrasonic images, motion-field smoothing and moving object segmentation are outlined.
Robust RBF networks
TLDR
The Median RBF (MRBF) training algorithm and Alpha-Trimmed Mean RBF are introduced and the efficiency of MRBF and classical training using learning vector quantization are compared in estimating overlapping Gaussian distributions.
Optical flow estimation and moving object segmentation based on median radial basis function network
TLDR
In this study, the moving scene is decomposed into different regions with respect to their motion, by means of a pattern recognition scheme, using the median radial basis function (MRBF) neural network.
MM-WEBSOM: A VARIANT OF WEBSOM BASED ON ORDER STATISTICS
TLDR
A variant of the WEBSOM architecture for information retrieval is proposed, replacing the updating rule by employing the marginal median, to overcome the drawbacks of the standard technique in the presence of outliers in the training set and to use robust estimators of the reference vectors for each class.
Application of two non-linear methods for the localization of artifacts on trend data [medical]
  • L. Senhadji, N. Nikolaidis, J. Ojaniemi
  • Computer Science
    Proceedings of the 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 'Magnificent Milestones and Emerging Opportunities in Medical Engineering' (Cat. No.97CH36136)
  • 1997
TLDR
Two non-linear methods for the localization of transient artifacts on trend data are presented, based on the matching pursuit method and a multi-dimensional technique which makes use of a particular neural network, namely the marginal median linear vector quantizer.
...
1
2
3
...

References

SHOWING 1-10 OF 24 REFERENCES
An Algorithm for Vector Quantizer Design
An efficient and intuitive algorithm is presented for the design of vector quantizers based either on a known probabilistic model or on a long training sequence of data. The basic properties of the…
Competitive learning and soft competition for vector quantizer design
TLDR
By incorporating the principles of the stochastic approach into the KLA, a deterministic VQ design algorithm, the soft competition scheme (SCS), is introduced and experimental results are presented where the SCS consistently provided better codebooks than the generalized Lloyd algorithm (GLA), even when the same computation time was used for both algorithms.
Vector median filters
Greedy tree growing for color image quantization
  • Tsann-Shyong Liu, Long-Wen Chang
  • Art, Computer Science
    Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing
  • 1994
TLDR
An algorithm to design the K-color palette by an unbalanced greedy binary tree is proposed, which splits the node with largest error reduction into two children by a hyperplane perpendicular to one of r,g,b axis among available nodes in the tree.
Color quantization of images based on human vision perception
  • N. Chaddha, Wee-Chiew Tan, T. Meng
  • Computer Science
    Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing
  • 1994
TLDR
A subjective distortion measure is developed which accounts for the higher sensitivity of the human visual system to errors in low activity areas compared toerrors in high activity areas and a color quantization algorithm is proposed which is applied to a cubic prequantizer and a weighted tree structured vector quantizer to obtain the final 8-bit color palette.
Color quantization of images
TLDR
The authors develop algorithms for the design of hierarchical tree structured color palettes incorporating performance criteria which reflect subjective evaluations of image quality, which produce higher-quality displayed images and require fewer computations than previously proposed methods.
The weighted median filter
TLDR
The Weighted Median Filter is described, a more general filter that enables filters to be designed with a wide variety of properties and the question of finding the number of distinct ways a class of filters can act is considered and solved for some classes.
Color image quantization for frame buffer display
TLDR
It is demonstrated that many color images which would normally require a frame buffer having 15 bits per pixel can be quantized to 8 or fewerbits per pixel with little subjective degradation.
Some methods for classification and analysis of multivariate observations
The main purpose of this paper is to describe a process for partitioning an N-dimensional population into k sets on the basis of a sample. The process, which is called 'k-means,' appears to give…
Nonlinear Digital Filters - Principles and Applications
TLDR
This chapter discusses digital filters based on order statistics, Morphological image and signal processing, and Adaptive nonlinear filters.
...
1
2
3
...