Methods of combining multiple classifiers and their applications to handwriting recognition
Citations
6,527 citations
5,670 citations
Cites background or methods from "Methods of combining multiple class..."
...If the classifier outputs are interpreted as fuzzy membership values, belief values or evidence, fuzzy rules [4], [5], belief functions and Dempster-Shafer techniques [9], [18], [20], [23] are used....
[...]
...If continuous outputs like posteriori probabilities are supplied, an average or some other linear combination have been suggested [11], [23], [25], [33]....
[...]
...This can be achieved by using different feature sets [23], [13] as well as by different training sets, randomly selected [12], [22] or based on a cluster analysis [3]....
[...]
5,632 citations
Cites background from "Methods of combining multiple class..."
...been widely suggested more recently, for example by Lincoln & Skrzypek (1990); Bridle & Cox (1991); Wolpert (1992); Xu et al. (1992) ; Perrone & Cooper (1993)....
[...]
3,821 citations
3,765 citations
References
15,671 citations
14,565 citations
5,112 citations
4,546 citations