Statistic Metrics for Evaluation of Binary Classifiers without Ground-Truth

Abstract : In this paper, are presented a number of statistically grounded performance evaluation metrics capable of evaluating binary classifiers in absence of annotated Ground Truth. These metrics are generic and can be applied to any type of classifier but are experimentally validated on binarization algorithms. The statistically grounded metrics were applied and compared with metrics based on annotated data. This approach has statistically significant better than random results in classifiers selection, and our evaluation metrics requiring no Ground Truth have high correlation with traditional metrics. The experiments were conducted on the images from the DIBCO binarization contests between 2009 and 2013.
Type de document :
Communication dans un congrès
IEEE First Ukraine Conference on Electrical and Computer Engineering (UKRCON) , May 2017, Kiev, Ukraine. IEEE, 2017, 〈http://ukrcon.ieee.org.ua/〉
Liste complète des métadonnées

https://hal.inria.fr/hal-01563615
Contributeur : Bart Lamiroy <>
Soumis le : lundi 17 juillet 2017 - 20:50:06
Dernière modification le : mardi 24 avril 2018 - 13:34:39
Document(s) archivé(s) le : samedi 27 janvier 2018 - 01:55:51

Fichier

UKRCON-2017_Doc_or_Tex_Paper_2...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01563615, version 1

Citation

Maksym Fedorchuk, Bart Lamiroy. Statistic Metrics for Evaluation of Binary Classifiers without Ground-Truth. IEEE First Ukraine Conference on Electrical and Computer Engineering (UKRCON) , May 2017, Kiev, Ukraine. IEEE, 2017, 〈http://ukrcon.ieee.org.ua/〉. 〈hal-01563615〉

Partager

Métriques

Consultations de la notice

199

Téléchargements de fichiers

126