Evaluation of combination methods

Author

Impedovo, S. ; Salzo, A.

Author_Institution

Dipt. di Inf., Bari Univ., Italy

fYear

1999

fDate

20-22 Sep 1999

Firstpage

394

Lastpage

397

Abstract

This paper presents a new approach to evaluate the performances of combination methods, which takes into account both the recognition rates of the experts combined and the correlation among them. At the purpose, a suitable estimator of correlation is defined. Two combination methods have been considered: majority vote and Dempster Shafer. A statistical test, based on the analysis of variance, has also been used to infer some interesting considerations on the behaviour of combination methods. The paper shows how the proposed approach allows the selection of the best combination method for each set of experts

Keywords

expert systems; inference mechanisms; optical character recognition; statistical analysis; Dempster Shafer method; combination methods; correlation estimator; experts; majority vote method; performance evaluation; recognition rates; statistical test; variance analysis; Analysis of variance; Character recognition; Degradation; Handwriting recognition; Optical character recognition software; Performance analysis; Postal services; Statistical analysis; Testing; Voting;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Analysis and Recognition, 1999. ICDAR '99. Proceedings of the Fifth International Conference on

Conference_Location

Bangalore

Print_ISBN

0-7695-0318-7

Type

conf

DOI

10.1109/ICDAR.1999.791807

Filename

791807