Title :
On Evaluation of Image Auto-Annotation Methods
Author :
Kwasnicka, Halina ; Paradowski, Mariusz
Author_Institution :
Paradowski, M Inst. of Appl. Informatics, Wroclaw Univ. of Technol.
Abstract :
Image auto-annotation problem grows more and more popular among the literature. There are many approaches presented, but also many ways to measure the quality of those methods. This paper discusses various quality measures for the image auto-annotation problem. We focus on comparing them and discussing their important features. Experiments and achieved results are presented for a number of auto-annotation methods
Keywords :
image classification; Mori coocurence model; image auto-annotation; quality measurement; Arithmetic; Computer science; Dictionaries; Equations; Image generation; Informatics; Intelligent systems; Machine learning; Testing;
Conference_Titel :
Intelligent Systems Design and Applications, 2006. ISDA '06. Sixth International Conference on
Conference_Location :
Jinan
Print_ISBN :
0-7695-2528-8
DOI :
10.1109/ISDA.2006.253861
