Journal ArticleDOI
Methods of combining multiple classifiers and their applications to handwriting recognition
Lei Xu,Adam Krzyżak,Ching Y. Suen +2 more
- Vol. 22, Iss: 3, pp 418-435
Reads0
Chats0
TLDR
On applying these methods to combine several classifiers for recognizing totally unconstrained handwritten numerals, the experimental results show that the performance of individual classifiers can be improved significantly.Abstract:
Possible solutions to the problem of combining classifiers can be divided into three categories according to the levels of information available from the various classifiers. Four approaches based on different methodologies are proposed for solving this problem. One is suitable for combining individual classifiers such as Bayesian, k-nearest-neighbor, and various distance classifiers. The other three could be used for combining any kind of individual classifiers. On applying these methods to combine several classifiers for recognizing totally unconstrained handwritten numerals, the experimental results show that the performance of individual classifiers can be improved significantly. For example, on the US zipcode database, 98.9% recognition with 0.90% substitution and 0.2% rejection can be obtained, as well as high reliability with 95% recognition, 0% substitution, and 5% rejection. >read more
Citations
More filters
Book ChapterDOI
Discriminant independent component analysis
TL;DR: Experimental results show improved classification performance when dICA features are used for recognition tasks in comparison to unsupervised (principal component analysis and ICA) and supervised feature extraction techniques like linear discriminant analysis (LDA), conditional ICA, and those based on information theoretic learning approaches.
Journal ArticleDOI
Data dependency in multiple classifier systems
TL;DR: It can be concluded that data-dependent aggregation methods are generally more stable and less sensitive to class imbalance than data-independent methods, and exhibited superior or identical generalization ability for most of the data sets.
A Comparative Study of Different Feature Extraction and Classification Methods for Recognition of Handwritten Kannada Numerals
TL;DR: A variety of feature extraction approaches and classification methods which have been used in various Optical Character Recognition applications which are designed to recognize handwritten numerals of Kannada script are examined.
Patent
Self-designing intelligent signal processing system capable of evolutional learning for classification/recognition of one and multidimensional signals
TL;DR: In this article, a self-designing Intelligent Signal Processing System is described which classifies data by an evolutionary learning environment that develops the features and algorithms that are best suited for the recognition problem under consideration.
Proceedings ArticleDOI
A Novel Confidence-Based Framework for Multiple Expert Decision Fusion
TL;DR: A novel confidence-based parallel multiple expert decision combination framework is introduced and very encouraging results have been obtained by implementing this proposed framework in combining decisions of multiple experts applied to the problem of handwritten and machine printed character recognition.
References
More filters
Book
Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference
TL;DR: Probabilistic Reasoning in Intelligent Systems as mentioned in this paper is a complete and accessible account of the theoretical foundations and computational methods that underlie plausible reasoning under uncertainty, and provides a coherent explication of probability as a language for reasoning with partial belief.
Book
A mathematical theory of evidence
TL;DR: This book develops an alternative to the additive set functions and the rule of conditioning of the Bayesian theory: set functions that need only be what Choquet called "monotone of order of infinity." and Dempster's rule for combining such set functions.
Journal ArticleDOI
Statistical and structural approaches to texture
TL;DR: This survey reviews the image processing literature on the various approaches and models investigators have used for texture, including statistical approaches of autocorrelation function, optical transforms, digital transforms, textural edgeness, structural element, gray tone cooccurrence, run lengths, and autoregressive models.
Journal ArticleDOI
An introduction to hidden Markov models
TL;DR: The purpose of this tutorial paper is to give an introduction to the theory of Markov models, and to illustrate how they have been applied to problems in speech recognition.