A similarity value transformation method for probabilistic scoring

Author

Segawa, Hideo ; Ukita, Teruhiko

Author_Institution

Toshiba Res. & Dev. Center, Kawasaki, Japan

fYear

1988

fDate

14-17 Nov 1988

Firstpage

1225

Abstract

A method to transform a similarity measure into a probability measure which indicates the reliability of classification is shown. A statistical model for the similarity value distribution is introduced for efficient estimation from a small number of samples. It is theoretically derived that the similarity value distribution in the multiple similarity method belongs to the family of Γ distribution under this model. Several experiments were carried out to give support to the similarity value distribution model. It is shown that the estimated posterior probability using the proposed method proves effective for pattern recognition, such as connected-digit speech recognition

Keywords

pattern recognition; probability; Γ distribution; connected-digit speech recognition; pattern recognition; posterior probability; probabilistic scoring; probability measure; similarity measure; similarity value transformation method; Character recognition; Distribution functions; Gaussian distribution; Pattern recognition; Performance evaluation; Research and development; Speech processing; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 1988., 9th International Conference on

Conference_Location

Rome

Print_ISBN

0-8186-0878-1

Type

conf

DOI

10.1109/ICPR.1988.28477

Filename

28477